Skip to content

Select batched memcpy flags by copy size #23675

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bdice wants to merge 3 commits into
base: main
Choose a base branch
from
+13 −9
Open

Select batched memcpy flags by copy size #23675

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
375cda0
Select batched memcpy flag by copy size
bdice Aug 16, 2026
6788608
Merge branch 'main' into fix/cuda-memcpy-batch-threshold
bdice Aug 17, 2026
97896d5
Fix batched memcpy builds across CUDA versions
bdice Aug 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions cpp/include/cudf/detail/utilities/cuda_memcpy.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/

Expand Down Expand Up @@ -28,10 +28,8 @@ void cuda_memcpy_async_impl(
* satisfied, but for host memory the caller must ensure the source is not freed before the stream
* is synchronized.
*
* All copies share a single attribute entry (`cudaMemcpySrcAccessOrderStream` +
* `cudaMemcpyFlagPreferOverlapWithCompute`). Per-copy attributes are not supported by this
* wrapper; callers requiring different attributes per copy should call `cudaMemcpyBatchAsync`
* directly.
* A batch uses `cudaMemcpyFlagPreferOverlapWithCompute` when every copy is 128 KiB or less. If
* any copy is larger, the batch uses `cudaMemcpyFlagDefault`.
*
* @param dsts Host pointer to a list of destination pointers.
* @param srcs Host pointer to a list of source pointers.
Expand Down
14 changes: 10 additions & 4 deletions cpp/src/utilities/cuda_memcpy.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,8 @@ cudaError_t memcpy_batch_async(void* const* dsts,
// cudaMemcpyBatchAsync does not support the default stream.
#if CUDART_VERSION >= 13000
if (!stream.is_default()) {
constexpr std::size_t prefer_overlap_threshold = 128 * 1024;

// Filter out invalid copies (nullptr dst/src or size==0);
// cudaMemcpyBatchAsync does not support these inputs
auto is_invalid = [&](auto i) {
Expand Down Expand Up @@ -90,10 +92,14 @@ cudaError_t memcpy_batch_async(void* const* dsts,
count = valid_dsts.size();
}

cudaMemcpyAttributes attrs = {.srcAccessOrder = cudaMemcpySrcAccessOrderStream,
.flags = cudaMemcpyFlagPreferOverlapWithCompute};
std::size_t attrs_idxs = 0;
return cudaMemcpyBatchAsync(dsts, srcs, sizes, count, &attrs, &attrs_idxs, 1, stream.value());
unsigned int const flags =
std::ranges::any_of(std::ranges::views::iota(std::size_t{0}, count),
[&](auto i) { return sizes[i] > prefer_overlap_threshold; })
? cudaMemcpyFlagDefault
: cudaMemcpyFlagPreferOverlapWithCompute;
cudaMemcpyAttributes attrs = {.srcAccessOrder = cudaMemcpySrcAccessOrderStream, .flags = flags};
std::size_t attrs_idx = 0;
return cudaMemcpyBatchAsync(dsts, srcs, sizes, count, &attrs, &attrs_idx, 1, stream.value());
}
#endif // CUDART_VERSION >= 13000
for (std::size_t i = 0; i < count; ++i) {
Expand Down
Loading