Chunk the D2H copy across N copy threads (#6068) - #6068
Open
FriedCosey wants to merge 2 commits into
Open
Conversation
Contributor
|
@FriedCosey has exported this pull request. If you are a Meta employee, you can view the originating Diff in D113594180. |
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 25, 2026
…ytorch#6068) Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 25, 2026
…ytorch#6068) Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 25, 2026
…ytorch#6068) Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
meta-codesync
Bot
changed the title
FriedCosey
force-pushed
the
export-D113594180
branch
from
July 30, 2026 08:47
9030371 to
198f306
Compare
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 30, 2026
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
added 2 commits
July 30, 2026 01:53
Summary: The no-fbcode streamer test compiled the header with FBGEMM_FBCODE off but linked the always-flag-on :raw_embedding_streamer, so the flag-on constructor overran the smaller flag-off object layout → ASan heap-buffer-overflow (pre-existing latent bug). Fix: link the test against a new -UFBGEMM_FBCODE build, :raw_embedding_streamer_no_fbcode, so its header view matches the library layout; switch the test include to the short form so it resolves via fbgemm_gpu's include/ dir instead of the manual pin to the flag-on lib. Differential Revision: D114193888
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
force-pushed
the
export-D113594180
branch
from
July 30, 2026 08:54
198f306 to
51f7189
Compare
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 30, 2026
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 30, 2026
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 30, 2026
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
FriedCosey
pushed a commit
to FriedCosey/FBGEMM
that referenced
this pull request
Jul 30, 2026
Summary: X-link: facebookresearch/FBGEMM#2968 Speed up the RES C++ streamer's device->host copy by parallelizing it. Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to `kNumCopyThreads` threads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges(). Differential Revision: D113594180
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
X-link: https://github.com/facebookresearch/FBGEMM/pull/2968
Speed up the RES C++ streamer's device->host copy by parallelizing it.
Previously stream() copied all updated rows to CPU on a single thread and enqueued one item. This replaces that serial copy with a chunked copy across up to
kNumCopyThreadsthreads: tensor_copy_chunk() copies a [start, end) row range, and the per-thread tiling is factored into a pure, unit-testable computeChunkRanges().Differential Revision: D113594180