Add GEMM-based standard SDPA benchmark#18646
Open
kimishpatel wants to merge 17 commits into
Open
Conversation
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18646
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 Cancelled Jobs, 4 Unrelated FailuresAs of commit 7e7896f with merge base 1debeb6 ( CANCELLED JOBS - The following jobs were cancelled. Please retry:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Apr 1, 2026
digantdesai
approved these changes
Apr 1, 2026
digantdesai
left a comment
digantdesai
left a comment
Contributor
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
This PR needs a
|
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
This was referenced Apr 6, 2026
Closed
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation (run_standard_sdpa) alongside ExecuTorch's tiled flash attention (custom_sdpa_out) for comparative benchmarking. The standalone SDPA uses full GEMM per head with 3-pass softmax and supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading dimension parameters, allowing isolation of algorithm vs layout effects. Includes validation tests that verify the GEMM-based implementation matches custom_sdpa_out within tolerance. Differential Revision: [D96044313](https://our.internmc.facebook.com/intern/diff/D96044313/) [ghstack-poisoned]
|
Hi @kimishpatel! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
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
2 participants
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.
Stack from ghstack (oldest at bottom):
Add bench_sdpa.cpp with a standalone GEMM-based SDPA implementation
(run_standard_sdpa) alongside ExecuTorch's tiled flash attention
(custom_sdpa_out) for comparative benchmarking.
The standalone SDPA uses full GEMM per head with 3-pass softmax and
supports both [B,S,H,D] and [B,H,S,D] layouts via BLAS leading
dimension parameters, allowing isolation of algorithm vs layout effects.
Includes validation tests that verify the GEMM-based implementation
matches custom_sdpa_out within tolerance.
Differential Revision: D96044313