forked from NVIDIA/cutlass
-
Notifications
You must be signed in to change notification settings - Fork 71
Rewrite mma unit tests #557
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.
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
Merged
Merged
Conversation
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
6f44bc8 to
6e2a6ac
Compare
97b9cf6 to
2202405
Compare
tdeng5
approved these changes
Dec 9, 2025
2efd984 to
648d6a6
Compare
tdeng5
reviewed
Dec 9, 2025
648d6a6 to
4eadb54
Compare
tdeng5
reviewed
Dec 10, 2025
tdeng5
approved these changes
Dec 17, 2025
f91af3e to
f6d0588
Compare
tdeng5
approved these changes
Dec 25, 2025
taozha2
approved these changes
Dec 25, 2025
auto-merge was automatically disabled
December 26, 2025 03:35
Head branch was pushed to by a user without write access
tdeng5
approved these changes
Dec 26, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Rewrite MMA unit tests to use the cooperative GEMM interface (test_cooperative_gemm_col_major_layout) instead of the legacy standalone MMA_Test implementation.
Changes:
Removed legacy kernel implementation : The old gemm_device, gemm, and MMA_Test template functions with manual SYCL kernel launch logic were removed in favor of reusing the shared cooperative GEMM test infrastructure.
Reduced problem sizes: All tests now use [Shape<_128, _128, _16>{}] (128x128x16) instead of the previous (512x512x256) due to shared local memory limitations.
Added sub_group_size to cooperative GEMM launch policy : Added sc_exp::kernel_properties{sycl_ext::sub_group_size<16>} to the kernel launch policy in test_cooperative_gemm and test_cooperative_gemm_rmem_c. This is required because if the sub-group size is not explicitly specified, it may lead to GEMM computation errors on some hardware (e.g., PVC).