Repository navigation
Fix WASM CMake packing widths for SYMM and TRMM - #6098
Merged
martin-frbg merged 1 commit intoOct 7, 2026
Merged
Conversation
Collaborator
|
Thank you |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #6097.
CMake cross-builds for
WASM128_GENERICselect default 2-wide symmetric and triangular packers that are incompatible with the current WASM kernels. This appears to be a regression following the recent 4×4 kernel update and 8×4 SGEMM update, which changed the kernel widths without updating the CMake settings. Make already uses the correct widths.Set SGEMM’s unroll widths to 8×4 and DGEMM’s to 4×4, matching
param.handKERNEL.WASM128_GENERIC. This corrects SYMM and TRMM results without modifying the kernels or other targets.Add exact-valued single- and double-precision SYMM/TRMM regression tests to the existing unit-test suite, registered for both CMake and Make builds. The issue includes a minimal standalone reproducer.