[Codegen][GPU] Add pass to unroll to native mma widths #18101
Merged
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Outdated suggestions cannot be applied.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.
Left as TODO is to extend this pass to also unroll consumers/producers. To eventually connect everything we should add a pattern that unrolls iter args of
scf.for
loops.Note that the unrolling pattern is already tested in its own test, so simply updating the pipeline test is fine here. Once extending this pass to do more unrolling a test can be added.