[AMD] Improve shared layout for Wmma's operands #7319
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
antiagainst
requested changes
Jun 25, 2025
| } else { | ||
| // Do not swizzle in case k dimension is not innermost. | ||
| // In this case accesses will go in different banks even without swizzling. | ||
| int kDimIndex = dotOpEnc.getOpIdx() == 0 ? 1 : 0; |
There was a problem hiding this comment.
While we are here can we do something like MFMA layout in the above to use a helper function?
There was a problem hiding this comment.
you mean put the logic into some helper function like composeSharedLayoutForOperand?
There was a problem hiding this comment.
refractored, also add @zhanglx13 @joviliast to review
Swizzling is always disabled for Wmma's B operand, it should be disabled only when k dimension is not contiguous. Both vectorSize, perPhase and maxPhase are now determined using a heuristic approach.
antiagainst
approved these changes
Jun 26, 2025
zhanglx13
reviewed
Jun 26, 2025
joviliast
approved these changes
Jun 27, 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Outdated suggestions cannot be applied.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.
Swizzling is always disabled for Wmma's B operand, it should be disabled only when k dimension is not contiguous.
Both vectorSize, perPhase and maxPhase are now determined using a heuristic approach.
New contributor declaration
I am not making a trivial change, such as fixing a typo in a comment.
I have written a PR description following these
rules.
I have run
pre-commit run --from-ref origin/main --to-ref HEAD.Select one of the following.
/testforlittests/unittestfor C++ tests/python/testfor end-to-end testsSelect one of the following.
littests.littests I have added follow these best practices,including the "tests should be minimal" section. (Usually running Python code
and using the instructions it generates is not minimal.)