Skip swizzling when read/gather row phases are inconsistent #699
+25
−21
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
Hardcode84
approved these changes
Jan 9, 2026
harsh-nod
force-pushed
the
swizzle_fix
branch
3 times, most recently
from
ef381fd to
a7224f5
Compare
Add validation to detect row phase mismatch between reads and gathers in gather_to_shared_swizzling and gracefully skip unsupported cases. Add F32_32x32x16_F16 MMA test for CDNA4 which fails if this validation is not present. Signed-off-by: harsh-nod <menonharsh@gmail.com>
harsh-nod
force-pushed
the
swizzle_fix
branch
from
a7224f5 to
843510d
Compare
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Outdated suggestions cannot be applied.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.
Add validation to detect row phase mismatch between reads and gathers in gather_to_shared_swizzling and gracefully skip unsupported cases. Add F32_32x32x16_F16 MMA test for CDNA4 which fails if this validation is not present.