[AMDGPU] Do not reassign scale source operands in amdgpu-rewrite-agpr… #577
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
…-copy-mfma Testing this seems difficult, as there has to be sufficient register pressure and live range overlapping to trigger the reassignment of the scale source operands. Manually verified that this prevents a CK compilation failure from SWDEV-564511
Collaborator
dhruvachak
reviewed
Nov 13, 2025
dhruvachak
left a comment
dhruvachak
left a comment
There was a problem hiding this comment.
Is there a reason this is not submitted upstream?
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Outdated suggestions cannot be applied.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.
[AMDGPU] Do not reassign scale source operands in amdgpu-rewrite-agpr-copy-mfma
Testing this seems difficult, as there has to be sufficient register pressure and live range overlapping to trigger the reassignment of the scale source operands.
Manually verified that this prevents a CK compilation failure from SWDEV-564511
v_mfma_scale_f32_16x16x128_f8f6f4 a[80:83], a[72:75], a[44:47], a[80:83], v41, a0/Invalid register, operand has 'VGPR_32' register class/ op_sel_hi:[0,0,0] cbsz:4 blgp:4