This is an archive of the discontinued LLVM Phabricator instance.

[AMDGPU] Refactor multiclass FLAT_Atomic_Pseudo. NFC.
ClosedPublic

Authored by foad on Feb 9 2023, 8:33 AM.

Details

Reviewers
piotr
rampitec
Group Reviewers
Restricted Project
Commits
rGd6c3d7924fee: [AMDGPU] Refactor multiclass FLAT_Atomic_Pseudo. NFC.
Summary

This is just for consistency with FLAT_Global_Atomic_Pseudo.

Diff Detail

Event Timeline

foad created this revision.Feb 9 2023, 8:33 AM
Herald added a project: Restricted Project. · View Herald TranscriptFeb 9 2023, 8:33 AM
foad requested review of this revision.Feb 9 2023, 8:33 AM
Herald added a project: Restricted Project. · View Herald TranscriptFeb 9 2023, 8:33 AM
rampitec added inline comments.Feb 9 2023, 11:21 AM
llvm/lib/Target/AMDGPU/FLATInstructions.td
469

This can be just a class now?

foad added inline comments.Feb 9 2023, 11:38 AM
llvm/lib/Target/AMDGPU/FLATInstructions.td
469

Yes, and I did try that, but I preferred the consistency of having everything here be a multiclass. Note that both FLAT_Global_Atomic_Pseudo_NO_RTN and FLAT_Global_Atomic_Pseudo_RTN have to be multiclasses because they have to define additional _SADDR variants.

Do you feel strongly that it should be a class?

rampitec accepted this revision.Feb 9 2023, 11:40 AM

LGTM

llvm/lib/Target/AMDGPU/FLATInstructions.td
469

No, not really.

This revision is now accepted and ready to land.Feb 9 2023, 11:40 AM
This revision was landed with ongoing or failed builds.Feb 9 2023, 1:14 PM
This revision was automatically updated to reflect the committed changes.