[PATCH] D137138: AMDGPU: Fix DivergenceAnalysis for llvm.read_register

[Matt Arsenault via Phabricator via llvm-commits]

arsenm updated this revision to Diff 473735.
arsenm added a comment.

Don't fully parse register names. This does change the behavior for invalid register names from divergent to not divergent


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D137138/new/

https://reviews.llvm.org/D137138

Files:
  llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
  llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
  llvm/test/Analysis/DivergenceAnalysis/AMDGPU/read_register.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D137138.473735.patch
Type: text/x-patch
Size: 6833 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221107/c6e07695/attachment.bin>