[PATCH] D148906: [AMDGPU] Remove function if FeatureWavefrontSize 32/64 is not supported on current GPU

krishna chaitanya sankisa via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon May 1 01:24:21 PDT 2023


skc7 updated this revision to Diff 518409.
skc7 retitled this revision from "[AMDGPU] Remove function if FeatureWavefrontSize32 is not supported on current GPU" to "[AMDGPU] Remove function if FeatureWavefrontSize 32/64 is not supported on current GPU".
skc7 edited the summary of this revision.
skc7 set the repository for this revision to rG LLVM Github Monorepo.
skc7 added a comment.

Remove wavefrontsize64 function if compiling in wave32 mode.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D148906/new/

https://reviews.llvm.org/D148906

Files:
  llvm/lib/Target/AMDGPU/AMDGPURemoveIncompatibleFunctions.cpp
  llvm/test/CodeGen/AMDGPU/remove-incompatible-wave32-feature.ll
  llvm/test/CodeGen/AMDGPU/remove-incompatible-wave64-feature.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D148906.518409.patch
Type: text/x-patch
Size: 6597 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230501/84849239/attachment.bin>


More information about the llvm-commits mailing list