[PATCH] D103659: [AMDGPU][GlobalISel] Try to use op_sel when selecting packed instructions

Vang Thao via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Jun 8 12:59:48 PDT 2021


vangthao updated this revision to Diff 350699.
vangthao added a comment.

Addressed comments.

Functions return register value instead of using argument to return value.
Fix bug with illegally stripping FNeg instructions that are not of type 2x16 or size 16.
Added mir tests.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D103659/new/

https://reviews.llvm.org/D103659

Files:
  llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-op-sel.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.sdot2.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.udot2.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/op-sel.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D103659.350699.patch
Type: text/x-patch
Size: 141841 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210608/396eedd4/attachment-0001.bin>


More information about the llvm-commits mailing list