[PATCH] D101481: [AMDGPU] Select V_CVT_*16_F16 more often

[Julien Pagès via Phabricator via llvm-commits]

jpages updated this revision to Diff 342057.
jpages added a comment.

Thank you for your inputs.

Rebased the patch to do the same thing in the Legalizer. It seems more natural indeed.
I took the occasion to do the suggested refactoring around LowerFP_TO_SINT/LowerFP_TO_UINT to merge them into one.

For @foad, I changed the tests back to the original version, thanks for the comment.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101481/new/

https://reviews.llvm.org/D101481

Files:
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/fp_to_uint.ll
  llvm/test/CodeGen/AMDGPU/fptosi.f16.ll
  llvm/test/CodeGen/AMDGPU/fptoui.f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D101481.342057.patch
Type: text/x-patch
Size: 9712 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210430/47883a2f/attachment.bin>