[PATCH] D83891: AMDGPU/GlobalISel: Try to promote to use packed saturating add/sub

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: foad, kerbowa, Petar.Avramovic, mbrkusanin.
Herald added subscribers: hiraditya, t-tye, tpr, dstuttard, rovka, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

This produces worse results right now for i8 vectors, but that should
be addressed when we actually try to optimize packed vectors.


https://reviews.llvm.org/D83891

Files:
  llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-saddsat.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ssubsat.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddsat.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-usubsat.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/saddsat.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/ssubsat.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/uaddsat.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/usubsat.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D83891.278245.patch
Type: text/x-patch
Size: 97797 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200715/a72a1ed4/attachment-0001.bin>