[PATCH] D112085: [DAGCombiner] fold bit-hack form of usubsat

[Sanjay Patel via Phabricator via llvm-commits]

spatel updated this revision to Diff 380778.
spatel added a comment.

Patch updated:
Rebased after D112095 <https://reviews.llvm.org/D112095> / 92a0389b0425 <https://reviews.llvm.org/rG92a0389b0425a9535a99a0ce13ba0eeda2bce7ad> - so we don't have the SSE2/3 regression.
There's still an extra instruction for AVX512 on that test. If that's a regression, I can mark that as TODO or try to avoid that too.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D112085/new/

https://reviews.llvm.org/D112085

Files:
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/test/CodeGen/AMDGPU/usubsat.ll
  llvm/test/CodeGen/X86/psubus.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D112085.380778.patch
Type: text/x-patch
Size: 9747 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211019/6c66432f/attachment.bin>