[PATCH] D149844: [X86] Add lowering of fminimum/fmaximum for vector operands

[Serguei Katkov via Phabricator via llvm-commits]

skatkov updated this revision to Diff 520910.
skatkov added a comment.

I've pre-landed the new tests, fixed the name in the test and updated this revision.

Unfortunately handlining -f 0. for max and 0.f for min will not work as we want due to we check only for preferred zero.
And it is not a problem of vectorized version but scalar as well.

I propose to handle this as follow-up patch.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149844/new/

https://reviews.llvm.org/D149844

Files:
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
  llvm/test/CodeGen/X86/fminimum-fmaximum.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D149844.520910.patch
Type: text/x-patch
Size: 84516 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230510/0ea7e4e2/attachment.bin>