[PATCH] D64490: AMDGPU/GlobalISel: Selection for fminnum/fmaxnum

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: tstellar, nhaehnle, aemerson, aditya_nandakumar, paquette.
Herald added subscribers: Petar.Avramovic, t-tye, tpr, dstuttard, rovka, yaxunl, wdng, jvesely, kzhuravl.

v2f16 case doesn't work yet because the VOP3P complex patterns haven't
been ported yet.


https://reviews.llvm.org/D64490

Files:
  include/llvm/Target/GlobalISel/SelectionDAGCompat.td
  lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
  test/CodeGen/AMDGPU/GlobalISel/inst-select-fmaxnum-ieee.mir
  test/CodeGen/AMDGPU/GlobalISel/inst-select-fmaxnum.mir
  test/CodeGen/AMDGPU/GlobalISel/inst-select-fminnum-ieee.mir
  test/CodeGen/AMDGPU/GlobalISel/inst-select-fminnum.mir
  test/CodeGen/AMDGPU/GlobalISel/inst-select-maxnum.mir
  test/CodeGen/AMDGPU/GlobalISel/inst-select-minnum.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D64490.208950.patch
Type: text/x-patch
Size: 71437 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190710/efc77379/attachment.bin>