[PATCH] D115731: [AMDGPU] Use v_fma_f16 on GFX10

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: arsenm, rampitec.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
foad requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Teach convertToThreeAddress to use the V_FMA_F16_gfx9 pseudo (i.e. the
standard instruction in GFX9 onwards) instead of V_FMA_F16 (the legacy
pseudo for GFX8 compatibility, which is no longer supported in GFX10).
This follows the example of macToMad in SIFoldOperands.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D115731

Files:
  llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-fma-mul.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-mul.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/fma.ll
  llvm/test/CodeGen/AMDGPU/strict_fma.f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D115731.394251.patch
Type: text/x-patch
Size: 5794 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211214/10e7e354/attachment.bin>