[PATCH] D153544: [AMDGPU] Use V_FMA_MIX* more often

[Mateja Marjanovic via Phabricator via llvm-commits]

matejam created this revision.
matejam added reviewers: Joe_Nash, foad, tsymalla, arsenm.
matejam added a project: LLVM.
Herald added subscribers: StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
matejam requested review of this revision.
Herald added a subscriber: wdng.

Combine mul (f32) + fptrunc (f32->f16) + add (f16) to v_fma_mixlo_f16.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D153544

Files:
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/test/CodeGen/AMDGPU/mad-mix-lo.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D153544.533565.patch
Type: text/x-patch
Size: 5103 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230622/9cb5ce4a/attachment.bin>