[PATCH] D110074: [AMDGPU] Prefer fmac over fma when selecting FMA_W_CHAIN

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: arsenm, rampitec, ruiling, mareko.
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.

FMA_W_CHAIN is used when lowering fdiv f32. Prefer to select it to fmac
if there are no source modifiers, just like we do for other mad/mac and
fma/fmac cases.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D110074

Files:
  llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  llvm/test/CodeGen/AMDGPU/fdiv.ll
  llvm/test/CodeGen/AMDGPU/frem.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D110074.373590.patch
Type: text/x-patch
Size: 6694 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210920/3a6be7ca/attachment.bin>