[PATCH] D156677: AMDGPU: Remove pointless libcall optimization of fma/mad

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: AMDGPU, rampitec, jhuber6, vpykhtin, dfukalov, foad, yaxunl.
Herald added subscribers: StephenFan, kerbowa, hiraditya, tpr, dstuttard, jvesely, kzhuravl.
Herald added a project: All.
arsenm requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

After the library is linked and trivially inlined, the generic fma and
fmuladd intrinsics already handle these cases, and with precise flag
handling. This was requiring all fast math flags when we really just
need nsz for the fma(a, b, 0) case.


https://reviews.llvm.org/D156677

Files:
  llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
  llvm/test/CodeGen/AMDGPU/simplify-libcalls.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156677.545605.patch
Type: text/x-patch
Size: 5566 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230731/57e6bc21/attachment.bin>