[PATCH] D157874: AMDGPU: Replace some libcalls with intrinsics

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: AMDGPU, rampitec, foad, jmmartinez, cdevadas, Pierre-vh.
Herald added subscribers: StephenFan, kerbowa, hiraditya, Anastasia, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
arsenm requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

OpenCL loses fast math information by going through libcall wrappers
around intrinsics.

      

Do this to preserve call site flags which are lost when inlining. It's
not safe in general to propagate flags during inline, so avoid dealing
with this by just special casing some of the useful calls.


https://reviews.llvm.org/D157874

Files:
  llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-exp.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-exp2.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-fma.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-fmax.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-fmin.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-log.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-log10.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-log2.ll
  llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-mad.ll
  llvm/test/CodeGen/AMDGPU/simplify-libcalls.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D157874.549928.patch
Type: text/x-patch
Size: 114083 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230814/2fae7d86/attachment.bin>