[PATCH] D152697: AMDGPU: Add llvm.amdgcn.log intrinsic

[Matt Arsenault via Phabricator via cfe-commits]

arsenm created this revision.
arsenm added reviewers: AMDGPU, foad, rampitec, Pierre-vh, cdevadas, jhuber6.
Herald added subscribers: StephenFan, kerbowa, hiraditya, 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.

This will map directly to the hardware instruction which does not
handle denormals for f32. This will allow moving the generic intrinsic
to be lowered correctly. Also handles selecting the f16 version, but
there's no reason to use it over the generic intrinsic.


https://reviews.llvm.org/D152697

Files:
  clang/include/clang/Basic/BuiltinsAMDGPU.def
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGenOpenCL/builtins-amdgcn.cl
  llvm/docs/ReleaseNotes.rst
  llvm/include/llvm/IR/IntrinsicsAMDGPU.td
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
  llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
  llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
  llvm/lib/Target/AMDGPU/R600Instructions.td
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/lib/Target/AMDGPU/VOP1Instructions.td
  llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.log.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D152697.530454.patch
Type: text/x-patch
Size: 11761 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20230612/e5eb324c/attachment-0001.bin>