[PATCH] D130579: AMDGPU: Remove manual selection for atomic fadd

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic created this revision.
Petar.Avramovic added reviewers: foad, arsenm, abinavpp.
Herald added subscribers: kosarev, jsilvanus, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
Herald added a project: All.
Petar.Avramovic requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

AMDGPU: Remove manual selection for atomic fadd

Remove manual selection for atomic fadd from global-isel. 
Select llvm.amdgcn.global.atomic.fadd using auto-generated
selector directly from intrinsic. Split rtn/nortn patterns
and add fix predicates.
Stop pre-isel translation to AtomicLoadFAdd/G_ATOMICRMW_FADD
which corresponds to llvm-ir's atomicrmw fadd instruction.
Edit buffer atomic fadd patterns to import into global-isel.


https://reviews.llvm.org/D130579

Files:
  llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
  llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
  llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
  llvm/lib/Target/AMDGPU/BUFInstructions.td
  llvm/lib/Target/AMDGPU/FLATInstructions.td
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.global.atomic.fadd-with-ret.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.global.atomic.fadd.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.fadd-with-ret.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.fadd-with-ret.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.fadd.rtn_no-rtn.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D130579.447714.patch
Type: text/x-patch
Size: 31443 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220726/3fcf4a20/attachment.bin>