[all-commits] [llvm/llvm-project] ba80b7: AMDGPU: Legalize atomicrmw fadd for v2f16/v2bf16 f...

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/amdgpu-legalize-vector-atomicrmw-fadd-local
  Home:   https://github.com/llvm/llvm-project
  Commit: ba80b77ee85a70110f616edfcb2f116fa137517e
      https://github.com/llvm/llvm-project/commit/ba80b77ee85a70110f616edfcb2f116fa137517e
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-14 (Fri, 14 Jun 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/DSInstructions.td
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/fp-atomics-gfx940.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll
    M llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll

  Log Message:
  -----------
  AMDGPU: Legalize atomicrmw fadd for v2f16/v2bf16 for local memory

Make this legal for gfx940 and gfx12



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications