[all-commits] [llvm/llvm-project] 5021e6: AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd f...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5021e6dd548323e1169be3d466d440009e6d1f8e
      https://github.com/llvm/llvm-project/commit/5021e6dd548323e1169be3d466d440009e6d1f8e
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-15 (Sat, 15 Jun 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/FLATInstructions.td
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/fp-atomics-gfx940.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2bf16-agent.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2bf16-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2f16-agent.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2f16-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-fp-vector.ll

  Log Message:
  -----------
  AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)

Unlike the existing fadd cases, choose to ignore the requirement for
amdgpu-unsafe-fp-atomics in case of fine-grained memory access. This
is to minimize migration pain to the new atomic control metadata. This
should not break any users, as the atomic intrinsics are still
directly consumed, and clang does not yet produce vector FP atomicrmw.



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