[all-commits] [llvm/llvm-project] c02602: AMDGPU: Legalize v2f16 atomicrmw fadd for buffer f...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c026024ff9c7ed79afffde318a73793c1f14e004
      https://github.com/llvm/llvm-project/commit/c026024ff9c7ed79afffde318a73793c1f14e004
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-21 (Fri, 21 Jun 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fadd.ll

  Log Message:
  -----------
  AMDGPU: Legalize v2f16 atomicrmw fadd for buffer fat pointers (#95929)

Unfortunately the v2bf16 case is complicated because gfx90a
doesn't support it, while it does for global/flat.



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