[all-commits] [llvm/llvm-project] f4f772: [AMDGPU] Stop reserving $vcc_hi in wave32 mode (#8...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f4f772ceef379bd434d266b6e0d2bbdf796f81cb
      https://github.com/llvm/llvm-project/commit/f4f772ceef379bd434d266b6e0d2bbdf796f81cb
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-04-16 (Tue, 16 Apr 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
    M llvm/test/CodeGen/AMDGPU/bf16.ll
    M llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.f16.ll
    M llvm/test/CodeGen/AMDGPU/load-constant-i16.ll
    M llvm/test/CodeGen/AMDGPU/load-constant-i8.ll
    M llvm/test/CodeGen/AMDGPU/sgpr-spill-overlap-wwm-reserve.mir

  Log Message:
  -----------
  [AMDGPU] Stop reserving $vcc_hi in wave32 mode (#87783)

This gives us one extra SGPR to play with. The comment suggested that it
could cause bugs, but I have tested it with Vulkan CTS with the default
wave size for compute shaders set to 32 and did not find any problems.



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