[all-commits] [llvm/llvm-project] 05a705: [AMDGPU] Restrict to VGPR only for mfma scale oper...

[Changpeng Fang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 05a705efda4bf62f54eed1bcb97e212ae823c585
      https://github.com/llvm/llvm-project/commit/05a705efda4bf62f54eed1bcb97e212ae823c585
  Author: Changpeng Fang <changpeng.fang at amd.com>
  Date:   2025-09-11 (Thu, 11 Sep 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOP3PInstructions.td
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.scale.f32.16x16x128.f8f6f4.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.scale.f32.32x32x64.f8f6f4.ll
    M llvm/test/CodeGen/AMDGPU/mai-hazards-mfma-scale.gfx950.mir
    M llvm/test/MC/AMDGPU/mai-gfx950-err.s
    M llvm/test/MC/AMDGPU/mai-gfx950.s
    M llvm/test/MC/Disassembler/AMDGPU/gfx950_mai.txt

  Log Message:
  -----------
  [AMDGPU] Restrict to VGPR only for mfma scale operands (#158117)

Restrict to VGPR only (VRegSrc_32) for mfma scale operands to workaround
a hardware design defect: For all Inline/SGPR constants, SP HW use bits
[30:23] as the scale.

TODO: We may still be able to allow Inline Constants/SGPR, with a proper
shift, to obtain a potentially better performance.

Fixes: SWDEV-548629



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