[all-commits] [llvm/llvm-project] a577bb: [AMDGPU] Restrict scale operands of WMMA to low 25...

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/users/rampitec/09-08-_amdgpu_restrict_scale_operands_of_wmma_to_low_256_vgprs
  Home:   https://github.com/llvm/llvm-project
  Commit: a577bb7737dc7c2abdf08d5758bb58eca74ac842
      https://github.com/llvm/llvm-project/commit/a577bb7737dc7c2abdf08d5758bb58eca74ac842
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2025-09-08 (Mon, 08 Sep 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOP3PInstructions.td
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma.gfx1250.w32.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma.imm.gfx1250.w32.ll

  Log Message:
  -----------
  [AMDGPU] Restrict scale operands of WMMA to low 256 VGPRs

These cannot accept high registers.



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