[all-commits] [llvm/llvm-project] 7f38e2: WIP: AMDGPU: Always select the VGPR version of MFMAs

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/amdgpu/always-select-vgpr-version-of-mfma
  Home:   https://github.com/llvm/llvm-project
  Commit: 7f38e2b194c6ef4e4d4b34af6dc93f8d67e81434
      https://github.com/llvm/llvm-project/commit/7f38e2b194c6ef4e4d4b34af6dc93f8d67e81434
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-06-20 (Fri, 20 Jun 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
    M llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
    M llvm/lib/Target/AMDGPU/VOP3PInstructions.td

  Log Message:
  -----------
  WIP: AMDGPU: Always select the VGPR version of MFMAs

We do not want to use AGPRs unless absolutely required due
to register pressure. Rely on a post-regalloc pass to replace
VGPR MFMAs with the AGPR version if it avoids the copies introduced
due to live range splitting.



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