[all-commits] [llvm/llvm-project] 5052b6: [AMDGPU] Scavenge a VGPR to eliminate a frame inde...

[Anshil Gandhi via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5052b6ce1d3a1d1b36333f036525ec8cff6c9a10
      https://github.com/llvm/llvm-project/commit/5052b6ce1d3a1d1b36333f036525ec8cff6c9a10
  Author: Anshil Gandhi <95053726+gandhi56 at users.noreply.github.com>
  Date:   2025-12-09 (Tue, 09 Dec 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
    A llvm/test/CodeGen/AMDGPU/flat-scratch-alloca-issue-155902.ll

  Log Message:
  -----------
  [AMDGPU] Scavenge a VGPR to eliminate a frame index (#166979)

If the subtarget supports flat scratch SVS mode and there is no SGPR
available to replace a frame index, convert a scratch instruction in SS
form into SV form and replace the frame index with a scavenged VGPR.
Resolves #155902

Co-authored-by: Matt Arsenault <matthew.arsenault at amd.com>



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