[all-commits] [llvm/llvm-project] 32161e: [AMDGPU] Do not fold an immediate into instruction...

[Changpeng Fang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 32161e9de36a747dde22a06c1c99a6091eb2920b
      https://github.com/llvm/llvm-project/commit/32161e9de36a747dde22a06c1c99a6091eb2920b
  Author: Changpeng Fang <changpeng.fang at amd.com>
  Date:   2025-08-06 (Wed, 06 Aug 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch.ll
    M llvm/test/CodeGen/AMDGPU/flat-scratch.ll
    M llvm/test/CodeGen/AMDGPU/fold-operands-frame-index.mir
    M llvm/test/CodeGen/AMDGPU/fold-sgpr-multi-imm.mir
    M llvm/test/CodeGen/AMDGPU/frame-index-elimination.ll
    M llvm/test/CodeGen/AMDGPU/issue130120-eliminate-frame-index.ll
    M llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
    A llvm/test/CodeGen/AMDGPU/no-folding-imm-to-inst-with-fi.ll

  Log Message:
  -----------
  [AMDGPU] Do not fold an immediate into instructions with frame indexes (#151263)

Do not fold an immediate into an instruction that already has a frame
index operand. A frame index could possibly turn out to be another immediate.

Fixes: SWDEV-536263

---------

Co-authored-by: Matt Arsenault <arsenm2 at gmail.com>



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