[all-commits] [llvm/llvm-project] d5a24e: [AMDGPU] Replace relaxed-buffer-oob-mode feature w...

[Piotr Sobczak via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d5a24ef8d093708141b03ef1da809363841065b1
      https://github.com/llvm/llvm-project/commit/d5a24ef8d093708141b03ef1da809363841065b1
  Author: Piotr Sobczak <piotr.sobczak at amd.com>
  Date:   2026-06-01 (Mon, 01 Jun 2026)

  Changed paths:
    M llvm/docs/AMDGPUUsage.rst
    M llvm/docs/ReleaseNotes.md
    M llvm/lib/IR/Verifier.cpp
    M llvm/lib/Target/AMDGPU/AMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/unaligned-buffer.ll
    M llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/merge-vectors.ll
    M llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/unaligned-buffer.ll
    A llvm/test/Verifier/AMDGPU/module-flag-oob-mode.ll

  Log Message:
  -----------
  [AMDGPU] Replace relaxed-buffer-oob-mode feature with module flag (#160922)

Remove AMDGPU subtarget feature toggle for relaxed buffer OOB handling
and replace it with two explicit LLVM module flags:
- amdgpu.buffer.oob.relaxed for untyped buffer instructions
- amdgpu.tbuffer.oob.relaxed for typed buffer instructions

Each flag is modeled as i32 with Max merge behavior and validated as a
tri-state value, where 0 means Any/default, 1 means Relaxed and 2 means Strict. 
The absence of the module flag implies the default mode, which is currently treated
as Strict by the backend.



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