[all-commits] [llvm/llvm-project] 36d2fb: [AMDGPU] Reject sub-dword format buffer loads and ...

[Arseniy Obolenskiy via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 36d2fb92bcac253e2e1bb20b7ea7b22033027691
      https://github.com/llvm/llvm-project/commit/36d2fb92bcac253e2e1bb20b7ea7b22033027691
  Author: Arseniy Obolenskiy <arseniy.obolenskiy at amd.com>
  Date:   2026-07-16 (Thu, 16 Jul 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.format.i8.xfail.ll

  Log Message:
  -----------
  [AMDGPU] Reject sub-dword format buffer loads and stores (#209703)

An i8 `buffer.{load,store}.format` has no corresponding hardware
instruction so diagnose it in SelectionDAG and fail legalization in
GlobalISel instead of emitting invalid format opcodes



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