[all-commits] [llvm/llvm-project] a34a02: [AMDGPU][SIInsertWaitCnts] skip meta instructions ...

[Sameer Sahasrabuddhe via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a34a02481246482a490c320afb7375ec24cb634e
      https://github.com/llvm/llvm-project/commit/a34a02481246482a490c320afb7375ec24cb634e
  Author: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
  Date:   2025-07-01 (Tue, 01 Jul 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
    M llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll
    M llvm/test/CodeGen/AMDGPU/extract-subvector-16bit.ll
    M llvm/test/CodeGen/AMDGPU/extract-subvector.ll
    M llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
    M llvm/test/CodeGen/AMDGPU/memory-legalizer-global-agent.ll
    M llvm/test/CodeGen/AMDGPU/memory-legalizer-global-system.ll
    M llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll
    M llvm/test/CodeGen/AMDGPU/packed-op-sel.ll
    A llvm/test/CodeGen/AMDGPU/waitcnt-trailing.mir

  Log Message:
  -----------
  [AMDGPU][SIInsertWaitCnts] skip meta instructions early  (#145720)

When iterating over a block, meta instructions have no effect on wait counts,
but their presence drops the reference to earlier waitcnt instructions before
they are processed. This results in spurious wait counts, which do not affect
correctness, but are also not required in the resulting program. Skipping meta
instructions as soon as they are seen cleans this up.



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