[all-commits] [llvm/llvm-project] fa2dcc: [AMDGPU] Remove one case of vmcnt loop header flus...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fa2dccb377d0b712223efe5b62e5fc633580a9e6
      https://github.com/llvm/llvm-project/commit/fa2dccb377d0b712223efe5b62e5fc633580a9e6
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-08-23 (Fri, 23 Aug 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
    M llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir

  Log Message:
  -----------
  [AMDGPU] Remove one case of vmcnt loop header flushing for GFX12 (#105550)

When a loop contains a VMEM load whose result is only used outside the
loop, do not bother to flush vmcnt in the loop head on GFX12. A wait for
vmcnt will be required inside the loop anyway, because VMEM instructions
can write their VGPR results out of order.



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