[all-commits] [llvm/llvm-project] 283d34: [AMDGPU] Remove one case of vmcnt loop header flus...

[Jay Foad via All-commits]

  Branch: refs/heads/users/foad/vmem-write-vgpr-in-order_split_split
  Home:   https://github.com/llvm/llvm-project
  Commit: 283d345b62f65f93af733894de6bc47c279e6e68
      https://github.com/llvm/llvm-project/commit/283d345b62f65f93af733894de6bc47c279e6e68
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-08-22 (Thu, 22 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

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