[PATCH] D124626: [AMDGPU] Produce waitcounts for LDS DMA

Stanislav Mekhanoshin via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Apr 28 11:43:24 PDT 2022


rampitec added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp:502-503
+static bool mayWriteLDSThroughDMA(const MachineInstr &MI) {
+  return SIInstrInfo::isVALU(MI) &&
+         (SIInstrInfo::isMUBUF(MI) || SIInstrInfo::isFLAT(MI)) &&
+         MI.getOpcode() != AMDGPU::BUFFER_STORE_LDS_DWORD;
----------------
arsenm wrote:
> isVALU is redundant with isMUBUF || isFLAT?
MUBUF and FLAT have VALU = 0 unless it is LDS DMA, which are both memory and VALU instructions. The only of that kind.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124626/new/

https://reviews.llvm.org/D124626



More information about the llvm-commits mailing list