================
@@ -703,8 +713,37 @@ void WaitcntBrackets::updateByEvent(const SIInstrInfo *TII,
setRegScore(RegNo, T, CurrScore);
}
}
- if (Inst.mayStore() && (TII->isDS(Inst) || mayWriteLDSThroughDMA(Inst))) {
- setRegScore(SQ_MAX_PGM_VGPRS + EXTRA_VGPR_LDS, T, CurrScore);
+ if (Inst.mayStore() &&
+ (TII->isDS(Inst) || TII->mayWriteLDSThroughDMA(Inst))) {
+ // MUBUF and FLAT LDS DMA operations need a wait on vmcnt before LDS
+ // written can be accessed. A load from LDS to VMEM does not need a wait.
+ unsigned Slot = 0;
+ for (const auto *MemOp : Inst.memoperands()) {
+ if (!MemOp->isStore() ||
+ MemOp->getAddrSpace() != AMDGPUAS::LOCAL_ADDRESS)
+ continue;
+ // Comparing just AA info does not guarantee memoperands are equal
----------------
arsenm wrote:
The values don't need to be identical, that's the point of the AA query.
BasicAA will parse through the offsets
https://github.com/llvm/llvm-project/pull/74537
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
