================
@@ -1107,13 +1153,31 @@ void WaitcntBrackets::updateByEvent(WaitEventType E,
MachineInstr &Inst) {
setVMemScore(LDSDMA_BEGIN + Slot, T, CurrScore);
}
+ if (Context->isAsyncLdsDmaWrite(Inst) && T == LOAD_CNT) {
+ // FIXME: Not supported on GFX12 yet. Will need a new feature when we do.
+ assert(!SIInstrInfo::usesASYNC_CNT(Inst));
+ AsyncScore[T] = CurrScore;
+ }
+
if (SIInstrInfo::isSBarrierSCCWrite(Inst.getOpcode())) {
setRegScore(AMDGPU::SCC, T, CurrScore);
PendingSCCWrite = &Inst;
}
}
}
+void WaitcntBrackets::recordAsyncMark(MachineInstr &Inst) {
+ AsyncMarkers.emplace_back(AsyncScore);
----------------
jayfoad wrote:
I wouldn't recommend trying to measure any performance gains. Personally I use
emplace if and only if it lets me write the code more simply. So my own rule of
thumb is pretty much what it says at the end of your second link:
> So in general, if both push_back() and emplace_back() would work with the
> same arguments, you should prefer push_back()
https://github.com/llvm/llvm-project/pull/173259
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
