================
@@ -2326,6 +2326,20 @@ bool
SIInsertWaitcnts::insertWaitcntInBlock(MachineFunction &MF,
}
#endif
+ if (ST->isPreciseMemoryEnabled() && Inst.mayLoadOrStore()) {
+ AMDGPU::Waitcnt Wait;
+ if (ST->hasExtendedWaitCounts())
+ Wait = AMDGPU::Waitcnt(0, 0, 0, 0, 0, 0, 0);
+ else
+ Wait = AMDGPU::Waitcnt(0, 0, 0, 0);
+
+ if (!Inst.mayStore())
+ Wait.StoreCnt = ~0u;
----------------
jayfoad wrote:
```suggestion
AMDGPU::Waitcnt Wait = WCG->getAllZeroWaitcnt(Inst.mayStore());
```
However, as a general rule:
- loads and atomics-with-return update LOADcnt
- stores and atomics-without-return update STOREcnt
so it might be more accurate to use the condition `Inst.mayStore() &&
!SIInstrInfo::isAtomicRet(Inst)`.
Please make sure you have tests for atomics with and without return.
https://github.com/llvm/llvm-project/pull/79236
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
