================
@@ -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:
GFX10 introduced a separate counter for **VMEM** stores with the name VScnt.
GFX12 just renamed it to STOREcnt. No architecture has a separate store counter
for DS or SMEM. So `ds_add_u32 v0, v1` followed by `s_waitcnt lgkmcnt(0)`
(pre-GFX12) or `s_wait_dscnt 0` (GFX12) is fine .
https://github.com/llvm/llvm-project/pull/79236
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
