[llvm-branch-commits] [llvm] [AMDGPU] Fold constant offsets into named barrier addresses (PR #205216)

[Jay Foad via llvm-branch-commits]

================
@@ -12570,8 +12578,11 @@ SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
         BarVal = C->getZExtValue();
       else if (auto *GA = dyn_cast<GlobalAddressSDNode>(BarOp))
         if (auto Addr = AMDGPUMachineFunctionInfo::getLDSAbsoluteAddress(
-                *GA->getGlobal()))
+                *GA->getGlobal())) {
+          assert(GA->getOffset() % 16 == 0 &&
+                 "named barrier offset must land on a barrier object");
----------------
jayfoad wrote:

Same here.

https://github.com/llvm/llvm-project/pull/205216