================
@@ -2573,7 +2574,17 @@ bool AMDGPULegalizerInfo::legalizeAddrSpaceCast(
         return B.buildIntToPtr(Dst, Sub).getReg(0);
       }
 
-      // Extract low 32-bits of the pointer.
+      if (DestAS == AMDGPUAS::BARRIER) {
+        // flat -> barrier: extract the low 32 bits, then sub the barrier AS
+        // offset.
+        Register LoBits = B.buildExtract(S32, Src, 0).getReg(0);
+        Register Sub =
+            B.buildSub(S32, LoBits,
+                       B.buildConstant(S32, AMDGPUAS::BarrierAddrLDSOffset))
+                .getReg(0);
+        return B.buildIntToPtr(Dst, Sub).getReg(0);
+      }
----------------
ssahasra wrote:

I am guessing that masking out AMDGPUAS::BarrierAddrLDSOffset is cheaper than 
subtracting it.

https://github.com/llvm/llvm-project/pull/209746
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

Reply via email to