[llvm-branch-commits] [llvm] [AMDGPU] Fold sreg32 operand across Lo16 subcopy (PR #217999)

[Matt Arsenault via llvm-branch-commits]

================
@@ -935,6 +935,24 @@ bool SIFoldOperandsImpl::tryAddToFoldList(
       }
     }
 
+    // Special case for valu16 using sreg32
+    // %1:vgpr32 = copy %0:sreg32/sregxx:sub_x
----------------
arsenm wrote:

```suggestion
    // %1:vgpr32 = copy %0:sreg32:sub_x
```

https://github.com/llvm/llvm-project/pull/217999