[llvm] [AMDGPU][AggressiveInstCombine] Narrow 64 bit math to 32 bit if profitable (PR #130577)

[Yingwei Zheng via llvm-commits]

================
@@ -1224,6 +1224,68 @@ static bool foldLibCalls(Instruction &I, TargetTransformInfo &TTI,
   return false;
 }
 
+static bool tryNarrowMathIfNoOverflow(Instruction &I, TargetTransformInfo &TTI,
+                                      const DataLayout &DL) {
+  unsigned opc = I.getOpcode();
----------------
dtcxzyw wrote:

```suggestion
  unsigned Opc = I.getOpcode();
```

https://github.com/llvm/llvm-project/pull/130577