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

[Shilei Tian via llvm-commits]

================
@@ -1560,6 +1560,86 @@ void AMDGPUCodeGenPrepareImpl::expandDivRem64(BinaryOperator &I) const {
   llvm_unreachable("not a division");
 }
 
+Type *findSmallestLegalBits(Instruction *I, int OrigBit, int MaxBitsNeeded,
+                            const TargetLowering *TLI, const DataLayout &DL) {
+  if (MaxBitsNeeded >= OrigBit) {
+    return nullptr;
+  }
----------------
shiltian wrote:

```suggestion
  if (MaxBitsNeeded >= OrigBit)
    return nullptr;
```

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