llvm-project

145b4a39 - [AMDGPU][CodeGenPrepare] Narrow 64 bit math to 32 bit if profitable (#130577)

[AMDGPU][CodeGenPrepare] Narrow 64 bit math to 32 bit if profitable (#130577) For Add, Sub, Mul with Int64 type, if profitable, then do: 1. Trunc operands to Int32 type 2. Apply 32 bit Add/Sub/Mul 3. Zext to Int64 type