[llvm] [AMDGPU][SDAG] Try folding "lshr i64 + mad" to "mad_[iu]64_[iu]32" (PR #119218)

[Jay Foad via llvm-commits]

jayfoad wrote:

> Try folding "lshr i64 + mad" to "mad_[iu]64_[iu]32"

Just "mad_u64_u32". This optimization does not use the signed version of the instruction.

https://github.com/llvm/llvm-project/pull/119218