[llvm] [AMDGPU] Use LSH for lowering ctlz_zero_undef.i8/i16 (PR #88512)

[Leon Clark via llvm-commits]

PeddleSpam wrote:

> Does this need an update after [ac09292](https://github.com/llvm/llvm-project/commit/ac092925c3fa61144e606c7a9d0d375b96e1abda)?

Updated and ran tests again.

https://github.com/llvm/llvm-project/pull/88512