[llvm] [AMDGPU] narrow only on store to pow of 2 mem location (PR #150093)

[Shilei Tian via llvm-commits]

shiltian wrote:

Those are just some random types used for testing purposes. LLVM accepts integers of any size. I don't think we'd realistically get such types in IR generated by a frontend. They’re mostly the result of artificially constructed test cases. But the real question is: are we actually going to support arbitrary integer sizes?

https://github.com/llvm/llvm-project/pull/150093