[llvm] [AMDGPU] add SROA before InferAddressSpace (PR #137909)

[Matt Arsenault via llvm-commits]

arsenm wrote:

> I can see mulitple LIT test changed after adding SROA, for example simple_indirect_call.ll, I checked, load and store get eliminated. This was originally from Nicolai. He observed this issue with some HIP code he wrote.

The codegen pipeline is not responsible for most of the heavy optimizations. Ideally we would not run SROA or InferAddressSpaces at all in the codegen pipeline. 

https://github.com/llvm/llvm-project/pull/137909