[llvm] [NVPTX] Add IR pass for FMA transformation in the llc pipeline (PR #154735)

[Artem Belevich via llvm-commits]

https://github.com/Artem-B commented:

> By moving this transformation earlier into the IR phase, we enable more opportunities for FMA folding, including across basic blocks.

This sounds like something that may be useful in general. Perhaps it makes sense to make it a generic pass. There's nothing in it that's NVPTX-specific.  
  
@arsenm -- would this be useful for AMDGPU?

https://github.com/llvm/llvm-project/pull/154735