[llvm] [NVPTX] Promote internal function alignments in IR pass (PR #208040)

[Rahul Joshi via llvm-commits]

jurahul wrote:

> Adding module passes in the middle of the codegen pipeline used to have surprising effects, but that's the right model for what you want to do, and PTX modules usually don't have giant callgraphs anyway, so this is probably what we want.
> 
> 
> 
> Lgtm

Won't that increase the total footprint of the compilation?

https://github.com/llvm/llvm-project/pull/208040