[llvm] [NVPTX] Constant fold NVVM fmin and fmax (PR #121966)

[Artem Belevich via llvm-commits]

Artem-B wrote:

On a side note, would it make sense to autoupgrade some of the min/max intrinsics to their LLVM counterpart, so LLVM can optimize them?

https://github.com/llvm/llvm-project/pull/121966