[llvm] [NVPTX] Support llvm.exp2 for f32 and vector of f32 (PR #120519)

[Artem Belevich via llvm-commits]

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

I'm not sure that lowering fexp2 to `ex2.approx` is a good idea.

At the very least it should've been conditional to some sort of fast math flag allowing reduced precision.

https://github.com/llvm/llvm-project/pull/120519