[llvm] [NVPTX] Support llvm.{exp2, log2} for f32/f16/bf16 and vectors (PR #120519)

[Artem Belevich via llvm-commits]

Artem-B wrote:

@jhuber6 you've dealt with the math library recently. Do you know what are the expectations for the precision of `exp2f` ? 

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