[llvm] [NVPTX] Add support for nvvm.flo.[us] intrinsics (PR #114489)

[Artem Belevich via llvm-commits]

Artem-B wrote:

> Here is a small example of what the PTX for this instruction will be lowered to according to godbolt: https://godbolt.org/z/4crzY67oo

Fascinating. OK, given that there's h/w support for exactly that instruction, I see no problem providing an intrinsic for it. 

https://github.com/llvm/llvm-project/pull/114489