[llvm] [NVPTX] Add support for atomic add for bf16 type (PR #89586)

[Artem Belevich via llvm-commits]

Artem-B wrote:

> Do you know someone we could ask who is a floating point expert?

@majnemer Do you have an opinion on atomics and denormals handling for bf16/f16? Who would be the right folks to consult on that?

https://github.com/llvm/llvm-project/pull/89586