[clang] [AMDGPU][clang] provide device implementation for __builtin_logb and … (PR #129347)

[Joseph Huber via cfe-commits]

https://github.com/jhuber6 commented:

Are you trying to do an IR lowering? It'd probably make more sense to handle that in LLVM than clang, but I guess Matt would be the expert there.

https://github.com/llvm/llvm-project/pull/129347