[clang] [AArch64] Implement FP8 floating-point mode helper intrinsics (PR #100608)

[Momchil Velikov via cfe-commits]

momchil-velikov wrote:

> Are you also planning to do the feature test macros, e.g. `__ARM_FEATURE_FP8`?

In principle, yes, but once the ACLE intrinsics are implemented, since the presence of the macro indicates that
both target feature *and* the intrinsics are available.

https://github.com/llvm/llvm-project/pull/100608