[clang][X86] Replace vprot/vprol/vpror/vshld/vshrd intrinsics with...

[clang][X86] Replace vprot/vprol/vpror/vshld/vshrd intrinsics with __builtin_elementwise_fshl/fshr (#153229)

Replaces the XOP/AVX512 per-element rotation/funnel shift builtins with the generic __builtin_elementwise_fshl/fshr

We still have uniform immediate variants to handle next.

Part of #153152