threads: improve ggml_barrier scaling with large number of threads (llama/9598)

threads: improve ggml_barrier scaling with large number of threads (llama/9598)

Make sure n_barrier and n_barrier_passed do not share the cache line to avoid cache line bouncing.
This optimization shows performance improvements even for n_threads <= 8 cases.

Resurect TSAN (Thread Sanitizer) check so that we can avoid doing expensive read-modify-write
in the normal case and just use thread-fence as originally intended.