Optimize pg_atomic_exchange_u32 and pg_atomic_exchange_u64.

Optimize pg_atomic_exchange_u32 and pg_atomic_exchange_u64.

Presently, all platforms implement atomic exchanges by performing
an atomic compare-and-swap in a loop until it succeeds.  This can
be especially expensive when there is contention on the atomic
variable.  This commit optimizes atomic exchanges on many platforms
by using compiler intrinsics, which should compile into something
much less expensive than a compare-and-swap loop.  Since these
intrinsics have been available for some time, the inline assembly
implementations are omitted.

Suggested-by: Andres Freund
Reviewed-by: Andres Freund
Discussion: https://postgr.es/m/20231129212905.GA1258737%40nathanxps13