https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80878
--- Comment #29 from Yongwei Wu <wuyongwei at gmail dot com> --- As usual, test results are always elusive. I have to add yet another important piece of information. The very bad performance result does not occur on Linux, but only on macOS (Homebrew versions of GCC and libatomic). So far, it seems to indicate that this is more a libatomic issue on macOS, which I traced to pthread_mutex_lock, instead of "lock cmpxchg16b" on Linux...
