[throwaway54-762]

> In the author's example, the fastest implementation was actually _not_ lock-free, it merely used a better spinlock than std::mutex.

The author is also using gcc 4.6; perhaps different results would be obtained with gcc 4.8 or recent Clang. If you care enough to think about LFDS, measure measure measure =).

[ajross]

Or glibc's pthread_mutex_t implementation. Or hand-written assembly above futex(2). There's no lack of synchronization primitives.