timur spin lock without RAII unlock non realtimesafe/overhead

gistfile1.txt

#include <array>
#include <thread>
#include <atomic>
#include <emmintrin.h>

struct spin_mutex {
    void lock() noexcept {
        // approx. 5x5 ns (= 25 ns), 10x40 ns (= 400 ns), and 3000x350 ns 
        // (~ 1 ms), respectively, when measured on a 2.9 GHz Intel i9
        constexpr std::array iterations = {5, 10, 3000};

        for (int i = 0; i < iterations[0]; ++i) {
            if (try_lock())
                return;
        }

        for (int i = 0; i < iterations[1]; ++i) {
            if (try_lock())
                return;

            _mm_pause();
        }

        while (true) {
            for (int i = 0; i < iterations[2]; ++i) {
                if (try_lock())
                    return;

                _mm_pause(); //Windows can use YieldProcessor()
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
                _mm_pause();
            }

            // waiting longer than we should, let's give other threads 
            // a chance to recover
            std::this_thread::yield();
        }

    bool try_lock() noexcept {
        return !flag.test_and_set(std::memory_order_acquire);
    }

    void unlock() noexcept {
        flag.clear(std::memory_order_release);
    }

private:
    std::atomic_flag flag = ATOMIC_FLAG_INIT;
};