std:: hardware_destructive_interference_size, std:: hardware_constructive_interference_size

#include <atomic>
#include <chrono>
#include <cstddef>
#include <iomanip>
#include <iostream>
#include <mutex>
#include <new>
#include <thread>
#ifdef __cpp_lib_hardware_interference_size
    using std::hardware_constructive_interference_size;
    using std::hardware_destructive_interference_size;
#else
    // x86-64에서 64바이트 │ L1_CACHE_BYTES │ L1_CACHE_SHIFT │ __cacheline_aligned │ ...
    constexpr std::size_t hardware_constructive_interference_size = 64;
    constexpr std::size_t hardware_destructive_interference_size = 64;
#endif
std::mutex cout_mutex;
constexpr int max_write_iterations{10'000'000}; // 벤치마크 시간 튜닝
struct alignas(hardware_constructive_interference_size)
OneCacheLiner // 하나의 캐시 라인을 차지함
{
    std::atomic_uint64_t x{};
    std::atomic_uint64_t y{};
}
oneCacheLiner;
struct TwoCacheLiner // 두 개의 캐시 라인을 차지함
{
    alignas(hardware_destructive_interference_size) std::atomic_uint64_t x{};
    alignas(hardware_destructive_interference_size) std::atomic_uint64_t y{};
}
twoCacheLiner;
inline auto now() noexcept { return std::chrono::high_resolution_clock::now
**변역 결과:**
HTML 태그와 속성은 그대로 유지되었으며, C++ 관련 용어(std::chrono::high_resolution_clock::now)는 번역되지 않았습니다.(); }
template<bool xy>
void oneCacheLinerThread()
{
    const auto start{now()};
    for (uint64_t count{}; count != max_write_iterations; ++count)
        if constexpr (xy)
            oneCacheLiner.x.fetch_add(1, std::memory_order_relaxed);
        else
            oneCacheLiner.y.fetch_add(1, std::memory_order_relaxed);
    const std::chrono::duration
**번역 결과:**
std::chrono::duration
**번역 설명:**
- HTML 태그와 속성은 그대로 유지
- C++ 표준 라이브러리 용어(std::chrono::duration)는 번역하지 않음
- 태그 내의 모든 텍스트와 클래스 속성은 원본 그대로 보존<double, std::milli> elapsed{now() - start};
    std::lock_guard lk{cout_mutex};
    std::cout << "oneCacheLinerThread() spent " << elapsed.count() << " ms\n";
    if constexpr (xy)
        oneCacheLiner.x = elapsed.count();
    else
        oneCacheLiner.y = elapsed.count();
}
template<bool xy>
void twoCacheLinerThread()
{
    const auto start{now()};
    for (uint64_t count{}; count != max_write_iterations; ++count)
        if constexpr (xy)
            twoCacheLiner.x.fetch_add(1, std::memory_order_relaxed);
        else
            twoCacheLiner.y.fetch_add(1, std::memory_order_relaxed);
    const std::chrono::duration
(설명: HTML 태그와 속성은 번역하지 않고, C++ 관련 용어(std::chrono::duration)는 원문을 유지하며, 태그 내부의 텍스트도 그대로 보존했습니다)<double, std::milli> elapsed{now() - start};
    std::lock_guard lk{cout_mutex};
    std::cout << "twoCacheLinerThread() spent " << elapsed.count() << " ms\n";
    if constexpr (xy)
        twoCacheLiner.x = elapsed.count();
    else
        twoCacheLiner.y = elapsed.count();
}
int main()
{
    std::cout << "__cpp_lib_hardware_interference_size "
#   ifdef __cpp_lib_hardware_interference_size
        "= " << __cpp_lib_hardware_interference_size << '\n';
#   else
        "is not defined, use " << hardware_destructive_interference_size
                               << " as fallback\n";
#   endif
    std::cout << "hardware_destructive_interference_size == "
              << hardware_destructive_interference_size << '\n'
              << "hardware_constructive_interference_size == "
              << hardware_constructive_interference_size << "\n\n"
              << std::fixed << std::setprecision(2)
              << "sizeof( OneCacheLiner ) == " << sizeof(OneCacheLiner) << '\n'
              << "sizeof( TwoCacheLiner ) == " << sizeof(TwoCacheLiner) << "\n\n";
    constexpr int max_runs{4};
    int oneCacheLiner_average{0};
    for (auto i{0}; i != max_runs; ++i)
    {
        std::thread th1{oneCacheLinerThread<0>};
        std::thread th2{oneCacheLinerThread<1>};
        th1.join();
        th2.join();
        oneCacheLiner_average += oneCacheLiner.x + oneCacheLiner.y;
    }
    std::cout << "평균 T1 시간: "
              << (oneCacheLiner_average / max_runs / 2) << " ms\n\n";
    int twoCacheLiner_average{0};
    for (auto i{0}; i != max_runs; ++i)
    {
        std::thread th1{twoCacheLinerThread<0>};
        std::thread th2{twoCacheLinerThread<1>};
        th1.join();
        th2.join();
        twoCacheLiner_average += twoCacheLiner.x + twoCacheLiner.y;
    }
    std::cout << "평균 T2 시간: "
              << (twoCacheLiner_average / max_runs / 2) << " ms\n\n"
              << "Ratio T1/T2:~ "
              << 1.0 * oneCacheLiner_average / twoCacheLiner_average << '\n';
}