std:: hardware_destructive_interference_size, std:: hardware_constructive_interference_size
From cppreference.net
C++
Concurrency support library
|
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
定义于头文件
<new>
|
||
|
inline
constexpr
std::
size_t
hardware_destructive_interference_size = /*由实现定义*/ ; |
(1) | (C++17 起) |
|
inline
constexpr
std::
size_t
hardware_constructive_interference_size = /*由实现定义*/ ; |
(2) | (C++17 起) |
1)
避免伪共享的两个对象间最小偏移量。保证至少为
alignof
(
std::
max_align_t
)
struct keep_apart { alignas(std::hardware_destructive_interference_size) std::atomic<int> cat; alignas(std::hardware_destructive_interference_size) std::atomic<int> dog; };
2)
用于促进真共享的最大连续内存大小。保证至少为
alignof
(
std::
max_align_t
)
struct together { std::atomic<int> dog; int puppy; }; struct kennel { // 其他数据成员... alignas(sizeof(together)) together pack; // 其他数据成员... }; static_assert(sizeof(together) <= std::hardware_constructive_interference_size);
注释
这些常量提供了一种可移植的方式来访问L1数据缓存行大小。
| 功能测试 宏 | 值 | 标准 | 功能特性 |
|---|---|---|---|
__cpp_lib_hardware_interference_size
|
201703L
|
(C++17) |
constexpr
std
::
hardware_constructive_interference_size
与
constexpr std :: hardware_destructive_interference_size |
示例
该程序使用两个线程以原子方式写入给定全局对象的数据成员。第一个对象适配于单个缓存行，这会导致"硬件干扰"。第二个对象将其数据成员保持在独立的缓存行上，从而避免了线程写入后可能的"缓存同步"。
运行此代码
#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 // 64 bytes on x86-64 │ 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}; // the benchmark time tuning struct alignas(hardware_constructive_interference_size) OneCacheLiner // occupies one cache line { std::atomic_uint64_t x{}; std::atomic_uint64_t y{}; } oneCacheLiner; struct TwoCacheLiner // occupies two cache lines { 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(); } 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<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<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 <<
参见
|
[static]
|
返回实现支持的并发线程数
(
std::thread
的公开静态成员函数)
|
|
[static]
|
返回实现支持的并发线程数
(
std::jthread
的公开静态成员函数)
|