我经常在思考这个问题，所以我开始编写一些非常简单的基准测试来尝试通过循环的原子计数器模拟性能，对于每个函数指针回调版本。
请记住，这些是对只执行一个操作——原子地递增其计数器的函数的裸调用；
通过检查生成的汇编输出，您可能会发现，裸C函数指针循环被编译成了3个CPU指令；
C++11的std::function调用仅添加了2个CPU指令，因此在我们的示例中有5个。总之：无论使用何种函数指针技术，开销差异都非常小。
((然而令人困惑的是，分配的lambda表达式似乎比其他表达式运行得更快，甚至比C语言的表达式还要快。))
使用以下命令编译示例：clang++ -o tests/perftest-fncb tests/perftest-fncb.cpp -std=c++11 -pthread -lpthread -lrt -O3 -march=native -mtune=native
#include <functional>
#include <pthread.h>
#include <stdio.h>
#include <unistd.h>
typedef unsigned long long counter_t;
struct Counter {
volatile counter_t bare;
volatile counter_t cxx;
volatile counter_t cxo1;
volatile counter_t virt;
volatile counter_t lambda;
Counter() : bare(0), cxx(0), cxo1(0), virt(0), lambda(0) {}
} counter;
void bare(Counter* counter) { __sync_fetch_and_add(&counter->bare, 1); }
void cxx(Counter* counter) { __sync_fetch_and_add(&counter->cxx, 1); }
struct CXO1 {
void cxo1(Counter* counter) { __sync_fetch_and_add(&counter->cxo1, 1); }
virtual void virt(Counter* counter) { __sync_fetch_and_add(&counter->virt, 1); }
} cxo1;
void (*bare_cb)(Counter*) = nullptr;
std::function<void(Counter*)> cxx_cb;
std::function<void(Counter*)> cxo1_cb;
std::function<void(Counter*)> virt_cb;
std::function<void(Counter*)> lambda_cb;
void* bare_main(void* p) { while (true) { bare_cb(&counter); } }
void* cxx_main(void* p) { while (true) { cxx_cb(&counter); } }
void* cxo1_main(void* p) { while (true) { cxo1_cb(&counter); } }
void* virt_main(void* p) { while (true) { virt_cb(&counter); } }
void* lambda_main(void* p) { while (true) { lambda_cb(&counter); } }
int main()
{
pthread_t bare_thread;
pthread_t cxx_thread;
pthread_t cxo1_thread;
pthread_t virt_thread;
pthread_t lambda_thread;
bare_cb = &bare;
cxx_cb = std::bind(&cxx, std::placeholders::_1);
cxo1_cb = std::bind(&CXO1::cxo1, &cxo1, std::placeholders::_1);
virt_cb = std::bind(&CXO1::virt, &cxo1, std::placeholders::_1);
lambda_cb = [](Counter* counter) { __sync_fetch_and_add(&counter->lambda, 1); };
pthread_create(&bare_thread, nullptr, &bare_main, nullptr);
pthread_create(&cxx_thread, nullptr, &cxx_main, nullptr);
pthread_create(&cxo1_thread, nullptr, &cxo1_main, nullptr);
pthread_create(&virt_thread, nullptr, &virt_main, nullptr);
pthread_create(&lambda_thread, nullptr, &lambda_main, nullptr);
for (unsigned long long n = 1; true; ++n) {
sleep(1);
Counter c = counter;
printf(
"%15llu bare function pointer\n"
"%15llu C++11 function object to bare function\n"
"%15llu C++11 function object to object method\n"
"%15llu C++11 function object to object method (virtual)\n"
"%15llu C++11 function object to lambda expression %30llu-th second.\n\n",
c.bare, c.cxx, c.cxo1, c.virt, c.lambda, n
);
}
}
