c - 在多线程共享进程中，原子操作似乎比信号量操作慢

Question

尽管指令数量有所减少，但您能想到原子操作看起来比信号量慢的任何充分理由吗？

示例代码:

 void increment(){
     if (strcmp(type, "ATOMIC") == 0) {
         for (int i = 0; i < RUN_TIME; ++i) {
            atomic_fetch_add_explicit(&count, 1, memory_order_relaxed);
        }
    }
     if (strcmp(type, "SEMAPHORE") == 0){
        for (int i = 0; i < RUN_TIME; ++i) {
            sem_wait(sem);
            count++;
            sem_post(sem);
        }
    }
}

输出:

   time ./CMAIN "SEMAPHORE";time ./CMAIN "ATOMIC";
 [C] SEMAPHORE, count 4000000

 real    0m0.039s
 user    0m0.029s
 sys     0m0.002s
[C] ATOMIC, count 4000000

 real    0m0.092s
 user    0m0.236s
 sys     0m0.003s

Answer 1

无法重现。对于 10^9 次迭代，我得到(来自 bash、i5、x86_64、Linux):

$ TIMEFORMAT="%RR %UU %SS"
$ gcc atomic.c -Os -lpthread && ( time ./a.out ATOMIC  ; time ./a.out  SEMAPHORE )
1.572R  1.568U  0.000S  #ATOMIC
5.542R  5.536U  0.000S  #SEMAPHORE

(大约 4000000 次迭代的相同比率。)

我的 atomic.c(你的例子填满了空白):

#include <stdio.h>
#include <string.h>
#include <stdatomic.h>
#include <semaphore.h>
#define RUN_TIME 100000000
char * type;
sem_t *sem;

_Atomic int count = ATOMIC_VAR_INIT(0);

 void increment(){
     if (strcmp(type, "ATOMIC") == 0) {
         for (int i = 0; i < RUN_TIME; ++i) {
            atomic_fetch_add_explicit(&count, 1, memory_order_relaxed);
        }
    }
     if (strcmp(type, "SEMAPHORE") == 0){
        for (int i = 0; i < RUN_TIME; ++i) {
            sem_wait(sem);
            count++;
            sem_post(sem);
        }
    }
}

int main(int C, char**V)
{
    sem_t s;
    sem_init(&s, 0, 1);
    sem = &s;
    type = V[1];
    increment();
}

请发布mcve ，以及您的平台规范。