// 修改自 http://www.gpfeng.com/?p=451
// 环境：glibc 2.33，gcc 11.1.0，gcc test.c -O0 -S

#include <stdio.h>
#include <stdlib.h>
#include <pthread.h>
#include <time.h>

#define MAX_THREADS 10

char sum = 0;
char sum1 = 0;

pthread_barrier_t barr;
pthread_mutex_t   lock = PTHREAD_MUTEX_INITIALIZER;

__attribute__ ((noinline)) void *thread_add_func0(void * param)
{
  pthread_barrier_wait(&barr);
  int i;
  for (i = 0; i < *((int*)param); i++)
  {
    pthread_mutex_lock(&lock);
    pthread_mutex_unlock(&lock);
  }
}

__attribute__ ((noinline)) void *thread_add_func1(void * param)
{
  pthread_barrier_wait(&barr);
  int i;
  for (i = 0; i < *((int*)param); i++)
  {
    pthread_mutex_lock(&lock);
    sum++;
    pthread_mutex_unlock(&lock);
  }
}

__attribute__ ((noinline)) void *thread_add_func2(void * param)
{
  pthread_barrier_wait(&barr);
  int i;
  int j = 0;
  for (i = 0; i < *((int*)param); i++)
  {
    pthread_mutex_lock(&lock);
    if (j == 0)
    {
      sum += 3;
      j = 1;
    }
    else
    {
      sum -= 1;
      j = 0;
    }
    pthread_mutex_unlock(&lock);
  }
}

__attribute__ ((noinline)) void *thread_add_func3(void * param)
{
  pthread_barrier_wait(&barr);
  int i;
  for (i = 0; i < *((int*)param); i++)
    __sync_add_and_fetch(&sum, 1);
}

void test_func(void* (*func)(void *), int threads, int loop, const char *name)
{
  pthread_barrier_init(&barr, NULL, threads + 1);

  pthread_t tids[MAX_THREADS];

  int i;
  sum = 0;

  for (i = 0; i < threads; i++)
    pthread_create(&tids[i], NULL, func, (void*)&loop);

  pthread_barrier_wait(&barr);
  time_t start = time(NULL);

  for (i = 0; i < threads; i++)
    pthread_join(tids[i], NULL);

  printf("%s:\tsum: %d, time: %d seconds\n",
         name, sum, time(NULL) - start);
}

int main(int argc, char *argv[]) {
  int loop = 8;
  int threads = 4;

  printf("threads: %d, loops per thread: %d\n", threads, loop);

  test_func(thread_add_func0, threads, loop, "mutex-void");  // 结果为 0，不正确
  test_func(thread_add_func1, threads, loop, "mutex-sum");
  test_func(thread_add_func2, threads, loop, "mutex-sum-2");
  test_func(thread_add_func3, threads, loop, "gcc atomic add");

  printf("\n");

  return 0;
}