我创建了一个矩阵乘法程序,一个串行执行,一个使用pthread并发。我需要比较它们的运行时间。我的串行代码花费约16秒来计算1000x1000的矩阵乘法,并且我用秒表检查过,结果正好如预期一样。另一方面,当我运行我的pthread矩阵乘法程序时,我会得到大约22-23秒的结果,但结果在终端上打印得比较快。我还使用秒表检查输出运行时间所需的时间,它大约为6秒,但它打印说花费了约23秒。我猜测有其他方法来检查pthread程序的运行时间。以下是我的pthread代码:
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <pthread.h>
#include <assert.h>
int SIZE, NTHREADS;
int **A, **B, **C;
void init()
{
int i, j;
A = (int**)malloc(SIZE * sizeof(int *));
for(i = 0; i < SIZE; i++)
A[i] = malloc(SIZE * sizeof(int));
B = (int**)malloc(SIZE * sizeof(int *));
for(i = 0; i < SIZE; i++)
B[i] = malloc(SIZE * sizeof(int));
C = (int**)malloc(SIZE * sizeof(int *));
for(i = 0; i < SIZE; i++)
C[i] = malloc(SIZE * sizeof(int));
srand(time(NULL));
for(i = 0; i < SIZE; i++) {
for(j = 0; j < SIZE; j++) {
A[i][j] = rand()%100;
B[i][j] = rand()%100;
}
}
}
void mm(int tid)
{
int i, j, k;
int start = tid * SIZE/NTHREADS;
int end = (tid+1) * (SIZE/NTHREADS) - 1;
for(i = start; i <= end; i++) {
for(j = 0; j < SIZE; j++) {
C[i][j] = 0;
for(k = 0; k < SIZE; k++) {
C[i][j] += A[i][k] * B[k][j];
}
}
}
}
void *worker(void *arg)
{
int tid = (int)arg;
mm(tid);
}
int main(int argc, char* argv[])
{
pthread_t* threads;
int rc, i;
if(argc != 3)
{
printf("Usage: %s <size_of_square_matrix> <number_of_threads>\n", argv[0]);
exit(1);
}
SIZE = atoi(argv[1]);
NTHREADS = atoi(argv[2]);
init();
threads = (pthread_t*)malloc(NTHREADS * sizeof(pthread_t));
clock_t begin, end;
double time_spent;
begin = clock();
for(i = 0; i < NTHREADS; i++) {
rc = pthread_create(&threads[i], NULL, worker, (void *)i);
assert(rc == 0);
}
for(i = 0; i < NTHREADS; i++) {
rc = pthread_join(threads[i], NULL);
assert(rc == 0);
}
end = clock();
time_spent = (double)(end - begin) / CLOCKS_PER_SEC;
printf("Elapsed time: %.2lf seconds.\n", time_spent);
for(i = 0; i < SIZE; i++)
free((void *)A[i]);
free((void *)A);
for(i = 0; i < SIZE; i++)
free((void *)B[i]);
free((void *)B);
for(i = 0; i < SIZE; i++)
free((void *)C[i]);
free((void *)C);
free(threads);
return 0;
}