PThread并行实现矩阵乘法

最新推荐文章于 2022-04-25 15:08:20 发布

94Howen

最新推荐文章于 2022-04-25 15:08:20 发布

阅读量1.8k

点赞数

分类专栏： High-performance Computing 文章标签： c++ eclipse parallel matrix

本文链接：https://blog.csdn.net/tim365/article/details/42027207

版权

本文档详细介绍了如何利用Eclipse Luna在OS X 10.10环境下，通过PThread库来实现高效的矩阵乘法并行计算。通过这种方式，可以充分利用多核处理器的计算能力，提升程序的运行效率。

摘要由CSDN通过智能技术生成

以下用Eclipse luna 在OS X 10.10下编译通过。

#include "MatrixMultiplication.h"

void* Hello(void* rank);

int main() {
	long thread;
	pthread_t* thread_handles;
	thread_handles = reinterpret_cast<pthread_t*>(malloc(
			thread_count * sizeof(pthread_t)));
	for (thread = 0; thread < thread_count; thread++) {
		pthread_create(&thread_handles[thread], NULL, Hello, (void*) thread);
	}
	printf("Hello world from the main thread.\n");
	for (thread = 0; thread < thread_count; thread++) {
		pthread_join(thread_handles[thread], NULL);
	}
	free(thread_handles);
	GenerateMatrix();
	printf("\nBegin to multiply two matrix...\n");
	MultiplyMatrix();

	return 0;
}

void* Hello(void* rank) {
	long my_rank = reinterpret_cast<long>(rank);
	printf("Hello world from %ld thread of %ld.\n", my_rank, thread_count);
	return NULL;
}

#include <iostream>
#include <stdlib.h>
#include <stdio.h>
#include <pthread.h>
#include <fstream>
#include <sys/time.h>

#define MATRIX_COLUMN 1000
#define MATRIX_ROW 1000

using namespace std;

long thread_count = 2; //Actually, the number of the threads is thread_count square.

int matrix_a[MATRIX_ROW][MATRIX_COLUMN];
int matrix_b[MATRIX_ROW][MATRIX_COLUMN];
int serial_result_matrix[MATRIX_ROW][MATRIX_COLUMN];
int parallel_result_matrix[MATRIX