矩阵相加CUDA实现
//矩阵相加的CUDA程序实现
//Author: Eric Lv
//Email: Eric2014_Lv@sjtu.edu.cn
//Date: 6/7/2017
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#include <math.h>
#include <stdlib.h>
//#include <cuda.h>
#define N 32
__global__ void matrix_add(const int a[][N], const int b[][N],