CUDA例子

一维数组相加

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#define N 10

__global__ void add(int *a, int *b, int *c)
{
    int tid =blockIdx.x;
    c[tid] = a[tid] + b[tid];

}
int main()
{
    int a[N], b[N], c[N];
    int *deva, *devb, *devc;
    //在GPU上分配内存
    cudaMalloc((void **)&deva, N*sizeof(int));
    cudaMalloc((void **)&devb, N*sizeof(int));
    cudaMalloc((void **)&devc, N*sizeof(int));

    //在CPU上为数组赋值
    for (int