CUDA By Examples 2 - 并行计算向量相加

#include "book.h"

#define N 2880
// __global__ 表示程序在GPU上运行
__global__ void add(int *a, int *b, int *c)
{
    // 每一个block的blockIdx.x都不一样
    int tid = blockIdx.x;
    //判断: 为了防止内存越界,进程被kill. 
    if (tid<N)
        c[tid]=a[tid]+b[tid];
}

int main(void)
{
    int a[N], b[N], c[N];
    int *dev_a, *dev_b, *dev_c;
    //分配内存
    HANDLE_ERROR( cudaMalloc((void**)&dev_a, N*sizeof(int)));
    HANDLE_ERROR( cudaMalloc((void**)&dev_b, N*sizeof(int)));
    HANDLE_ERROR( cudaMalloc((void**)&dev_c, N*sizeof(int)));
    // 向量的内容可以在CPU上fill, 也可以在GPU上fill
    for (int i=0; i<N; i++)
    {
        a[i] = -i;
        b[i] = i*i;
    }
    //copy到GPU上
    HANDLE_ERROR(cudaMemcpy(dev_a, a, N*sizeof(int),
                            cudaMemcpyHostToDevice));
    HANDLE_ERROR(cudaMemcpy(dev_b, b, N*sizeof(int),
                            cudaMemcpyHostToDevice));
    // 指定N个block, 每个block有1个thread
    add<<<N,1>>>(dev_a, dev_b, dev_c);
    //copy到CPU上
    HANDLE_ERROR(cudaMemcpy(c, dev_c, N*sizeof(int),
                            cudaMemcpyDeviceToHost));

    for (int i=0; i<N; i++)
    {
        printf("%d +%d = %d\n", a[i],b[i],c[i]);
    }
    //GPU释放资源
    cudaFree(dev_a);
    cudaFree(dev_b);
    cudaFree(dev_c);

    return 0;

}