cuda——数组相加（矢量和）

#include <stdio.h>
#define N 65535//数组长度
#define M 128//指定的每个线程块的线程数量
int a[N],b[N],c[N];
__global__ void add(int* a,int* b,int* c){
	int tid = threadIdx.x+blockIdx.x*blockDim.x;//计算线程索引
	while(tid < N){
		c[tid] = a[tid]+b[tid];
		tid += gridDim.x*blockDim.x;
	}
}
int main(){
	int i;
	int *d_a,*d_b,*d_c;
	for(i = 0;i<N;i++){
		a[i] = 0;
		b[i] = i;
	}
	//在GPU上分配内存
	cudaMalloc((void**)&d_a,sizeof(int)*N);	
	cudaMalloc((void**)&d_b,sizeof(int)*N);
	cudaMalloc((void**)&d_c,sizeof(int)*N);
	//将数组a和b复制到GPU	
	cudaMemcpy(d_a,a,N*sizeof(int),cudaMemcpyHostToDevice);
	cudaMemcpy(d_b,b,N*sizeof(int),cudaMemcpyHostToDevice);
	//调用核函数进行运算s
	add<<<(N+M-1)/M,M>>>(d_a,d_b,d_c);
	//将数组c从GPU复制到CPU	
	cudaMemcpy(c,d_c,N*sizeof(int),cudaMemcpyDeviceToHost);
	for(i = N-10;i<N;i++)
		printf("%d+%d=%d\n",a[i],b[i],c[i]);
	//释放GPU上的内存	
	cudaFree(d_a);
	cudaFree(d_b);
	cudaFree(d_c);
}