cuda之两个向量点乘

1.简介

本文中主要介绍了使用block来集散，每个block计算数组上对应两个数的乘积，最后将结果数组拷贝到CPU主内存上即可。

2.cuda代码演示

#include<iostream>
#include<cstdlib>
using namespace std;
#define N 100
__global__ void add(int *a,int *b,int *c) {
	int ind = blockIdx.x;
	c[ind] = a[ind] * b[ind];
}

void initialVector(int length,int *arr,int limit) {
	for(int i=0;i<length;i++,limit++)
		*(arr+i) = limit;
}
int main() {
	int *a,*b,*c;
	a = (int *)malloc(sizeof(int)*N);
	b = (int *)malloc(sizeof(int)*N);
	c = (int *)malloc(sizeof(int)*N);
	initialVector(N,a,1);
	initialVector(N,b,1);
	int *d_a,*d_b,*d_c;
        /* allocate memory on device */
	cudaMalloc((void **)&d_a,N*sizeof(int));	
	cudaMalloc((void **)&d_b,N*sizeof(int));	
	cudaMalloc((void **)&d_c,N*sizeof(int));	
	cudaMemcpy(d_a,a,N*sizeof(int),cudaMemcpyHostToDevice);
	cudaMemcpy(d_b,b,N*sizeof(int),cudaMemcpyHostToDevice);
	add<<<N,1>>>(d_a,d_b,d_c);
	cudaMemcpy(c,d_c,N*sizeof(int),cudaMemcpyDeviceToHost);
	cout<<"c["<<N-1<<"]:"<<c[N-1]<<endl;
	free(a);
	free(b);
	free(c);
	cudaFree(d_a);
	cudaFree(d_b);
	cudaFree(d_c);
	return 0;
}