向量相加CUDA练习

#include<string.h>
#include<math.h>
#include<stdlib.h>
#include<stdio.h>
#define N 100

__global__ void vecAdd(float* A,float* B,float* C){
    int i=threadIdx.x;
    if(i<N)
        C[i]=A[i]+B[i];
}




int main(int argc,int argv){
    size_t size=N*sizeof(float);
    float *h_A,*h_B,*h_C;
    h_A=(float*)malloc(size);
    h_B=(float*)malloc(size);
    h_C=(float*)malloc(size);
    float* d_A;
    cudaMalloc((void**)&d_A,size);
    float* d_B;
    cudaMalloc((void**)&d_B,size);
    float* d_C;
    cudaMalloc((void**)&d_C,size);
    srand(time(NULL));
    for(int i=0;i<N;i++){
        h_A[i]=rand()%100;
        h_B[i]=rand()%100;
    }
    cudaMemcpy(d_A,h_A,size,cudaMemcpyHostToDevice);
    cudaMemcpy(d_B,h_B,size,cudaMemcpyHostToDevice);
    int threadsPerBlock=256;
    int threadsPerGrid=(N+threadsPerBlock-1)/threadsPerBlock;
    vecAdd<<<threadsPerGrid,threadsPerBlock>>>(d_A,d_B,d_C);
    cudaMemcpy(h_C,d_C,size,cudaMemcpyDeviceToHost);
    for(int i=0;i<N;i++){
        printf("%5.0d:%.0f+%.0f=%.0f
",i,h_A[i],h_B[i],h_C[i]);
    }
    free(h_A);
    free(h_B);
    free(h_C);

    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
}