vectorAdd.cu

#include<stdio.h>
#include<cuda_runtime.h>


__global__ void vectorAdd(int *A, int* B, int* C, int n) {
    int i = threadIdx.x + blockDim.x * blockIdx.x;
    if(i < n) {
        C[i] = A[i] + B[i];
    }
}

int main(int argc, char **argv) {
    int *A, *B, *C;
    int *d_A, *d_B, *d_C;

    long long SIZE = 1024LL * 1024 * 32;
    long size = SIZE * sizeof(int);

    A = (int*) malloc(size);
    B = (int*) malloc(size);
    C = (int*)malloc(size);

    cudaMalloc((void**)&d_A, size);
    cudaMalloc((void**)&d_B, size);
    cudaMalloc((void**)&d_C, size);
    int threadsPerBlock = atoi(argv[1]);

    for(int i = 0; i < SIZE; ++i) {
        A[i] = i;
        B[i] = SIZE-i;
    }

    int blocksPerGrid = (SIZE + threadsPerBlock - 1) / threadsPerBlock;
    cudaMemcpy(d_A, A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, B, size, cudaMemcpyHostToDevice);

    vectorAdd<<<blocksPerGrid, threadsPerBlock>>> (d_A, d_B, d_C, SIZE);

    cudaMemcpy(C, d_C, size, cudaMemcpyDeviceToHost);

    for(int i = 0; i < SIZE; ++i) {
        printf("%d %d %d\n", A[i], B[i], C[i]);
    }

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

    free(A);
    free(B);
    free(C);

    return 0;
}