vectorAdd2.cu

#include<stdio.h>
#include<cuda_runtime.h>
#include<device_launch_parameters.h>
#define SIZE 2048

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

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

    int 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);

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

    cudaMemcpy(d_A, A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, B, size, cudaMemcpyHostToDevice);
    
    cudaEvent_t start, stop;
    cudaEventCreate(&start);
    cudaEventCreate(&stop);

    cudaEventRecord(start);
    vectorAdd<<<2, 32>>> (d_A, d_B, d_C, SIZE);
    cudaEventRecord(stop);

    cudaMemcpy(C, d_C, size, cudaMemcpyDeviceToHost);

    cudaEventSynchronize(stop);
    float milliseconds = 0;
    cudaEventElapsedTime(&milliseconds, start, stop);
    printf("execution time: %f millis\n", milliseconds);

    // 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;
}