vector_add.cu

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <assert.h>
#include <cuda.h>
#include <cuda_runtime.h>

#define N 10
#define MAX_ERR 1e-6

__global__ void vector_add(float *out, float *a, float *b, int n)
{
    for (int i = 0; i < n; i++)
    {
        out[i] = a[i] + b[i];
    }
}

int main()
{
    float *a, *b, *out;
    float *d_a, *d_b, *d_out;

    // Allocate host memory
    printf("Allocating host memory\n");
    a = (float *)malloc(sizeof(float) * N);
    b = (float *)malloc(sizeof(float) * N);
    out = (float *)malloc(sizeof(float) * N);

    // Initialize host arrays
    printf("Initializing host arrays\n");
    for (int i = 0; i < N; i++)
    {
        a[i] = 1.0f;
        b[i] = 2.0f;
    }

    // Allocate device memory
    printf("Allocating device memory\n");
    cudaMalloc((void **)&d_a, sizeof(float) * N);
    cudaMalloc((void **)&d_b, sizeof(float) * N);
    cudaMalloc((void **)&d_out, sizeof(float) * N);

    // Transfer data from host to device memory
    printf("Transferring data from host to device memory\n");
    cudaMemcpy(d_a, a, sizeof(float) * N, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, b, sizeof(float) * N, cudaMemcpyHostToDevice);

    // Executing kernel
    printf("Executing kernel\n");
    vector_add<<<1, 1>>>(d_out, d_a, d_b, N);

    // Transfer data back to host memory
    printf("Transferring data back to host memory\n");
    cudaMemcpy(out, d_out, sizeof(float) * N, cudaMemcpyDeviceToHost);

    // Verification
    printf("Verifying\n");
    for (int i = 0; i < N; i++)
    {
        assert(fabs(out[i] - a[i] - b[i]) < MAX_ERR);
    }
    printf("out[0] = %f\n", out[0]);

    // Deallocate device memory
    printf("Deallocating device memory\n");
    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_out);

    // Deallocate host memory
    printf("Deallocating host memory\n");
    free(a);
    free(b);
    free(out);

    printf("PASSED\n");
}