Shared CUDA Code

#include <stdio.h>

__global__ void vecAdd(float *a, float *b, float *c, int n) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i < n) {
        c[i] = a[i] + b[i];
    }
}

int main() {
    int n = 1024;
    size_t bytes = n * sizeof(float);

    float *h_a = (float*)malloc(bytes);
    float *h_b = (float*)malloc(bytes);
    float *h_c = (float*)malloc(bytes);

    for (int i = 0; i < n; i++) {
        h_a[i] = i * 1.0f;
        h_b[i] = i * 2.0f;
    }

    float *d_a, *d_b, *d_c;
    cudaMalloc(&d_a, bytes);
    cudaMalloc(&d_b, bytes);
    cudaMalloc(&d_c, bytes);

    cudaMemcpy(d_a, h_a, bytes, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, h_b, bytes, cudaMemcpyHostToDevice);

    int threadsPerBlock = 256;
    int blocksPerGrid = (n + threadsPerBlock - 1) / threadsPerBlock;
    vecAdd<<<blocksPerGrid, threadsPerBlock>>>(d_a, d_b, d_c, n);

    cudaMemcpy(h_c, d_c, bytes, cudaMemcpyDeviceToHost);

    printf("c[0] = %f\n", h_c[0]);
    printf("c[1023] = %f\n", h_c[1023]);

    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_c);
    free(h_a);
    free(h_b);
    free(h_c);

    return 0;
}