sum_array.cu

#include <stdio.h>

// Kernel function to add two arrays
__global__ void addArrays(int *a, int *b, int *c, int size) {
    int tid = threadIdx.x + blockIdx.x * blockDim.x;
    if (tid < size) {
        c[tid] = a[tid] + b[tid];
    }
}

int main() {
    int size = 100; // Size of the arrays
    int a[size], b[size], c[size]; // Host arrays
    int *d_a, *d_b, *d_c; // Device arrays

    // Initialize arrays
    for (int i = 0; i < size; i++) {
        a[i] = i;
        b[i] = i * 2;
    }

    // Allocate memory on GPU
    cudaMalloc((void **)&d_a, size * sizeof(int));
    cudaMalloc((void **)&d_b, size * sizeof(int));
    cudaMalloc((void **)&d_c, size * sizeof(int));

    // Copy data from host to device
    cudaMemcpy(d_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, b, size * sizeof(int), cudaMemcpyHostToDevice);

    // Define grid and block dimensions
    int blockSize = 256;
    int numBlocks = (size + blockSize - 1) / blockSize;

    // Launch kernel
    addArrays<<<numBlocks, blockSize>>>(d_a, d_b, d_c, size);

    // Copy result from device to host
    cudaMemcpy(c, d_c, size * sizeof(int), cudaMemcpyDeviceToHost);

    // Print result
    printf("Result:\n");
    for (int i = 0; i < size; i++) {
        printf("%d + %d = %d\n", a[i], b[i], c[i]);
    }

    // Free device memory
    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_c);

    return 0;
}