vector_add.cu

#include <iostream>
#include <cuda_runtime.h>

// CUDA kernel for vector addition
__global__ void vectorAdd(const float* A, const 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 = 1 << 20; // 1 million elements
    size_t size = N * sizeof(float);

    // Host memory allocation
    float *h_A = (float*)malloc(size);
    float *h_B = (float*)malloc(size);
    float *h_C = (float*)malloc(size);

    // Initialize host arrays
    for (int i = 0; i < N; i++) {
        h_A[i] = i * 1.0f;
        h_B[i] = i * 2.0f;
    }

    // Device memory allocation
    float *d_A, *d_B, *d_C;
    cudaMalloc((void**)&d_A, size);
    cudaMalloc((void**)&d_B, size);
    cudaMalloc((void**)&d_C, size);

    // Copy data from host to device
    cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    // Launch kernel with 256 threads per block
    int threadsPerBlock = 256;
    int blocksPerGrid = (N + threadsPerBlock - 1) / threadsPerBlock;
    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, N);

    // Copy result back to host
    cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    // Verify result
    bool success = true;
    for (int i = 0; i < N; i++) {
        if (h_C[i] != h_A[i] + h_B[i]) {
            success = false;
            break;
        }
    }

    std::cout << (success ? "Test PASSED!" : "Test FAILED!") << std::endl;

    // Free memory
    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
    free(h_A);
    free(h_B);
    free(h_C);

    return 0;
}