#include <iostream>
#include <ctime>
#include <arm_neon.h>

using namespace std;

#define H 5
#define W 5

// 打印矩阵
void printMatrix(float matrix[H][W]) {
    for (int i = 0; i < H; ++i) {
        for (int j = 0; j < W; ++j) {
            cout << matrix[i][j] << " ";
        }
        cout << endl;
    }
}

int main() {
    // 输入的5×5图像矩阵
    float src[H][W] = {
        {1, 2, 3, 4, 5},
        {6, 7, 8, 9, 10},
        {11, 12, 13, 14, 15},
        {16, 17, 18, 19, 20},
        {21, 22, 23, 24, 25}
    };

    // 高斯模糊核
    float kernel[3][3] = {
        {1/16.0, 2/16.0, 1/16.0},
        {2/16.0, 4/16.0, 2/16.0},
        {1/16.0, 2/16.0, 1/16.0}
    };

    // 行列分离核
    float kx[3] = {1/4.0, 2/4.0, 1/4.0};
    float ky[3] = {1/4.0, 2/4.0, 1/4.0};

    float dst1[H][W] = {0}, dst2[H][W] = {0}, dst3[H][W] = {0};

    // 计时步骤1
    clock_t start1 = clock();
    // applyGaussianBlur(src, dst1, H, W, kernel); // 假设已实现
    clock_t end1 = clock();

    // 计时步骤2
    clock_t start2 = clock();
    // applySeparableGaussianBlur(src, dst2, H, W, kx, ky); // 假设已实现
    clock_t end2 = clock();

    // 计时步骤3
    clock_t start3 = clock();
    // applySeparableGaussianBlur_NEON(src, dst3, H, W, kx, ky); // 假设已实现
    clock_t end3 = clock();

    // 结果输出
    cout << "步骤1输出矩阵:" << endl;
    printMatrix(dst1);
    cout << "步骤1运行时间: " << (double)(end1 - start1) / CLOCKS_PER_SEC << " 秒" << endl;

    cout << "步骤2输出矩阵:" << endl;
    printMatrix(dst2);
    cout << "步骤2运行时间: " << (double)(end2 - start2) / CLOCKS_PER_SEC << " 秒" << endl;

    cout << "步骤3输出矩阵:" << endl;
    printMatrix(dst3);
    cout << "步骤3运行时间: " << (double)(end3 - start3) / CLOCKS_PER_SEC << " 秒" << endl;

    return 0;
}