openMP 实现knn

OpenMP 是一种用于多线程编程的API，可以用于并行化各种类型的算法。下面是使用OpenMP并行化kNN算法的示例代码：

#include <iostream>
#include <cmath>
#include <omp.h>

using namespace std;

const int k = 3; // k值

// 计算欧几里得距离
float euclidean_distance(float a[], float b[], int dim) {
    float dist = 0.0;
    for (int i = 0; i < dim; i++) {
        dist += pow(a[i] - b[i], 2);
    }
    return sqrt(dist);
}

int main() {
    // 样本数据
    float samples[10][3] = {
        {2.0, 3.0, 1.0},
        {4.0, 2.0, 9.0},
        {3.0, 1.0, 5.0},
        {6.0, 7.0, 3.0},
        {9.0, 8.0, 4.0},
        {5.0, 1.0, 2.0},
        {8.0, 3.0, 6.0},
        {1.0, 4.0, 7.0},
        {7.0, 8.0, 9.0},
        {4.0, 5.0, 8.0}
    };

    // 查询点
    float query_point[3] = {4.5, 2.5, 3.5};

    int num_samples = sizeof(samples) / sizeof(samples[0]);
    float distances[num_samples];

    #pragma omp parallel for
    for (int i = 0; i < num_samples; i++) {
        distances[i] = euclidean_distance(samples[i], query_point, 3);
    }

    int indices[k];
    for (int i = 0; i < k; i++) {
        float min_dist = INFINITY;
        int min_index = -1;

        #pragma omp parallel for
        for (int j = 0; j < num_samples; j++) {
            if (distances[j] < min_dist) {
                bool already_selected = false;
                for (int m = 0; m < i; m++) {
                    if (indices[m] == j) {
                        already_selected = true;
                        break;
                    }
                }
                if (!already_selected) {
                    min_dist = distances[j];
                    min_index = j;
                }
            }
        }

        indices[i] = min_index;
    }

    cout << "The " << k << " nearest neighbors are: ";
    for (int i = 0; i < k; i++) {
        cout << indices[i] << " ";
    }
    cout << endl;

    return 0;
}

在上面的代码中，我们使用了 `#pragma omp parallel for` 来标记需要并行化的循环。在第一个循环中，我们计算了每个样本与查询点之间的距离。在第二个循环中，我们找到了距离查询点最近的k个样本。这两个循环都可以使用OpenMP并行化，从而提高算法的执行效率。