#include <iostream>
#include <math.h>
#include <omp.h>
#include <random>
using namespace std;

#pragma comment(linker, "/STACK:1024000000")
int main()
{

    /*int N = 100;
    int n = 1;
    double sum = 0.0;
    double start, end;
    start = omp_get_wtime();
    #pragma omp parallel for private(n) reduction(+:sum) num_threads(8) schedule(guided, 10000)
    for(n = 1; n <= N; n++)
    {
        sum+= pow(-1, n) / (pow((2 * n + 1), 3) - 1);
    }
    end = omp_get_wtime();
    cout << "Sum = " << sum << endl;
    cout << "Num Thread = " << omp_get_thread_num() << endl;
    cout << "Work took seconds  " << end - start;*/

    srand(time(0));
    cout << "count repeat" << endl;
    int q;
    cin >> q;

    const int N = 5;
    int i, j;
    float A[N][N];
    float B[N][N];
    float C[N][N];
    float sum;
    for (i = 0; i < N; i++) {
        for (j = 0; j < N; j++) {
            A[i][j] = (floorf((rand() * 1.0 / RAND_MAX - 0.5) * 100)) / 100;
            B[i][j] = (floorf((rand() * 1.0 / RAND_MAX - 0.5) * 100)) / 100;
            C[i][j] = 0.0;
        }
    }
    double start, end;

    start = omp_get_wtime();
    for (int l = 0; l < q; l++)
        for (i = 0; i < N; i++) {
            for (j = 0; j < N; j++) {
                sum = 0;
                for (int k = 0; k < N; k++)
                    sum += A[i][k] * B[k][j];
                C[i][j] = sum;
            }
        }
    end = omp_get_wtime();
    cout << "Matrix C:" << endl << C[0][0] << " " << C[N - 1][0] << endl << C[0][N - 1] << " " << C[N - 1][N - 1] << endl;
    cout << "Work took seconds non parallel  " << end - start << endl;

    start = omp_get_wtime();
    for (int l = 0; l < q; l++)
    {
#pragma omp parallel for private(i,j)
        for (i = 0; i < N; i++) {
            for (j = 0; j < N; j++) {
                sum = 0;
                for (int k = 0; k < N; k++)
                    sum += A[i][k] * B[k][j];
                C[i][j] = sum;
            }
        }
    }
    end = omp_get_wtime();
    cout << "Matrix C:" << endl << C[0][0] << " " << C[N - 1][0] << endl << C[0][N - 1] << " " << C[N - 1][N - 1] << endl;
    cout << "Work took seconds parallel i  " << end - start << endl;


    start = omp_get_wtime();
    for (int l = 0; l < q; l++)
    {
        for (i = 0; i < N; i++) {
#pragma omp parallel for
            for (j = 0; j < N; j++) {
                sum = 0;
                for (int k = 0; k < N; k++)
                    sum += A[i][k] * B[k][j];
                C[i][j] = sum;
            }
        }
    }
    end = omp_get_wtime();
    cout << "Matrix C:" << endl << C[0][0] << " " << C[N - 1][0] << endl << C[0][N - 1] << " " << C[N - 1][N - 1] << endl;
    cout << "Work took seconds parallel j  " << end - start << endl;


    start = omp_get_wtime();
    for (int l = 0; l < q; l++)
    {
        for (i = 0; i < N; i++) {
            for (j = 0; j < N; j++) {
                sum = 0;
                #pragma omp parallel for reduction(+:sum)
                for (int k = 0; k < N; k++)
                    sum += A[i][k] * B[k][j];
                C[i][j] = sum;
            }
        }
    }
    end = omp_get_wtime();
    cout << "Matrix C:" << endl << C[0][0] << " " << C[N - 1][0] << endl << C[0][N - 1] << " " << C[N - 1][N - 1] << endl;
    cout << "Work took seconds parallel k  " << end - start << endl;

}