//
// Created by otomo on 31.03.20.
//
#include "stdio.h"
#include "omp.h"
#include "stdlib.h"
#include "string.h"

int main(int argc, char *argv[]) {

    if(argc < 3) {
        printf("Usage: <matrix_size>");
        return EXIT_FAILURE;
    }

    int N = atoi(argv[1]);
    int c[N][N];
    int d[N][N];

    int a[N][N], b[N][N], f[N][N], l[N][N];

    double start, end, actual_time;


    // ========= INIT FIELDS =========
    for (size_t i = 0; i < N; ++i) {
        for (size_t j = 0; j < N; ++j) {
            a[i][j] = rand() % 100 + 1;
            b[i][j] = rand() % 100 + 1;
            f[i][j] = rand() % 100 + 1;
            l[i][j] = rand() % 100 + 1;
        }
    }

    if(strcmp(argv[2], "serial") == 0 ) {
        // ========= SERIAL IMPLEMENTATION 1 =========
        start = omp_get_wtime();
        for (size_t i = 0; i < N; ++i) {
            for (size_t j = 0; j < N; ++j) {
                c[i][j] = a[i][j] * b[i][j];
            }
        }
        end = omp_get_wtime();
        actual_time = end-start;
        printf("Serial implementation 1: WT Used: %f\n", actual_time);

        // ========= SERIAL IMPLEMENTATION 2 =========
        start = omp_get_wtime();
        for (size_t j = 0; j < N; ++j) {
            for (size_t i = 0; i < N; ++i) {
                c[i][j] = a[i][j] * b[i][j];
            }
        }
        end = omp_get_wtime();
        actual_time = end-start;
        printf("Serial implementation 2: WT Used: %f\n", actual_time);
        return EXIT_SUCCESS;
    }




    // ========= PARALLEL IMPLEMENTATION 1 =========
    start = omp_get_wtime();
    #pragma omp parallel for
    for (size_t i = 0; i < N; ++i) {
        #pragma omp parallel for
        for (size_t j = 0; j < N; ++j) {
            c[i][j] = a[i][j] * b[i][j];
        }
    }
    end = omp_get_wtime();
    actual_time = end-start;
    printf("Parallel implementation 1: WT Used: %f\n", actual_time);

    // ========= PARALLEL IMPLEMENTATION 2 =========
    start = omp_get_wtime();
    #pragma omp parallel for
    for (size_t j = 0; j < N; ++j) {
        #pragma omp parallel for
        for (size_t i = 0; i < N; ++i) {
            d[i][j] = a[i][j] * b[i][j];
        }
    }
    end = omp_get_wtime();
    actual_time = end-start;
    printf("Parallel implementation 2: WT Used: %f\n", actual_time);

    return EXIT_SUCCESS;
}