#include <omp.h>

#include <iostream>

#include <cstdlib>

#include <ctime>

using namespace std;

const int N = 800;

void matrix_vector_mult(float A[][N], float B[], float C[], int n, int num_threads) {

    int i, j;

    float sum;

    omp_set_num_threads(num_threads);

    #pragma omp parallel for private(j, sum)

    for (i = 0; i < n; i++) {

        sum = 0.0;

        for (j = 0; j < n; j++) {

            sum += A[i][j] * B[j];

        }

        C[i] = sum;

    }

}

int main() {

    float A[N][N], B[N], C[N];

    int i, j, num_threads;

    double start_time, end_time;

    // Initialize matrix A and vector B with random values

    srand(time(0));

    for (i = 0; i < N; i++) {

        B[i] = (float)rand() / RAND_MAX;

        for (j = 0; j < N; j++) {

            A[i][j] = (float)rand() / RAND_MAX;

        }

    }

    // Perform matrix-vector multiplication using OpenMP multi-threading with 1, 2, 4, 8, 12, and 16 threads

    for (num_threads = 1; num_threads <= 16; num_threads *= 2) {

        start_time = omp_get_wtime();

        matrix_vector_mult(A, B, C, N, num_threads);

        end_time = omp_get_wtime();

        cout << "Time taken with " << num_threads << " threads: " << end_time - start_time << " seconds" << endl;

    }

    return 0;

}