#include<iostream>
#include<cstdlib>
#include <thread>
#include<windows.h>
using namespace std;

// maximum size of matrix
static const long MAX = 4;

// maximum number of threads
static const int MAX_THREAD = 4;

int matA[MAX][MAX];
int matB[MAX][MAX];
int matC[MAX][MAX];
int step_i = 0;

void* multi(void* arg)
{
	int core = step_i++;


	for (int i = core * MAX / 4; i < (core + 1) * MAX / 4; i++)
		for (int j = 0; j < MAX; j++)
			for (int k = 0; k < MAX; k++)
				matC[i][j] += matA[i][k] * matB[k][j];
}


int main()
{

	for (int i = 0; i < MAX; i++) {
		for (int j = 0; j < MAX; j++) {
			matA[i][j] = rand() % 10;
			matB[i][j] = rand() % 10;
		}
	}


	cout << endl
		<< "Matrix A" << endl;
	for (int i = 0; i < MAX; i++) {
		for (int j = 0; j < MAX; j++)
			cout << matA[i][j] << " ";
		cout << endl;
	}


	cout << endl
		<< "Matrix B" << endl;
	for (int i = 0; i < MAX; i++) {
		for (int j = 0; j < MAX; j++)
			cout << matB[i][j] << " ";
		cout << endl;
	}

	// declaring four threads
	std::thread threads[MAX_THREAD];


	// Creating four threads, each evaluating its own part
	for (int i = 0; i < MAX_THREAD; i++) {

		int* p;
		threads[i] = std::thread(multi, std::ref(*p), i);

	}

	// joining and waiting for all threads to complete
	for (int i = 0; i < MAX_THREAD; i++)
		threads[i].join();
	// Displaying the result matrix
	cout << endl
		<< "Multiplication of A and B" << endl;
	for (int i = 0; i < MAX; i++) {
		for (int j = 0; j < MAX; j++)
			cout << matC[i][j] << " ";
		cout << endl;
	}


	system("pause");
	return 0;
}