Блочное умножение cpp определяет точку входа для консольного приложени

// Блочное умножение.cpp: определяет точку входа для консольного приложения.
//

#include "stdafx.h"
#include <pthread.h>
#include <iostream>
#include <locale.h>
#include <time.h>

using namespace std;

pthread_mutex_t mut = PTHREAD_MUTEX_INITIALIZER;

int n=4;
int m=4;
int blN = 2, blM = 2;
int p = blN*blM;
pthread_t **threads;
int *b, *c;
int **a;
long times = clock();

struct Block
{
	int begN;
	int endN;
	int begM;
	int endM;
};

void multiple(int begN, int endN, int begM, int endM)
{
	int *tmp = (int*)malloc((endN-begN)*sizeof(int));
	for (int i = 0; i < endN - begN; i++)
		tmp[i] = 0;
	for (int i = begN; i < endN; i++)
		for (int j = begM; j < endM; j++)
			tmp[i - begN]+= a[i][j] * b[j];
		for (int j = begN; j < endN; j++)
		{
			pthread_mutex_lock(&mut);
			c[j] += tmp[j - begN];
			cout << "c[" << j << "]=" << c[j] << "\n";
			pthread_mutex_unlock(&mut);
		}
		delete[] tmp;
}

void *process_function(void *pa)
{
	Block bl = *((struct Block *)pa);
	multiple(bl.begN, bl.endN, bl.begM, bl.endM);
	delete (struct Block *)pa;
	return 0;
}


int main()
{
	setlocale(LC_ALL, "Rus");
	a = (int**)malloc(n*sizeof(int));
	for (int i = 0; i < n; i++)
		a[i] = (int*)malloc(m*sizeof(int));
	b = (int*)malloc(m*sizeof(int));
	c = (int*)malloc(n*sizeof(int));
	threads = new pthread_t*[blN];
	for (int i = 0; i<blN; i++) 
		threads[i] = new pthread_t[blM];
	for (int i = 0; i < n; i++)
		c[i] = 0;
	for (int i = 0; i < n; i++)
	for (int j = 0; j < m; j++)
	{
		a[i][j] = rand() % 5;
		cout << a[i][j] << ' ';
		if (j == m - 1) cout << "\n";
	}
	cout << endl;
	for (int i = 0; i < m; i++)
	{
		b[i] = rand() % 5;
		cout << b[i] << "\n";
	}
	cout << endl;
	int locM = m / blM;
	int locN = n / blN;
	int ostM = m%blM;
	int ostN = n%blN;
	int endM = 0, endN = 0;
	
	for (int i = 0; i < blN; i++)
	{
		Block *bl = new Block;
		bl->begN = endN;
		if (ostN > 0)
			bl->endN = bl->begN + locN + 1;
		else
			bl->endN = bl->begN + locN;
		endN = bl->endN;
		endM = 0;
		ostM = n%blM;
		for (int j = 0; j < blM; j++)
		{
			Block *block = new Block;
			block = bl;
			block->begM = endM;
			if (ostM > 0)
				block->endM = block->begM + locM + 1;
			else
				block->endM = block->begM + locM;
			endM = block->endM;
			pthread_create(&threads[i][j], NULL, process_function, block);
		}
		free(bl);
	}
	for (int i = 0; i<blN; i++)
		for (int j = 0; j<blM; j++)
			if (pthread_join(threads[i][j], NULL))
				fprintf(stderr, "wait thread #d!\n", i,j);
	cout << "Результат: \n";
	for (int i = 0; i<n; i++) 
		cout << c[i] << '\n';
	cout << "Время выполнения:" << times << endl;
	for (int i = 0; i < n; i++)
		free(a[i]);
	free(a);
	free(b);
	free(c);
	return 0;
}