OpenMP code is aborted - c++

Question

I'm trying to perform matrix multiplication using openMP as follows and I compile it using GCC : g++ -std=gnu++11 -g -Wall -fopenmp -o parallel_not_opt parallel_not_opt.cpp
But when I try to run it by using parallel_not_opt.exe, it aborts giving the typical Windows error parallel_not_opt.exe has stopped working...
Am I missing something?
#include "includes/stdafx.h"
#include <iostream>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <vector>
# include <omp.h>
#include <chrono>
#include <fstream>
#include <algorithm>
#include <immintrin.h>
#include <cfloat>
#include <limits>
#include <math.h>
using namespace std::chrono;
using namespace std;
//populate matrix with random values.
double** generateMatrix(int n){
double max = DBL_MAX;
double min = DBL_MIN;
double** matA = new double*[n];
for (int i = 0; i < n; i++) {
matA[i] = new double[n];
for (int j = 0; j < n; j++) {
double randVal = (double)rand() / RAND_MAX;
matA[i][j] = min + randVal * (max - min);
}
}
return matA;
}
//generate matrix for final result.
double** generateMatrixFinal(int n){
double** matA = new double*[n];
for (int i = 0; i < n; i++) {
matA[i] = new double[n];
for (int j = 0; j < n; j++) {
matA[i][j] = 0;
}
}
return matA;
}
//matrix multiplication - parallel
double matrixMultiplicationParallel(double** A, double** B, double** C, int n){
int i, j, k;
clock_t begin_time = clock();
# pragma omp parallel shared ( A,B,C,n ) // private ( i, j, k )
{
# pragma omp for
for (i = 0; i < n; i++) {
// cout<< i << ", " ;
for (j = 0; j < n; j++) {
for (k = 0; k < n; k++) {
C[i][j] += A[i][k] * B[k][j];
}
}
}
}
double t = float(clock() - begin_time);
return t;
}
int _tmain(int argc, _TCHAR* argv[])
{
ofstream out("output.txt", ios::out | ios::app);
out << "--------------STARTED--------------" << "\n";
int start = 200, stop = 2000, step = 200;
for (int n = start; n <= stop; n += step)
{
srand(time(NULL));
cout << "\nn: " << n << "\n";
double t1 = 0;
int my_size = n;
double **A = generateMatrix(my_size);
double **B = generateMatrix(my_size);
double **C = generateMatrixFinal(my_size);
double single_sample_time = matrixMultiplicationParallel(A, B, C, n);
t1 += single_sample_time;
for (int i = 0; i < n; i++) {
delete[] A[i];
delete[] B[i];
delete[] C[i];
}
delete[] A;
delete[] B;
delete[] C;
}
out << "-----------FINISHED-----------------" << "\n";
out.close();
return 0;
}

Answer 1

The private ( i, j, k ) declaration is not optional. Add it back, otherwise the inner loop variables j and k are shared, which completely messes up the inner loops.
It is better to declare variables as locally as possible. That makes reasoning about OpenMP code much easier:
clock_t begin_time = clock();
# pragma omp parallel
{
# pragma omp for
for (int i = 0; i < n; i++) {
for (int j = 0; j < n; j++) {
for (int k = 0; k < n; k++) {
C[i][j] += A[i][k] * B[k][j];
}
}
}
}
return float(clock() - begin_time);
In that case, A,B,C will be shared by default - coming from the outside, and j,k are private because they are declared within the parallel scope. The loop variable of a parallel for is always implicitly private.