OpenMP用于矩阵乘法

我是OpenMP新手，正在拼命学习。我试图在visual studio 2012中编写c++示例代码来实现矩阵乘法。我希望有OpenMP经验的人可以看看这段代码，并帮助我获得最终的速度/并行化:

#include <iostream>
#include <stdlib.h>
#include <omp.h>
#include <random>
using namespace std;
#define NUM_THREADS 4
// Program Variables
double**        A;
double**        B;
double**        C;
double          t_Start;
double          t_Stop;
int             Am;
int             An;
int             Bm;
int             Bn;
// Program Functions
void            Get_Matrix();
void            Mat_Mult_Serial();
void            Mat_Mult_Parallel();
void            Delete_Matrix();

int main()
{
    printf("Matrix Multiplication Programnn");
    cout << "Enter Size of Matrix A: ";
    cin >> Am >> An;
    cout << "Enter Size of Matrix B: ";
    cin >> Bm >> Bn;
    Get_Matrix();
    Mat_Mult_Serial();
    Mat_Mult_Parallel();

    system("pause");
    return 0;
}

void Get_Matrix()
{
    A = new double*[Am];
    B = new double*[Bm];
    C = new double*[Am];
    for ( int i=0; i<Am; i++ ){A[i] = new double[An];}
    for ( int i=0; i<Bm; i++ ){B[i] = new double[Bn];}
    for ( int i=0; i<Am; i++ ){C[i] = new double[Bn]; }
    for ( int i=0; i<Am; i++ )
    {
         for ( int j=0; j<An; j++ )
         {
             A[i][j]= rand() % 10 + 1;
         }
    }
    for ( int i=0; i<Bm; i++ )
    {
        for ( int j=0; j<Bn; j++ )
        {
            B[i][j]= rand() % 10 + 1;
        }
    }
    printf("Matrix Create Complete.n");
}

void Mat_Mult_Serial()
{
    t_Start = omp_get_wtime();
    for ( int i=0; i<Am; i++ )
    {
        for ( int j=0; j<Bn; j++ )
        {
            double temp = 0;
            for ( int k=0; k<An; k++ )
            {
                temp += A[i][k]*B[k][j];
            }
        }
    }
    t_Stop = omp_get_wtime() - t_Start;
    cout << "Serial Multiplication Time: " << t_Stop << " seconds" << endl;
    }

void Mat_Mult_Parallel()
{
    int i,j,k;
    t_Start = omp_get_wtime();
    omp_set_num_threads(NUM_THREADS);
    #pragma omp parallel for private(i,j,k) schedule(dynamic)
    for ( i=0; i<Am; i++ )
    {
        for ( j=0; j<Bn; j++ )
        {
            //double temp = 0;
            for ( k=0; k<An; k++ )
            {
                C[i][j] += A[i][k]*B[k][j];
            }
        }
    }
    t_Stop = omp_get_wtime() - t_Start;
    cout << "Parallel Multiplication Time: " << t_Stop << " seconds." << endl;
}

void Delete_Matrix()
{
    for ( int i=0; i<Am; i++ ){ delete [] A[i]; }
    for ( int i=0; i<Bm; i++ ){ delete [] B[i]; }
    for ( int i=0; i<Am; i++ ){ delete [] C[i]; }
    delete [] A;
    delete [] B;
    delete [] B;
}