#include <stdio.h>
#include <conio.h>
#include <omp.h>
#include <math.h>

int main(int argc, char *argv[])
{
    int    i,j,threads,t=1;
    double Begin,End;
    float  DX[8][8] = {0};
    float  D[8][8]  = {0};
    int    C[8][8] = {0};
    int    M[8][8];

    int Origin[8][8] =  {{154,123,123,123,123,123,123,136},
                        {192,180,136,154,154,154,136,110},
                        {254,198,154,154,180,154,123,123},
                        {239,180,136,180,180,166,123,123},
                        {180,154,136,167,166,149,136,136},
                        {128,136,123,136,154,180,198,154},
                        {123,105,110,149,136,136,180,166},
                        {110,136,123,123,123,136,154,136},};

    double C1 = 0.4904, C2 = 0.4619, C3 = 0.4157,C4 = 0.3536,
           C5 = 0.2778, C6 = 0.1913, C7 = 0.0975;
    //Cn = 0.5cos(n(pi)/16) pi = 3.1415

    omp_set_num_threads(8);
    int id;
    double T[8][8] =  {{C4,C4,C4,C4,C4,C4,C4,C4,},
                      {C1,C3,C5,C7,-C7,-C5,-C3,-C1},
                      {C2,C6,-C6,-C2,-C2,-C6,C6,C2},
                      {C3,-C7,-C1,-C5,C5,C1,C7,-C3},
                      {C4,-C4,-C4,C4,C4,-C4,-C4,C4},
                      {C5,-C1,C7,C3,-C3,-C7,C1,-C5},
                      {C6,-C2,C3,-C6,-C6,C3,-C2,C6},
                      {C7,-C5,C2,-C1,C1,-C2,C5,-C7},};

    double RT[8][8] = {{C4,C1,C2,C3,C4,C5,C6,C7,},
                      {C4,C3,C6,-C7,-C4,-C1,-C2,-C5},
                      {C4,C5,-C6,-C1,-C4,C7,C3,C2},
                      {C4,C7,-C2,-C5,C4,C3,-C6,-C1},
                      {C4,-C7,-C2,C5,C4,-C3,-C6,C1},
                      {C4,-C5,-C6,C1,-C4,-C7,C3,-C2},
                      {C4,-C3,C6,C7,-C4,C1,-C2,C5},
                      {C4,-C1,C2,-C3,C4,-C5,C6,-C7}};

    int Q[8][8] =     {{16,11,10,16,24,40,51,61},
                      {12,12,14,19,26,58,60,55},
                      {14,13,16,24,40,57,69,56},
                      {14,17,22,29,51,87,80,62},
                      {18,22,37,56,68,109,103,77},
                      {24,35,55,64,81,104,113,92},
                      {49,64,78,87,103,121,120,101},
                      {72,92,95,98,112,100,103,99},};


    printf("Input data is Origin.\n\n");
    Begin = omp_get_wtime();
    for(i=0;i<8;i++)
    {
        for(j=0;j<8;j++)
        {
            printf("%d \t",Origin[i][j]);
        }
         printf("\n");
    }
    printf("-------------------------------------------------------------\n");

    #pragma omp parallel
    #pragma omp for

    for(i=0;i<8;i++)
    {   id = omp_get_thread_num();
        printf("Origin[i][j]-128, i=%d, Thread=%d\n",i,id);
        for(j=0;j<8;j++)
        {
            M[i][j] = Origin[i][j] - 128;                          //scaling made by X[i][j]-128
        }
    }
    printf("-------------------------------------------------------------\n");

    printf("Show M (Origin[i][j]-128)\n");
    printf("\n");

    for(i=0;i<8;i++)
    {
        for(j=0;j<8;j++)
        {
            printf("%d \t",M[i][j]);
        }
         printf("\n");
    }
    printf("-------------------------------------------------------------\n");

    #pragma omp parallel
    #pragma omp for
    for(i=0;i<8;i++)
    {
        id = omp_get_thread_num();
        printf("T*Origin, i=%d, Thread=%d\n",i,id);
        for(j=0;j<8;j++)
        {
            for(threads=0;threads<8;threads++)
            {
                DX[i][j] += T[i][threads] * M[threads][j];
            }
        }
    }
    printf("-------------------------------------------------------------\n");
    printf("Show T*Origin\n");
    printf("\n");
    for(i=0;i<8;i++)
    {
        for(j=0;j<8;j++)
        {
            printf("%.2f\t",DX[i][j]);
        }
         printf("\n");
    }
    printf("-------------------------------------------------------------\n");

    #pragma omp parallel
    #pragma omp for
    for(i=0;i<8;i++)
    {
        id = omp_get_thread_num();
        printf("D,i=%d, Thread=%d\n",i,id);
        for(j=0;j<8;j++)
        {
            for(threads=0;threads<8;threads++)
            {
                D[i][j] += DX[i][threads] * RT[threads][j] ;
            }
        }
    }
    printf("-------------------------------------------------------------\n");

    printf("Show D\n");
    printf("\n");
    for(i=0;i<8;i++)
    {
        for(j=0;j<8;j++)
        {
            printf("%.2f\t",D[i][j]);
        }
         printf("\n");
    }
    printf("-------------------------------------------------------------\n");

    #pragma omp parallel
    #pragma omp for
    for(i=0;i<8;i++)
    {
        id = omp_get_thread_num();
        printf("C,i=%d, Thread=%d\n",i,id);
        for(j=0;j<8;j++)
        {
            C[i][j] = round(D[i][j]/Q[i][j]);
        }
    }
    printf("-------------------------------------------------------------\n");

    printf("Show the answer \n");
    printf("\n");
    for(i=0;i<8;i++)
    {
        for(j=0;j<8;j++)
        {
            printf("%d \t",C[i][j]);
        }
         printf("\n");
    }
    printf("-------------------------------------------------------------\n");
    End = omp_get_wtime();
    printf("Time = %f s\n",End-Begin);

return 0;
}