source: proiecte/PPPP/eigenface/new/jacobi.c @ 99

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

#define ROTATE(a,i,j,k,l) g=a[i][j];h=a[k][l];a[i][j]=g-s*(h+g*tau);\
a[k][l]=h+s*(g-h*tau);

/*
Computes all eigenvalues and eigenvectors of a real symmetric matrix a[1..n][1..n]. On
output, elements of a above the diagonal are destroyed. d[1..n] returns the eigenvalues of a.
v[1..n][1..n] is a matrix whose columns contain, on output, the normalized eigenvectors of
a. nrot returns the number of Jacobi rotations that were required.
*/
void jacobi(float **a, int n, float d[], float **v, int *nrot)
{
        int j,iq,ip,i;
        float tresh,theta,tau,sm,s,h,g,c,*b,*z;
        float t;        
        b = (float *) malloc(n * sizeof(float));
        z = (float *) malloc(n * sizeof(float));
        
        int nthreads, tid;

        /* Fork a team of threads giving them their own copies of variables */
        #pragma omp parallel private(nthreads, tid, i, j, ip, iq) shared(tresh, theta, tau, sm, s, h, g, c, b, z, a, n, d, v, nrot)
        {

        /* Obtain thread number */
        tid = omp_get_thread_num();
        printf("Hello World from thread = %d\n", tid);

        /* Only master thread does this */
        if (tid == 0) 
    {
        nthreads = omp_get_num_threads();
        printf("Number of threads = %d\n", nthreads);
    }


        #pragma omp parallel for
        for (ip=0;ip<n;ip++) {          // Initialize to the identity matrix.
                for (iq=0;iq<n;iq++) 
                        v[ip][iq]=0.0;
                v[ip][ip]=1.0;
        }
        
        #pragma omp parallel for
        for (ip=0;ip<n;ip++) {     // Initialize b and d to the diagonal of a.
                b[ip]=d[ip]=a[ip][ip];                                  
                z[ip]=0.0;                         // This vector will accumulate terms of the form t*a[pq] as in equation (11.1.14).
        }
        
        }  /* All threads join master thread and disband */
        
        *nrot=0;
        for (i=1;i<=50;i++) {

                sm = 0.0;

                for (ip=0;ip<n-1;ip++) {                        // Sum off-diagonal elements.
                        #pragma omp parallel for reduction(+:sm)
                        for (iq=ip+1;iq<n;iq++) {
                                sm += fabs(a[ip][iq]);
                        printf("Hello World from thread = %d\n", omp_get_thread_num());
                        }
                }
                if (sm == 0.0) {                                // The normal return, which relies on quadratic convergence to machine underflow.
                        free(z);
                        free(b);
                        return;
                }
                if (i < 4)
                        tresh=0.2*sm/(n*n);                             // ...on the first three sweeps.
                else
                        tresh=0.0;                                      // ...thereafter.
        
                for (ip=0;ip<n-1;ip++) {
                        for (iq=ip+1;iq<n;iq++) {
                                g=100.0*fabs(a[ip][iq]);
                                if (i > 4 && (float)(fabs(d[ip])+g) == (float)fabs(d[ip])       // After four sweeps, skip the rotation if the off-diagonal element is small.
                                        && (float)(fabs(d[iq])+g) == (float)fabs(d[iq]))
                                        a[ip][iq]=0.0;
                                else if (fabs(a[ip][iq]) > tresh) {
                                        h=d[iq]-d[ip];
                                        if ((float)(fabs(h)+g) == (float)fabs(h))
                                                t=(a[ip][iq])/h;        // t = 1/(2*theta)
                                        else {
                                                theta=0.5*h/(a[ip][iq]); 
                                                t=1.0/(fabs(theta)+sqrt(1.0+theta*theta));
                                                if (theta < 0.0) t = -t;
                                        }
                                        
                                        c=1.0/sqrt(1+t*t);
                                        s=t*c;
                                        tau=s/(1.0+c);
                                        h=t*a[ip][iq];
                                        z[ip] -= h;
                                        z[iq] += h;
                                        d[ip] -= h;
                                        d[iq] += h;
                                        a[ip][iq]=0.0;
                                
                                        #pragma omp parallel for
                                        for (j=0;j<=ip-1;j++) { // Case of rotations 1 <= j < p.
                                                ROTATE(a,j,ip,j,iq)
                                        } 
                                        #pragma omp parallel for
                                        for (j=ip+1;j<=iq-1;j++) { // Case of rotations p < j < q.
                                                ROTATE(a,ip,j,j,iq)
                                        }
                                        #pragma omp parallel for
                                        for (j=iq+1;j<n;j++) {  // Case of rotations q < j <= n.
                                                ROTATE(a,ip,j,iq,j)
                                        }
                                        #pragma omp parallel for
                                        for (j=0;j<n;j++) {
                                                ROTATE(v,j,ip,j,iq)
                                        }
                                        
                                        ++(*nrot);
                                }
                        }
                }
                
                #pragma omp parallel for
                for (ip=0;ip<n;ip++) {
                        b[ip] += z[ip];
                        d[ip]=b[ip];            // Update d with the sum of t*a[pq],
                        z[ip]=0.0;                      // and reinitialize z.
                }
        }
        
        printf("Too many iterations in routine jacobi\n");
}

int main(int argc, char * argv[])
{
        int n, i, j;
        float *d;
        float **a;
        float **v;
        int nrot = 0;

        char * filename = argv[1];      
        FILE * f = fopen(filename, "r");
        fscanf(f,"%d", &n);
        
        a = (float **)malloc(n * sizeof(float*));
        for(i = 0; i < n; i++)
                a[i] = (float *)malloc(n * sizeof(float));
        
        v  = (float **)malloc(n * sizeof(float*));
        for(i = 0; i < n; i++)
                v[i] = (float *)malloc(n * sizeof(float));
        
        d = (float *)malloc(n * sizeof(float));
        
        for(i = 0; i < n; i++)
                for(j = 0; j < n; j++)
                        fscanf(f,"%f", &a[i][j]);
        for(i = 0; i < n; i++)
        {
                for(j = 0; j < n; j++)
                        printf("%f ", a[i][j]);
                printf("\n");
        }
        
        jacobi(a, n, d, v, &nrot); 
        
        printf("v:\n");
        for(i = 0; i < n; i++)
        {
                for(j = 0; j < n; j++)
                        printf("%f ", v[i][j]);
                printf("\n");
        }

        printf("d:\n");
        for(i = 0; i < n; i++)
        {
                printf("%f ", d[i]);
        }
        printf("\n");

        return 0;
}