void mini(vector<vector<double>> &M, size_t n, vector<double> &rowk, vector<double> &colk)
{
    size_t i, j;

    for ( i=0; i<n; i++)
        for ( j=0; j<n; j++)
            M[i][j]=min(rowk[j]+colk[i], M[i][j]);

}

$ time ./floyd

real    0m0,349s
user    0m0,349s
sys     0m0,000s

void mini(vector<vector<double>> &M, size_t n, vector<double> &rowk, vector<double> &colk)
{

    #pragma omp parallel
    {
        size_t i, j;

        #pragma omp parallel for
        for ( i=0; i<n; i++)
            for ( j=0; j<n; j++)
                M[i][j]=min(rowk[j]+colk[i], M[i][j]);
    }

}

$ grep -c ^processor /proc/cpuinfo
4
$ time ./floyd

real    0m0,547s
user    0m2,073s
sys     0m0,004s