GURLS_EXPORT void inv(const gMat2D<float>& A, gMat2D<float>& Ainv, InversionAlgorithm alg)
{
    Ainv = A;
    int k = std::min(Ainv.cols(), Ainv.rows());

    int info;
    int* ipiv = new int[k];

    int m = Ainv.rows();
    int n = Ainv.cols();
    int lda = Ainv.rows();

    sgetrf_(&m, &n, Ainv.getData(), &lda, ipiv, &info);

    float* work = new float[n];

    sgetri_(&m, Ainv.getData(), &lda, ipiv, work, &n, &info);

    delete[] ipiv;
    delete[] work;
}

GURLS_EXPORT void cholesky(const gMat2D<float>& A, gMat2D<float>& L, bool upper){

    typedef float T;
    L = A;

    int LDA = A.rows();
    int n = A.cols();
    char UPLO = upper? 'U' : 'L';
    int info;

    spotrf_(&UPLO,&n, L.getData(),&LDA,&info);

    // This is required because we adopted a column major order to store the
    // data into matrices
    gMat2D<T> tmp(L.rows(), L.cols());
    if (!upper){
        L.uppertriangular(tmp);
    } else {
        L.lowertriangular(tmp);
    }
    tmp.transpose(L);

}

    bool updateModule()
    {
        ++updateCount;
        
        if (updateCount > numPred)
        {
            cout << "Specified number of predictions reached. Shutting down the module." << endl;
            return false;
        }

        // DEBUG

        if(verbose) cout << "updateModule #" << updateCount << endl;


        // Recursive update support and storage variables declaration and initialization
        gMat2D<T> Xnew(1,d);
        gMat2D<T> ynew(1,t);
        gVec<T> Xnew_v(d);
        gVec<T> ynew_v(t);
        gMat2D<T> *resptr = 0;
        
        // Wait for input feature vector
        if(verbose) cout << "Expecting input vector" << endl;
        
        Bottle *bin = inVec.read();    // blocking call
        
        if (bin != 0)
        {
            if(verbose) cout << "Got it!" << endl << bin->toString() << endl;

            //Store the received sample in gMat2D format for it to be compatible with gurls++

            for (int i = 0 ; i < bin->size() ; ++i)
            {
                if ( i < d )
                {
                    Xnew(0,i) = bin->get(i).asDouble();
                }
                else if ( (i>=d) && (i<d+t) )
                {

                    ynew(0, i - d ) = bin->get(i).asDouble();
                }
            }
    
            if(verbose) cout << "Xnew: " << endl << Xnew << endl;
            if(verbose) cout << "ynew: " << endl << ynew.rows() << " x " << ynew.cols() << endl;
            if(verbose) cout<< ynew << endl;

            //-----------------------------------
            //          Prediction
            //-----------------------------------
            
            // Test on the incoming sample
            resptr = estimator.eval(Xnew);
            
            Bottle& bpred = pred.prepare(); // Get a place to store things.
            bpred.clear();  // clear is important - b might be a reused object

            for (int i = 0 ; i < t ; ++i)
            {
                bpred.addDouble((*resptr)(0 , i));
            }
            
            if(verbose) printf("Sending prediction!!! %s\n", bpred.toString().c_str());
            pred.write();
            if(verbose) printf("Prediction written to port\n");

            //----------------------------------
            // performance

            Bottle& bperf = perf.prepare(); // Get a place to store things.
            bperf.clear();  // clear is important - b might be a reused object
    
            if (perfType == "nMSE")     // WARNING: The estimated variance could be unreliable...
            {
                // Compute nMSE and store
                //NOTE: In GURLS, "/" operator works like matlab's "\".
                error += varCols / ( ynew - *resptr )*( ynew - *resptr ) ;   
                gMat2D<T> tmp = error  / (updateCount);   // WARNING: Check
                for (int i = 0 ; i < t ; ++i)
                {
                    bperf.addDouble(tmp(0 , i));
                }
            }
            else if (perfType == "RMSE")
            {
                gMat2D<T> tmp(1,t);
                tmp = ( ynew - *resptr )*( ynew - *resptr );
                
                //error = ( error * (updateCount-1) + sqrt(( ynew - *resptr )*( ynew - *resptr )) ) / updateCount;
                
                error = error * (updateCount-1);
                for (int i = 0 ; i < ynew.cols() ; ++i)
                    error(0,i) += sqrt(tmp(0,i));
                error = error / updateCount;
                
/*                for (int i = 0 ; i < t ; ++i)
                {
//.........这里部分代码省略.........

    bool configure(ResourceFinder &rf)
    {        
        string name=rf.find("name").asString().c_str();
        setName(name.c_str());
        
        // Set verbosity
        verbose = rf.check("verbose",Value(0)).asInt();
               
        // Set dimensionalities
        d = rf.check("d",Value(0)).asInt();
        t = rf.check("t",Value(0)).asInt();
        
        if (d <= 0 || t <= 0 )
        {
            printf("Error: Inconsistent feature or output dimensionalities!\n");
            return false;
        }
        
        // Set perf type WARNING: perf types should be defined as separate sister classes
        perfType = rf.check("perf",Value("RMSE")).asString();
        
        if ( perfType != "MSE" && perfType != "RMSE" && perfType != "nMSE" )
        {
            printf("Error: Inconsistent performance measure! Set to RMSE.\n");
            perfType = "RMSE";
        }
        
        // Set number of saved performance measurements
        numPred  = rf.check("numPred",Value("-1")).asInt();
        
        // Set number of saved performance measurements
        savedPerfNum = rf.check("savedPerfNum",Value("0")).asInt();
        if (savedPerfNum > numPred)
        {
            savedPerfNum = numPred;
            cout << "Warning: savedPerfNum > numPred, setting savedPerfNum = numPred" << endl;
        }
        
        //experimentCount = rf.check("experimentCount",Value("0")).asInt();
        experimentCount = rf.find("experimentCount").asInt();
        
        // Print Configuration
        cout << endl << "-------------------------" << endl;
        cout << "Configuration parameters:" << endl << endl;
        cout << "experimentCount = " << experimentCount << endl;
        cout << "d = " << d << endl;
        cout << "t = " << t << endl;
        cout << "perf = " << perfType << endl;
        cout << "-------------------------" << endl << endl;
       
        // Open ports
    
        string fwslash="/";
        inVec.open((fwslash+name+"/vec:i").c_str());
        printf("inVec opened\n");
        
        pred.open((fwslash+name+"/pred:o").c_str());
        printf("pred opened\n");
        
        perf.open((fwslash+name+"/perf:o").c_str());
        printf("perf opened\n");
        
        rpcPort.open((fwslash+name+"/rpc:i").c_str());
        printf("rpcPort opened\n");

        // Attach rpcPort to the respond() method
        attach(rpcPort);

        // Initialize random number generator
        srand(static_cast<unsigned int>(time(NULL)));

        // Initialize error structures
        error.resize(1,t);
        error = gMat2D<T>::zeros(1, t);          //
        
        if (savedPerfNum > 0)
        {
            storedError.resize(savedPerfNum,t);
            storedError = gMat2D<T>::zeros(savedPerfNum, t);          //MSE            
        }

        updateCount = 0;
        
        //------------------------------------------
        //         Pre-training
        //------------------------------------------

        if ( pretrain == 1 )
        {
            if ( pretr_type == "fromFile" )
            {
                //------------------------------------------
                //         Pre-training from file
                //------------------------------------------
                string trainFilePath = rf.getContextPath() + "/data/" + pretrainFile;
                
                try
                {
                    // Load data files
                    cout << "Loading data file..." << endl;
//.........这里部分代码省略.........

BigArray<T>::BigArray(std::string fileName, const gMat2D<T>& mat)
{
    init(fileName, mat.rows(), mat.cols());

    MPI_Barrier(MPI_COMM_WORLD);
}

void BigArray<T>::setMatrix(unsigned long startingRow, unsigned long startingCol, const gMat2D<T>&value)
{
    setMatrix(startingRow, startingCol, value.getData(), value.rows(), value.cols());
}

GURLS_EXPORT void cholesky(const gMat2D<float>& A, gMat2D<float>& L, bool upper)
{
    cholesky<float>(A.getData(), A.rows(), A.cols(), L.getData(), upper);
}

GURLS_EXPORT void lu(gMat2D<float>& A)
{
    gVec<int> pv(std::min(A.cols(), A.rows()));
    lu(A, pv);
}

GURLS_EXPORT void svd(const gMat2D<float>& A, gMat2D<float>& U, gVec<float>& W, gMat2D<float>& Vt) {

    char jobu = 'S', jobvt = 'S';
    int m = A.rows();
    int n = A.cols();
    int k = std::min<int>(m, n);

    if ((int)W.getSize() < k) {
        throw gException("The length of vector W must be at least equal to the minimum dimension of the input matrix A");
    }
    if ((int)U.rows() < m || (int)U.cols() < k) {
        throw gException("Please check the dimensions of the matrix U where to store the singular vectors");
    }
    if ((int)Vt.rows() < k || (int)Vt.cols() < n) {
        throw gException("Please check the dimensions of the matrix Vt where to store the rigth singular vectors");
    }

    int lda = A.cols();
    int ldu = U.cols();
    int ldvt = Vt.cols();
    int info, lwork = std::max<int>(3*k+std::max<int>(m,n), 5*k);
    float* work = new float[lwork];
    float* copy = new float[m*n];
    A.asarray(copy, m*n);
    sgesvd_(&jobu, &jobvt, &n, &m, copy, &lda, W.getData(), Vt.getData(), &ldvt, U.getData(), &ldu, work, &lwork, &info);
    delete[] work;
    delete[] copy;
}

GURLS_EXPORT void pinv(const gMat2D<float>& A, gMat2D<float>& Ainv, float RCOND){

    /*

subroutine SGELSS 	( 	INTEGER  	M,
  INTEGER  	N,
  INTEGER  	NRHS,
  REAL,dimension( lda, * )  	A,
  INTEGER  	LDA,
  REAL,dimension( ldb, * )  	B,
  INTEGER  	LDB,
  REAL,dimension( * )  	S,
  REAL  	RCOND,
  INTEGER  	RANK,
  REAL,dimension( * )  	WORK,
  INTEGER  	LWORK,
  INTEGER  	INFO
 )

*/

    int M = A.rows();
    int N = A.cols();

    // The following step is required because we are currently storing
    // the matrices using a column-major order while LAPACK's
    // routines require row-major ordering
    float* a = new float[M*N];
    const float* ptr_A = A.getData();
    float* ptr_a = a;
    for (int j = 0; j < N ; j++){
        for (int i = 0; i < M ; i++){
            *ptr_a++ = *(ptr_A+i*N+j);
        }
    }
    int LDA = M;
    int LDB = std::max(M, N);
    int NRHS = LDB;

    float *b = new float[LDB*NRHS], *b_ptr = b;
    for (int i = 0; i < LDB*NRHS; i++){
        *b_ptr++=0.f;
    }
    b_ptr = b;
    for (int i = 0; i < std::min(LDB, NRHS); i++, b_ptr+=(NRHS+1)){
        *b_ptr = 1.f;
    }

    float* S = new float[std::min(M,N)];
    float condnum = 0.f; // The condition number of A in the 2-norm = S(1)/S(min(m,n)).

    if (RCOND < 0){
        RCOND = 0.f;
    }
    int RANK = -1; // std::min(M,N);
    int LWORK = -1; //2 * (3*LDB + std::max( 2*std::min(M,N), LDB));
    float* WORK = new float[1];
    /*
   INFO:
   = 0:	successful exit
   < 0:	if INFO = -i, the i-th argument had an illegal value.
   > 0:	the algorithm for computing the SVD failed to converge;
     if INFO = i, i off-diagonal elements of an intermediate
     bidiagonal form did not converge to zero.
   */
    int INFO;

    /* Query and allocate the optimal workspace */
    /*int res = */sgelss_( &M, &N, &NRHS, a, &LDA, b, &LDB, S, &RCOND, &RANK, WORK, &LWORK, &INFO);
    LWORK = static_cast<int>(WORK[0]);
    delete [] WORK;
    WORK = new float[LWORK];

    /*res = */sgelss_( &M, &N, &NRHS, a, &LDA, b, &LDB, S, &RCOND, &RANK, WORK, &LWORK, &INFO);
    // TODO: check INFO on exit
    condnum = S[0]/(S[std::min(M, N)]-1);


//    gMat2D<float> *tmp = new gMat2D<float>(b, LDB, LDB, false);

    float *ainv = new float[N*M];
    float* ptr_b = ainv;
    float* ptr_B = b;
    for (int i = 0; i < N ; i++){
        for (int j = 0; j < M ; j++){
            *(ptr_b+i*M+j) = *(ptr_B+j*NRHS+i);
        }
    }
    Ainv = * new gMat2D<float>(ainv, N, M, true);

//	gMat2D<float> *tmp = new gMat2D<float>(b, LDB, NRHS, false);
//	gMat2D<float> *tmp1 = new gMat2D<float>(NRHS, LDB);
//	tmp->transpose(*tmp1);
//	Ainv = * new gMat2D<float>(tmp1->getData(), N, M, true);
//	std::cout << "A = " << std::endl << A << std::endl;
//	std::cout << "pinv(A) = " << std::endl << Ainv << std::endl;
    delete [] S;
    delete [] WORK;
    delete [] a;
//	delete tmp, tmp1;
//.........这里部分代码省略.........