dtzrzf.f

*> \brief \b DTZRZF
*
*  =========== DOCUMENTATION ===========
*
* Online html documentation available at
*            http://www.netlib.org/lapack/explore-html/
*
*> \htmlonly
*> Download DTZRZF + dependencies
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/dtzrzf.f">
*> [TGZ]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/dtzrzf.f">
*> [ZIP]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/dtzrzf.f">
*> [TXT]</a>
*> \endhtmlonly
*
*  Definition:
*  ===========
*
*       SUBROUTINE DTZRZF( M, N, A, LDA, TAU, WORK, LWORK, INFO )
*
*       .. Scalar Arguments ..
*       INTEGER            INFO, LDA, LWORK, M, N
*       ..
*       .. Array Arguments ..
*       DOUBLE PRECISION   A( LDA, * ), TAU( * ), WORK( * )
*       ..
*
*
*> \par Purpose:
*  =============
*>
*> \verbatim
*>
*> DTZRZF reduces the M-by-N ( M<=N ) real upper trapezoidal matrix A
*> to upper triangular form by means of orthogonal transformations.
*>
*> The upper trapezoidal matrix A is factored as
*>
*>    A = ( R  0 ) * Z,
*>
*> where Z is an N-by-N orthogonal matrix and R is an M-by-M upper
*> triangular matrix.
*> \endverbatim
*
*  Arguments:
*  ==========
*
*> \param[in] M
*> \verbatim
*>          M is INTEGER
*>          The number of rows of the matrix A.  M >= 0.
*> \endverbatim
*>
*> \param[in] N
*> \verbatim
*>          N is INTEGER
*>          The number of columns of the matrix A.  N >= M.
*> \endverbatim
*>
*> \param[in,out] A
*> \verbatim
*>          A is DOUBLE PRECISION array, dimension (LDA,N)
*>          On entry, the leading M-by-N upper trapezoidal part of the
*>          array A must contain the matrix to be factorized.
*>          On exit, the leading M-by-M upper triangular part of A
*>          contains the upper triangular matrix R, and elements M+1 to
*>          N of the first M rows of A, with the array TAU, represent the
*>          orthogonal matrix Z as a product of M elementary reflectors.
*> \endverbatim
*>
*> \param[in] LDA
*> \verbatim
*>          LDA is INTEGER
*>          The leading dimension of the array A.  LDA >= max(1,M).
*> \endverbatim
*>
*> \param[out] TAU
*> \verbatim
*>          TAU is DOUBLE PRECISION array, dimension (M)
*>          The scalar factors of the elementary reflectors.
*> \endverbatim
*>
*> \param[out] WORK
*> \verbatim
*>          WORK is DOUBLE PRECISION array, dimension (MAX(1,LWORK))
*>          On exit, if INFO = 0, WORK(1) returns the optimal LWORK.
*> \endverbatim
*>
*> \param[in] LWORK
*> \verbatim
*>          LWORK is INTEGER
*>          The dimension of the array WORK.  LWORK >= max(1,M).
*>          For optimum performance LWORK >= M*NB, where NB is
*>          the optimal blocksize.
*>
*>          If LWORK = -1, then a workspace query is assumed; the routine
*>          only calculates the optimal size of the WORK array, returns
*>          this value as the first entry of the WORK array, and no error
*>          message related to LWORK is issued by XERBLA.
*> \endverbatim
*>
*> \param[out] INFO
*> \verbatim
*>          INFO is INTEGER
*>          = 0:  successful exit
*>          < 0:  if INFO = -i, the i-th argument had an illegal value
*> \endverbatim
*
*  Authors:
*  ========
*
*> \author Univ. of Tennessee
*> \author Univ. of California Berkeley
*> \author Univ. of Colorado Denver
*> \author NAG Ltd.
*
*> \ingroup tzrzf
*
*> \par Contributors:
*  ==================
*>
*>    A. Petitet, Computer Science Dept., Univ. of Tenn., Knoxville, USA
*
*> \par Further Details:
*  =====================
*>
*> \verbatim
*>
*>  The N-by-N matrix Z can be computed by
*>
*>     Z =  Z(1)*Z(2)* ... *Z(M)
*>
*>  where each N-by-N Z(k) is given by
*>
*>     Z(k) = I - tau(k)*v(k)*v(k)**T
*>
*>  with v(k) is the kth row vector of the M-by-N matrix
*>
*>     V = ( I   A(:,M+1:N) )
*>
*>  I is the M-by-M identity matrix, A(:,M+1:N)
*>  is the output stored in A on exit from DTZRZF,
*>  and tau(k) is the kth element of the array TAU.
*>
*> \endverbatim
*>
*  =====================================================================
      SUBROUTINE dtzrzf( M, N, A, LDA, TAU, WORK, LWORK, INFO )
*
*  -- LAPACK computational routine --
*  -- LAPACK is a software package provided by Univ. of Tennessee,    --
*  -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..--
*
*     .. Scalar Arguments ..
      INTEGER            INFO, LDA, LWORK, M, N
*     ..
*     .. Array Arguments ..
      DOUBLE PRECISION   A( lda, * ), TAU( * ), WORK( * )
*     ..
*
*  =====================================================================
*
*     .. Parameters ..
      DOUBLE PRECISION   ZERO
      parameter( zero = 0.0d+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY
      INTEGER            I, IB, IWS, KI, KK, LDWORK, LWKMIN, LWKOPT,
     $                   m1, mu, nb, nbmin, nx
*     ..
*     .. External Subroutines ..
      EXTERNAL           xerbla, dlarzb, dlarzt, dlatrz
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          max, min
*     ..
*     .. External Functions ..
      INTEGER            ILAENV
      EXTERNAL           ilaenv
*     ..
*     .. Executable Statements ..
*
*     Test the input arguments
*
      info = 0
      lquery = ( lwork.EQ.-1 )
      IF( m.LT.0 ) THEN
         info = -1
      ELSE IF( n.LT.m ) THEN
         info = -2
      ELSE IF( lda.LT.max( 1, m ) ) THEN
         info = -4
      END IF
*
      IF( info.EQ.0 ) THEN
         IF( m.EQ.0 .OR. m.EQ.n ) THEN
            lwkopt = 1
            lwkmin = 1
         ELSE
*
*           Determine the block size.
*
            nb = ilaenv( 1, 'DGERQF', ' ', m, n, -1, -1 )
            lwkopt = m*nb
            lwkmin = max( 1, m )
         END IF
         work( 1 ) = lwkopt
*
         IF( lwork.LT.lwkmin .AND. .NOT.lquery ) THEN
            info = -7
         END IF
      END IF
*
      IF( info.NE.0 ) THEN
         CALL xerbla( 'DTZRZF', -info )
         RETURN
      ELSE IF( lquery ) THEN
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( m.EQ.0 ) THEN
         RETURN
      ELSE IF( m.EQ.n ) THEN
         DO 10 i = 1, n
            tau( i ) = zero
   10    CONTINUE
         RETURN
      END IF
*
      nbmin = 2
      nx = 1
      iws = m
      IF( nb.GT.1 .AND. nb.LT.m ) THEN
*
*        Determine when to cross over from blocked to unblocked code.
*
         nx = max( 0, ilaenv( 3, 'DGERQF', ' ', m, n, -1, -1 ) )
         IF( nx.LT.m ) THEN
*
*           Determine if workspace is large enough for blocked code.
*
            ldwork = m
            iws = ldwork*nb
            IF( lwork.LT.iws ) THEN
*
*              Not enough workspace to use optimal NB:  reduce NB and
*              determine the minimum value of NB.
*
               nb = lwork / ldwork
               nbmin = max( 2, ilaenv( 2, 'DGERQF', ' ', m, n, -1,
     $                 -1 ) )
            END IF
         END IF
      END IF
*
      IF( nb.GE.nbmin .AND. nb.LT.m .AND. nx.LT.m ) THEN
*
*        Use blocked code initially.
*        The last kk rows are handled by the block method.
*
         m1 = min( m+1, n )
         ki = ( ( m-nx-1 ) / nb )*nb
         kk = min( m, ki+nb )
*
         DO 20 i = m - kk + ki + 1, m - kk + 1, -nb
            ib = min( m-i+1, nb )
*
*           Compute the TZ factorization of the current block
*           A(i:i+ib-1,i:n)
*
            CALL dlatrz( ib, n-i+1, n-m, a( i, i ), lda, tau( i ),
     $                   work )
            IF( i.GT.1 ) THEN
*
*              Form the triangular factor of the block reflector
*              H = H(i+ib-1) . . . H(i+1) H(i)
*
               CALL dlarzt( 'Backward', 'Rowwise', n-m, ib, a( i, m1 ),
     $                      lda, tau( i ), work, ldwork )
*
*              Apply H to A(1:i-1,i:n) from the right
*
               CALL dlarzb( 'Right', 'No transpose', 'Backward',
     $                      'Rowwise', i-1, n-i+1, ib, n-m, a( i, m1 ),
     $                      lda, work, ldwork, a( 1, i ), lda,
     $                      work( ib+1 ), ldwork )
            END IF
   20    CONTINUE
         mu = i + nb - 1
      ELSE
         mu = m
      END IF
*
*     Use unblocked code to factor the last or only block
*
      IF( mu.GT.0 )
     $   CALL dlatrz( mu, n, n-m, a, lda, tau, work )
*
      work( 1 ) = lwkopt
*
      RETURN
*
*     End of DTZRZF
*
      END