cungtsqr.f

*> \brief \b CUNGTSQR
*
*  =========== DOCUMENTATION ===========
*
* Online html documentation available at
*            http://www.netlib.org/lapack/explore-html/
*
*> \htmlonly
*> Download CUNGTSQR + dependencies
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/cuntsqr.f">
*> [TGZ]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/cungtsqr.f">
*> [ZIP]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/cungtsqr.f">
*> [TXT]</a>
*> \endhtmlonly
*>
*  Definition:
*  ===========
*
*       SUBROUTINE CUNGTSQR( M, N, MB, NB, A, LDA, T, LDT, WORK, LWORK,
*      $                     INFO )
*
*       .. Scalar Arguments ..
*       INTEGER           INFO, LDA, LDT, LWORK, M, N, MB, NB
*       ..
*       .. Array Arguments ..
*       COMPLEX           A( LDA, * ), T( LDT, * ), WORK( * )
*       ..
*
*> \par Purpose:
*  =============
*>
*> \verbatim
*>
*> CUNGTSQR generates an M-by-N complex matrix Q_out with orthonormal
*> columns, which are the first N columns of a product of comlpex unitary
*> matrices of order M which are returned by CLATSQR
*>
*>      Q_out = first_N_columns_of( Q(1)_in * Q(2)_in * ... * Q(k)_in ).
*>
*> See the documentation for CLATSQR.
*> \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. M >= N >= 0.
*> \endverbatim
*>
*> \param[in] MB
*> \verbatim
*>          MB is INTEGER
*>          The row block size used by CLATSQR to return
*>          arrays A and T. MB > N.
*>          (Note that if MB > M, then M is used instead of MB
*>          as the row block size).
*> \endverbatim
*>
*> \param[in] NB
*> \verbatim
*>          NB is INTEGER
*>          The column block size used by CLATSQR to return
*>          arrays A and T. NB >= 1.
*>          (Note that if NB > N, then N is used instead of NB
*>          as the column block size).
*> \endverbatim
*>
*> \param[in,out] A
*> \verbatim
*>          A is COMPLEX array, dimension (LDA,N)
*>
*>          On entry:
*>
*>             The elements on and above the diagonal are not accessed.
*>             The elements below the diagonal represent the unit
*>             lower-trapezoidal blocked matrix V computed by CLATSQR
*>             that defines the input matrices Q_in(k) (ones on the
*>             diagonal are not stored) (same format as the output A
*>             below the diagonal in CLATSQR).
*>
*>          On exit:
*>
*>             The array A contains an M-by-N orthonormal matrix Q_out,
*>             i.e the columns of A are orthogonal unit vectors.
*> \endverbatim
*>
*> \param[in] LDA
*> \verbatim
*>          LDA is INTEGER
*>          The leading dimension of the array A.  LDA >= max(1,M).
*> \endverbatim
*>
*> \param[in] T
*> \verbatim
*>          T is COMPLEX array,
*>          dimension (LDT, N * NIRB)
*>          where NIRB = Number_of_input_row_blocks
*>                     = MAX( 1, CEIL((M-N)/(MB-N)) )
*>          Let NICB = Number_of_input_col_blocks
*>                   = CEIL(N/NB)
*>
*>          The upper-triangular block reflectors used to define the
*>          input matrices Q_in(k), k=(1:NIRB*NICB). The block
*>          reflectors are stored in compact form in NIRB block
*>          reflector sequences. Each of NIRB block reflector sequences
*>          is stored in a larger NB-by-N column block of T and consists
*>          of NICB smaller NB-by-NB upper-triangular column blocks.
*>          (same format as the output T in CLATSQR).
*> \endverbatim
*>
*> \param[in] LDT
*> \verbatim
*>          LDT is INTEGER
*>          The leading dimension of the array T.
*>          LDT >= max(1,min(NB1,N)).
*> \endverbatim
*>
*> \param[out] WORK
*> \verbatim
*>          (workspace) COMPLEX array, dimension (MAX(2,LWORK))
*>          On exit, if INFO = 0, WORK(1) returns the optimal LWORK.
*> \endverbatim
*>
*> \param[in] LWORK
*> \verbatim
*>          The dimension of the array WORK.  LWORK >= (M+NB)*N.
*>          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 ungtsqr
*
*> \par Contributors:
*  ==================
*>
*> \verbatim
*>
*> November 2019, Igor Kozachenko,
*>                Computer Science Division,
*>                University of California, Berkeley
*>
*> \endverbatim
*
*  =====================================================================
      SUBROUTINE cungtsqr( M, N, MB, NB, A, LDA, T, LDT, WORK, LWORK,
     $                     INFO )
      IMPLICIT NONE
*
*  -- 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, LDT, LWORK, M, N, MB, NB
*     ..
*     .. Array Arguments ..
      COMPLEX        A( lda, * ), T( ldt, * ), WORK( * )
*     ..
*
*  =====================================================================
*
*     .. Parameters ..
      COMPLEX            CONE, CZERO
      parameter( cone = ( 1.0e+0, 0.0e+0 ),
     $                     czero = ( 0.0e+0, 0.0e+0 ) )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY
      INTEGER            IINFO, LDC, LWORKOPT, LC, LW, NBLOCAL, J
*     ..
*     .. External Subroutines ..
      EXTERNAL           ccopy, clamtsqr, claset, xerbla
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          cmplx, max, min
*     ..
*     .. Executable Statements ..
*
*     Test the input parameters
*
      lquery  = lwork.EQ.-1
      info = 0
      IF( m.LT.0 ) THEN
         info = -1
      ELSE IF( n.LT.0 .OR. m.LT.n ) THEN
         info = -2
      ELSE IF( mb.LE.n ) THEN
         info = -3
      ELSE IF( nb.LT.1 ) THEN
         info = -4
      ELSE IF( lda.LT.max( 1, m ) ) THEN
         info = -6
      ELSE IF( ldt.LT.max( 1, min( nb, n ) ) ) THEN
         info = -8
      ELSE
*
*        Test the input LWORK for the dimension of the array WORK.
*        This workspace is used to store array C(LDC, N) and WORK(LWORK)
*        in the call to CLAMTSQR. See the documentation for CLAMTSQR.
*
         IF( lwork.LT.2 .AND. (.NOT.lquery) ) THEN
            info = -10
         ELSE
*
*           Set block size for column blocks
*
            nblocal = min( nb, n )
*
*           LWORK = -1, then set the size for the array C(LDC,N)
*           in CLAMTSQR call and set the optimal size of the work array
*           WORK(LWORK) in CLAMTSQR call.
*
            ldc = m
            lc = ldc*n
            lw = n * nblocal
*
            lworkopt = lc+lw
*
            IF( ( lwork.LT.max( 1, lworkopt ) ).AND.(.NOT.lquery) ) THEN
               info = -10
            END IF
         END IF
*
      END IF
*
*     Handle error in the input parameters and return workspace query.
*
      IF( info.NE.0 ) THEN
         CALL xerbla( 'CUNGTSQR', -info )
         RETURN
      ELSE IF ( lquery ) THEN
         work( 1 ) = cmplx( lworkopt )
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( min( m, n ).EQ.0 ) THEN
         work( 1 ) = cmplx( lworkopt )
         RETURN
      END IF
*
*     (1) Form explicitly the tall-skinny M-by-N left submatrix Q1_in
*     of M-by-M orthogonal matrix Q_in, which is implicitly stored in
*     the subdiagonal part of input array A and in the input array T.
*     Perform by the following operation using the routine CLAMTSQR.
*
*         Q1_in = Q_in * ( I ), where I is a N-by-N identity matrix,
*                        ( 0 )        0 is a (M-N)-by-N zero matrix.
*
*     (1a) Form M-by-N matrix in the array WORK(1:LDC*N) with ones
*     on the diagonal and zeros elsewhere.
*
      CALL claset( 'F', m, n, czero, cone, work, ldc )
*
*     (1b)  On input, WORK(1:LDC*N) stores ( I );
*                                          ( 0 )
*
*           On output, WORK(1:LDC*N) stores Q1_in.
*
      CALL clamtsqr( 'L', 'N', m, n, n, mb, nblocal, a, lda, t, ldt,
     $               work, ldc, work( lc+1 ), lw, iinfo )
*
*     (2) Copy the result from the part of the work array (1:M,1:N)
*     with the leading dimension LDC that starts at WORK(1) into
*     the output array A(1:M,1:N) column-by-column.
*
      DO j = 1, n
         CALL ccopy( m, work( (j-1)*ldc + 1 ), 1, a( 1, j ), 1 )
      END DO
*
      work( 1 ) = cmplx( lworkopt )
      RETURN
*
*     End of CUNGTSQR
*
      END