zlaunhr_col_getrfnp.f

*> \brief \b ZLAUNHR_COL_GETRFNP
*
*  =========== DOCUMENTATION ===========
*
* Online html documentation available at
*            http://www.netlib.org/lapack/explore-html/
*
*> \htmlonly
*> Download ZLAUNHR_COL_GETRFNP + dependencies
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/zlaunhr_col_getrfnp.f">
*> [TGZ]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/zlaunhr_col_getrfnp.f">
*> [ZIP]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/zlaunhr_col_getrfnp.f">
*> [TXT]</a>
*> \endhtmlonly
*
*  Definition:
*  ===========
*
*       SUBROUTINE ZLAUNHR_COL_GETRFNP( M, N, A, LDA, D, INFO )
*
*       .. Scalar Arguments ..
*       INTEGER            INFO, LDA, M, N
*       ..
*       .. Array Arguments ..
*       COMPLEX*16         A( LDA, * ), D( * )
*       ..
*
*
*> \par Purpose:
*  =============
*>
*> \verbatim
*>
*> ZLAUNHR_COL_GETRFNP computes the modified LU factorization without
*> pivoting of a complex general M-by-N matrix A. The factorization has
*> the form:
*>
*>     A - S = L * U,
*>
*> where:
*>    S is a m-by-n diagonal sign matrix with the diagonal D, so that
*>    D(i) = S(i,i), 1 <= i <= min(M,N). The diagonal D is constructed
*>    as D(i)=-SIGN(A(i,i)), where A(i,i) is the value after performing
*>    i-1 steps of Gaussian elimination. This means that the diagonal
*>    element at each step of "modified" Gaussian elimination is
*>    at least one in absolute value (so that division-by-zero not
*>    not possible during the division by the diagonal element);
*>
*>    L is a M-by-N lower triangular matrix with unit diagonal elements
*>    (lower trapezoidal if M > N);
*>
*>    and U is a M-by-N upper triangular matrix
*>    (upper trapezoidal if M < N).
*>
*> This routine is an auxiliary routine used in the Householder
*> reconstruction routine ZUNHR_COL. In ZUNHR_COL, this routine is
*> applied to an M-by-N matrix A with orthonormal columns, where each
*> element is bounded by one in absolute value. With the choice of
*> the matrix S above, one can show that the diagonal element at each
*> step of Gaussian elimination is the largest (in absolute value) in
*> the column on or below the diagonal, so that no pivoting is required
*> for numerical stability [1].
*>
*> For more details on the Householder reconstruction algorithm,
*> including the modified LU factorization, see [1].
*>
*> This is the blocked right-looking version of the algorithm,
*> calling Level 3 BLAS to update the submatrix. To factorize a block,
*> this routine calls the recursive routine ZLAUNHR_COL_GETRFNP2.
*>
*> [1] "Reconstructing Householder vectors from tall-skinny QR",
*>     G. Ballard, J. Demmel, L. Grigori, M. Jacquelin, H.D. Nguyen,
*>     E. Solomonik, J. Parallel Distrib. Comput.,
*>     vol. 85, pp. 3-31, 2015.
*> \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 >= 0.
*> \endverbatim
*>
*> \param[in,out] A
*> \verbatim
*>          A is COMPLEX*16 array, dimension (LDA,N)
*>          On entry, the M-by-N matrix to be factored.
*>          On exit, the factors L and U from the factorization
*>          A-S=L*U; the unit diagonal elements of L are not stored.
*> \endverbatim
*>
*> \param[in] LDA
*> \verbatim
*>          LDA is INTEGER
*>          The leading dimension of the array A.  LDA >= max(1,M).
*> \endverbatim
*>
*> \param[out] D
*> \verbatim
*>          D is COMPLEX*16 array, dimension min(M,N)
*>          The diagonal elements of the diagonal M-by-N sign matrix S,
*>          D(i) = S(i,i), where 1 <= i <= min(M,N). The elements can be
*>          only ( +1.0, 0.0 ) or (-1.0, 0.0 ).
*> \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 launhr_col_getrfnp
*
*> \par Contributors:
*  ==================
*>
*> \verbatim
*>
*> November 2019, Igor Kozachenko,
*>                Computer Science Division,
*>                University of California, Berkeley
*>
*> \endverbatim
*
*  =====================================================================
      SUBROUTINE zlaunhr_col_getrfnp( M, N, A, LDA, D, 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, M, N
*     ..
*     .. Array Arguments ..
      COMPLEX*16         A( lda, * ), D( * )
*     ..
*
*  =====================================================================
*
*     .. Parameters ..
      COMPLEX*16         CONE
      parameter( cone = ( 1.0d+0, 0.0d+0 ) )
*     ..
*     .. Local Scalars ..
      INTEGER            IINFO, J, JB, NB
*     ..
*     .. External Subroutines ..
      EXTERNAL           zgemm, zlaunhr_col_getrfnp2, ztrsm, xerbla
*     ..
*     .. External Functions ..
      INTEGER            ILAENV
      EXTERNAL           ilaenv
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          max, min
*     ..
*     .. Executable Statements ..
*
*     Test the input parameters.
*
      info = 0
      IF( m.LT.0 ) THEN
         info = -1
      ELSE IF( n.LT.0 ) THEN
         info = -2
      ELSE IF( lda.LT.max( 1, m ) ) THEN
         info = -4
      END IF
      IF( info.NE.0 ) THEN
         CALL xerbla( 'ZLAUNHR_COL_GETRFNP', -info )
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( min( m, n ).EQ.0 )
     $   RETURN
*
*     Determine the block size for this environment.
*

      nb = ilaenv( 1, 'ZLAUNHR_COL_GETRFNP', ' ', m, n, -1, -1 )

      IF( nb.LE.1 .OR. nb.GE.min( m, n ) ) THEN
*
*        Use unblocked code.
*
         CALL zlaunhr_col_getrfnp2( m, n, a, lda, d, info )
      ELSE
*
*        Use blocked code.
*
         DO j = 1, min( m, n ), nb
            jb = min( min( m, n )-j+1, nb )
*
*           Factor diagonal and subdiagonal blocks.
*
            CALL zlaunhr_col_getrfnp2( m-j+1, jb, a( j, j ), lda,
     $                                 d( j ), iinfo )
*
            IF( j+jb.LE.n ) THEN
*
*              Compute block row of U.
*
               CALL ztrsm( 'Left', 'Lower', 'No transpose', 'Unit', jb,
     $                     n-j-jb+1, cone, a( j, j ), lda, a( j, j+jb ),
     $                     lda )
               IF( j+jb.LE.m ) THEN
*
*                 Update trailing submatrix.
*
                  CALL zgemm( 'No transpose', 'No transpose', m-j-jb+1,
     $                        n-j-jb+1, jb, -cone, a( j+jb, j ), lda,
     $                        a( j, j+jb ), lda, cone, a( j+jb, j+jb ),
     $                        lda )
               END IF
            END IF
         END DO
      END IF
      RETURN
*
*     End of ZLAUNHR_COL_GETRFNP
*
      END