dorgqr.f

Go to the documentation of this file.

      SUBROUTINE dorgqr( M, N, K, A, LDA, TAU, WORK, LWORK, INFO )
*
*  -- LAPACK routine (version 3.0) --
*     Univ. of Tennessee, Univ. of California Berkeley, NAG Ltd.,
*     Courant Institute, Argonne National Lab, and Rice University
*     June 30, 1999
*
*     .. Scalar Arguments ..
      INTEGER            INFO, K, LDA, LWORK, M, N
*     ..
*     .. Array Arguments ..
      DOUBLE PRECISION   A( LDA, * ), TAU( * ), WORK( * )
*     ..
*
*  Purpose
*  =======
*
*  DORGQR generates an M-by-N real matrix Q with orthonormal columns,
*  which is defined as the first N columns of a product of K elementary
*  reflectors of order M
*
*        Q  =  H(1) H(2) . . . H(k)
*
*  as returned by DGEQRF.
*
*  Arguments
*  =========
*
*  M       (input) INTEGER
*          The number of rows of the matrix Q. M >= 0.
*
*  N       (input) INTEGER
*          The number of columns of the matrix Q. M >= N >= 0.
*
*  K       (input) INTEGER
*          The number of elementary reflectors whose product defines the
*          matrix Q. N >= K >= 0.
*
*  A       (input/output) DOUBLE PRECISION array, dimension (LDA,N)
*          On entry, the i-th column must contain the vector which
*          defines the elementary reflector H(i), for i = 1,2,...,k, as
*          returned by DGEQRF in the first k columns of its array
*          argument A.
*          On exit, the M-by-N matrix Q.
*
*  LDA     (input) INTEGER
*          The first dimension of the array A. LDA >= max(1,M).
*
*  TAU     (input) DOUBLE PRECISION array, dimension (K)
*          TAU(i) must contain the scalar factor of the elementary
*          reflector H(i), as returned by DGEQRF.
*
*  WORK    (workspace/output) DOUBLE PRECISION array, dimension (LWORK)
*          On exit, if INFO = 0, WORK(1) returns the optimal LWORK.
*
*  LWORK   (input) INTEGER
*          The dimension of the array WORK. LWORK >= max(1,N).
*          For optimum performance LWORK >= N*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.
*
*  INFO    (output) INTEGER
*          = 0:  successful exit
*          < 0:  if INFO = -i, the i-th argument has an illegal value
*
*  =====================================================================
*
*     .. Parameters ..
      DOUBLE PRECISION   ZERO
      parameter( zero = 0.0d+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY
      INTEGER            I, IB, IINFO, IWS, J, KI, KK, L, LDWORK,
     $                   LWKOPT, NB, NBMIN, NX
*     ..
*     .. External Subroutines ..
      EXTERNAL           dlarfb, dlarft, dorg2r, xerbla
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          max, min
*     ..
*     .. External Functions ..
      INTEGER            ILAENV
      EXTERNAL           ilaenv
*     ..
*     .. Executable Statements ..
*
*     Test the input arguments
*
      info = 0
      nb = ilaenv( 1, 'DORGQR', ' ', m, n, k, -1 )
      lwkopt = max( 1, n )*nb
      work( 1 ) = lwkopt
      lquery = ( lwork.EQ.-1 )
      IF( m.LT.0 ) THEN
         info = -1
      ELSE IF( n.LT.0 .OR. n.GT.m ) THEN
         info = -2
      ELSE IF( k.LT.0 .OR. k.GT.n ) THEN
         info = -3
      ELSE IF( lda.LT.max( 1, m ) ) THEN
         info = -5
      ELSE IF( lwork.LT.max( 1, n ) .AND. .NOT.lquery ) THEN
         info = -8
      END IF
      IF( info.NE.0 ) THEN
         CALL xerbla( 'DORGQR', -info )
         RETURN
      ELSE IF( lquery ) THEN
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( n.LE.0 ) THEN
         work( 1 ) = 1
         RETURN
      END IF
*
      nbmin = 2
      nx = 0
      iws = n
      IF( nb.GT.1 .AND. nb.LT.k ) THEN
*
*        Determine when to cross over from blocked to unblocked code.
*
         nx = max( 0, ilaenv( 3, 'DORGQR', ' ', m, n, k, -1 ) )
         IF( nx.LT.k ) THEN
*
*           Determine if workspace is large enough for blocked code.
*
            ldwork = n
            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, 'DORGQR', ' ', m, n, k, -1 ) )
            END IF
         END IF
      END IF
*
      IF( nb.GE.nbmin .AND. nb.LT.k .AND. nx.LT.k ) THEN
*
*        Use blocked code after the last block.
*        The first kk columns are handled by the block method.
*
         ki = ( ( k-nx-1 ) / nb )*nb
         kk = min( k, ki+nb )
*
*        Set A(1:kk,kk+1:n) to zero.
*
         DO 20 j = kk + 1, n
            DO 10 i = 1, kk
               a( i, j ) = zero
   10       CONTINUE
   20    CONTINUE
      ELSE
         kk = 0
      END IF
*
*     Use unblocked code for the last or only block.
*
      IF( kk.LT.n )
     $   CALL dorg2r( m-kk, n-kk, k-kk, a( kk+1, kk+1 ), lda,
     $                tau( kk+1 ), work, iinfo )
*
      IF( kk.GT.0 ) THEN
*
*        Use blocked code
*
         DO 50 i = ki + 1, 1, -nb
            ib = min( nb, k-i+1 )
            IF( i+ib.LE.n ) THEN
*
*              Form the triangular factor of the block reflector
*              H = H(i) H(i+1) . . . H(i+ib-1)
*
               CALL dlarft( 'Forward', 'Columnwise', m-i+1, ib,
     $                      a( i, i ), lda, tau( i ), work, ldwork )
*
*              Apply H to A(i:m,i+ib:n) from the left
*
               CALL dlarfb( 'Left', 'No transpose', 'Forward',
     $                      'Columnwise', m-i+1, n-i-ib+1, ib,
     $                      a( i, i ), lda, work, ldwork, a( i, i+ib ),
     $                      lda, work( ib+1 ), ldwork )
            END IF
*
*           Apply H to rows i:m of current block
*
            CALL dorg2r( m-i+1, ib, ib, a( i, i ), lda, tau( i ), work,
     $                   iinfo )
*
*           Set rows 1:i-1 of current block to zero
*
            DO 40 j = i, i + ib - 1
               DO 30 l = 1, i - 1
                  a( l, j ) = zero
   30          CONTINUE
   40       CONTINUE
   50    CONTINUE
      END IF
*
      work( 1 ) = iws
      RETURN
*
*     End of DORGQR
*
      END