dlaqr2.f

famous linear algebra library (LAPACK) ports to windows

      SUBROUTINE DLAQR2( WANTT, WANTZ, N, KTOP, KBOT, NW, H, LDH, ILOZ,
     $                   IHIZ, Z, LDZ, NS, ND, SR, SI, V, LDV, NH, T,
     $                   LDT, NV, WV, LDWV, WORK, LWORK )
*
*  -- LAPACK auxiliary routine (version 3.1) --
*     Univ. of Tennessee, Univ. of California Berkeley and NAG Ltd..
*     November 2006
*
*     .. Scalar Arguments ..
      INTEGER            IHIZ, ILOZ, KBOT, KTOP, LDH, LDT, LDV, LDWV,
     $                   LDZ, LWORK, N, ND, NH, NS, NV, NW
      LOGICAL            WANTT, WANTZ
*     ..
*     .. Array Arguments ..
      DOUBLE PRECISION   H( LDH, * ), SI( * ), SR( * ), T( LDT, * ),
     $                   V( LDV, * ), WORK( * ), WV( LDWV, * ),
     $                   Z( LDZ, * )
*     ..
*
*     This subroutine is identical to DLAQR3 except that it avoids
*     recursion by calling DLAHQR instead of DLAQR4.
*
*
*     ******************************************************************
*     Aggressive early deflation:
*
*     This subroutine accepts as input an upper Hessenberg matrix
*     H and performs an orthogonal similarity transformation
*     designed to detect and deflate fully converged eigenvalues from
*     a trailing principal submatrix.  On output H has been over-
*     written by a new Hessenberg matrix that is a perturbation of
*     an orthogonal similarity transformation of H.  It is to be
*     hoped that the final version of H has many zero subdiagonal
*     entries.
*
*     ******************************************************************
*     WANTT   (input) LOGICAL
*          If .TRUE., then the Hessenberg matrix H is fully updated
*          so that the quasi-triangular Schur factor may be
*          computed (in cooperation with the calling subroutine).
*          If .FALSE., then only enough of H is updated to preserve
*          the eigenvalues.
*
*     WANTZ   (input) LOGICAL
*          If .TRUE., then the orthogonal matrix Z is updated so
*          so that the orthogonal Schur factor may be computed
*          (in cooperation with the calling subroutine).
*          If .FALSE., then Z is not referenced.
*
*     N       (input) INTEGER
*          The order of the matrix H and (if WANTZ is .TRUE.) the
*          order of the orthogonal matrix Z.
*
*     KTOP    (input) INTEGER
*          It is assumed that either KTOP = 1 or H(KTOP,KTOP-1)=0.
*          KBOT and KTOP together determine an isolated block
*          along the diagonal of the Hessenberg matrix.
*
*     KBOT    (input) INTEGER
*          It is assumed without a check that either
*          KBOT = N or H(KBOT+1,KBOT)=0.  KBOT and KTOP together
*          determine an isolated block along the diagonal of the
*          Hessenberg matrix.
*
*     NW      (input) INTEGER
*          Deflation window size.  1 .LE. NW .LE. (KBOT-KTOP+1).
*
*     H       (input/output) DOUBLE PRECISION array, dimension (LDH,N)
*          On input the initial N-by-N section of H stores the
*          Hessenberg matrix undergoing aggressive early deflation.
*          On output H has been transformed by an orthogonal
*          similarity transformation, perturbed, and the returned
*          to Hessenberg form that (it is to be hoped) has some
*          zero subdiagonal entries.
*
*     LDH     (input) integer
*          Leading dimension of H just as declared in the calling
*          subroutine.  N .LE. LDH
*
*     ILOZ    (input) INTEGER
*     IHIZ    (input) INTEGER
*          Specify the rows of Z to which transformations must be
*          applied if WANTZ is .TRUE.. 1 .LE. ILOZ .LE. IHIZ .LE. N.
*
*     Z       (input/output) DOUBLE PRECISION array, dimension (LDZ,IHI)
*          IF WANTZ is .TRUE., then on output, the orthogonal
*          similarity transformation mentioned above has been
*          accumulated into Z(ILOZ:IHIZ,ILO:IHI) from the right.
*          If WANTZ is .FALSE., then Z is unreferenced.
*
*     LDZ     (input) integer
*          The leading dimension of Z just as declared in the
*          calling subroutine.  1 .LE. LDZ.
*
*     NS      (output) integer
*          The number of unconverged (ie approximate) eigenvalues
*          returned in SR and SI that may be used as shifts by the
*          calling subroutine.
*
*     ND      (output) integer
*          The number of converged eigenvalues uncovered by this
*          subroutine.
*
*     SR      (output) DOUBLE PRECISION array, dimension KBOT
*     SI      (output) DOUBLE PRECISION array, dimension KBOT
*          On output, the real and imaginary parts of approximate
*          eigenvalues that may be used for shifts are stored in
*          SR(KBOT-ND-NS+1) through SR(KBOT-ND) and
*          SI(KBOT-ND-NS+1) through SI(KBOT-ND), respectively.
*          The real and imaginary parts of converged eigenvalues
*          are stored in SR(KBOT-ND+1) through SR(KBOT) and
*          SI(KBOT-ND+1) through SI(KBOT), respectively.
*
*     V       (workspace) DOUBLE PRECISION array, dimension (LDV,NW)
*          An NW-by-NW work array.
*
*     LDV     (input) integer scalar
*          The leading dimension of V just as declared in the
*          calling subroutine.  NW .LE. LDV
*
*     NH      (input) integer scalar
*          The number of columns of T.  NH.GE.NW.
*
*     T       (workspace) DOUBLE PRECISION array, dimension (LDT,NW)
*
*     LDT     (input) integer
*          The leading dimension of T just as declared in the
*          calling subroutine.  NW .LE. LDT
*
*     NV      (input) integer
*          The number of rows of work array WV available for
*          workspace.  NV.GE.NW.
*
*     WV      (workspace) DOUBLE PRECISION array, dimension (LDWV,NW)
*
*     LDWV    (input) integer
*          The leading dimension of W just as declared in the
*          calling subroutine.  NW .LE. LDV
*
*     WORK    (workspace) DOUBLE PRECISION array, dimension LWORK.
*          On exit, WORK(1) is set to an estimate of the optimal value
*          of LWORK for the given values of N, NW, KTOP and KBOT.
*
*     LWORK   (input) integer
*          The dimension of the work array WORK.  LWORK = 2*NW
*          suffices, but greater efficiency may result from larger
*          values of LWORK.
*
*          If LWORK = -1, then a workspace query is assumed; DLAQR2
*          only estimates the optimal workspace size for the given
*          values of N, NW, KTOP and KBOT.  The estimate is returned
*          in WORK(1).  No error message related to LWORK is issued
*          by XERBLA.  Neither H nor Z are accessed.
*
*     ================================================================
*     Based on contributions by
*        Karen Braman and Ralph Byers, Department of Mathematics,
*        University of Kansas, USA
*
*     ================================================================
*     .. Parameters ..
      DOUBLE PRECISION   ZERO, ONE
      PARAMETER          ( ZERO = 0.0d0, ONE = 1.0d0 )
*     ..
*     .. Local Scalars ..
      DOUBLE PRECISION   AA, BB, BETA, CC, CS, DD, EVI, EVK, FOO, S,
     $                   SAFMAX, SAFMIN, SMLNUM, SN, TAU, ULP
      INTEGER            I, IFST, ILST, INFO, INFQR, J, JW, K, KCOL,
     $                   KEND, KLN, KROW, KWTOP, LTOP, LWK1, LWK2,
     $                   LWKOPT
      LOGICAL            BULGE, SORTED
*     ..
*     .. External Functions ..
      DOUBLE PRECISION   DLAMCH
      EXTERNAL           DLAMCH
*     ..
*     .. External Subroutines ..
      EXTERNAL           DCOPY, DGEHRD, DGEMM, DLABAD, DLACPY, DLAHQR,
     $                   DLANV2, DLARF, DLARFG, DLASET, DORGHR, DTREXC
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          ABS, DBLE, INT, MAX, MIN, SQRT
*     ..
*     .. Executable Statements ..
*
*     ==== Estimate optimal workspace. ====
*
      JW = MIN( NW, KBOT-KTOP+1 )
      IF( JW.LE.2 ) THEN
         LWKOPT = 1
      ELSE
*
*        ==== Workspace query call to DGEHRD ====
*
         CALL DGEHRD( JW, 1, JW-1, T, LDT, WORK, WORK, -1, INFO )
         LWK1 = INT( WORK( 1 ) )
*
*        ==== Workspace query call to DORGHR ====
*
         CALL DORGHR( JW, 1, JW-1, T, LDT, WORK, WORK, -1, INFO )
         LWK2 = INT( WORK( 1 ) )
*
*        ==== Optimal workspace ====
*
         LWKOPT = JW + MAX( LWK1, LWK2 )
      END IF
*
*     ==== Quick return in case of workspace query. ====
*
      IF( LWORK.EQ.-1 ) THEN
         WORK( 1 ) = DBLE( LWKOPT )
         RETURN
      END IF
*
*     ==== Nothing to do ...
*     ... for an empty active block ... ====
      NS = 0
      ND = 0
      IF( KTOP.GT.KBOT )
     $   RETURN
*     ... nor for an empty deflation window. ====
      IF( NW.LT.1 )
     $   RETURN
*
*     ==== Machine constants ====
*
      SAFMIN = DLAMCH( 'SAFE MINIMUM' )
      SAFMAX = ONE / SAFMIN
      CALL DLABAD( SAFMIN, SAFMAX )
      ULP = DLAMCH( 'PRECISION' )
      SMLNUM = SAFMIN*( DBLE( N ) / ULP )
*
*     ==== Setup deflation window ====
*
      JW = MIN( NW, KBOT-KTOP+1 )
      KWTOP = KBOT - JW + 1
      IF( KWTOP.EQ.KTOP ) THEN
         S = ZERO
      ELSE
         S = H( KWTOP, KWTOP-1 )
      END IF
*
      IF( KBOT.EQ.KWTOP ) THEN
*
*        ==== 1-by-1 deflation window: not much to do ====
*
         SR( KWTOP ) = H( KWTOP, KWTOP )
         SI( KWTOP ) = ZERO
         NS = 1
         ND = 0
         IF( ABS( S ).LE.MAX( SMLNUM, ULP*ABS( H( KWTOP, KWTOP ) ) ) )
     $        THEN
            NS = 0
            ND = 1
            IF( KWTOP.GT.KTOP )
     $         H( KWTOP, KWTOP-1 ) = ZERO
         END IF
         RETURN
      END IF
*
*     ==== Convert to spike-triangular form.  (In case of a
*     .    rare QR failure, this routine continues to do
*     .    aggressive early deflation using that part of
*     .    the deflation window that converged using INFQR
*     .    here and there to keep track.) ====
*
      CALL DLACPY( 'U', JW, JW, H( KWTOP, KWTOP ), LDH, T, LDT )
      CALL DCOPY( JW-1, H( KWTOP+1, KWTOP ), LDH+1, T( 2, 1 ), LDT+1 )
*
      CALL DLASET( 'A', JW, JW, ZERO, ONE, V, LDV )
      CALL DLAHQR( .true., .true., JW, 1, JW, T, LDT, SR( KWTOP ),
     $             SI( KWTOP ), 1, JW, V, LDV, INFQR )
*
*     ==== DTREXC needs a clean margin near the diagonal ====
*
      DO 10 J = 1, JW - 3