1*> \brief <b> CGESVJ </b>
2*
3*  =========== DOCUMENTATION ===========
4*
5* Online html documentation available at
6*            http://www.netlib.org/lapack/explore-html/
7*
8*> \htmlonly
9*> Download CGESVJ + dependencies
10*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/cgesvj.f">
11*> [TGZ]</a>
12*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/cgesvj.f">
13*> [ZIP]</a>
14*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/cgesvj.f">
15*> [TXT]</a>
16*> \endhtmlonly
17*
18*  Definition:
19*  ===========
20*
21*       SUBROUTINE CGESVJ( JOBA, JOBU, JOBV, M, N, A, LDA, SVA, MV, V,
22*                          LDV, CWORK, LWORK, RWORK, LRWORK, INFO )
23*
24*       .. Scalar Arguments ..
25*       INTEGER            INFO, LDA, LDV, LWORK, LRWORK, M, MV, N
26*       CHARACTER*1        JOBA, JOBU, JOBV
27*       ..
28*       .. Array Arguments ..
29*       COMPLEX            A( LDA, * ),  V( LDV, * ), CWORK( LWORK )
30*       REAL               RWORK( LRWORK ),  SVA( N )
31*       ..
32*
33*
34*> \par Purpose:
35*  =============
36*>
37*> \verbatim
38*>
39*> CGESVJ computes the singular value decomposition (SVD) of a complex
40*> M-by-N matrix A, where M >= N. The SVD of A is written as
41*>                                    [++]   [xx]   [x0]   [xx]
42*>              A = U * SIGMA * V^*,  [++] = [xx] * [ox] * [xx]
43*>                                    [++]   [xx]
44*> where SIGMA is an N-by-N diagonal matrix, U is an M-by-N orthonormal
45*> matrix, and V is an N-by-N unitary matrix. The diagonal elements
46*> of SIGMA are the singular values of A. The columns of U and V are the
47*> left and the right singular vectors of A, respectively.
48*> \endverbatim
49*
50*  Arguments:
51*  ==========
52*
53*> \param[in] JOBA
54*> \verbatim
55*>          JOBA is CHARACTER*1
56*>          Specifies the structure of A.
57*>          = 'L': The input matrix A is lower triangular;
58*>          = 'U': The input matrix A is upper triangular;
59*>          = 'G': The input matrix A is general M-by-N matrix, M >= N.
60*> \endverbatim
61*>
62*> \param[in] JOBU
63*> \verbatim
64*>          JOBU is CHARACTER*1
65*>          Specifies whether to compute the left singular vectors
66*>          (columns of U):
67*>          = 'U' or 'F': The left singular vectors corresponding to the nonzero
68*>                 singular values are computed and returned in the leading
69*>                 columns of A. See more details in the description of A.
70*>                 The default numerical orthogonality threshold is set to
71*>                 approximately TOL=CTOL*EPS, CTOL=SQRT(M), EPS=SLAMCH('E').
72*>          = 'C': Analogous to JOBU='U', except that user can control the
73*>                 level of numerical orthogonality of the computed left
74*>                 singular vectors. TOL can be set to TOL = CTOL*EPS, where
75*>                 CTOL is given on input in the array WORK.
76*>                 No CTOL smaller than ONE is allowed. CTOL greater
77*>                 than 1 / EPS is meaningless. The option 'C'
78*>                 can be used if M*EPS is satisfactory orthogonality
79*>                 of the computed left singular vectors, so CTOL=M could
80*>                 save few sweeps of Jacobi rotations.
81*>                 See the descriptions of A and WORK(1).
82*>          = 'N': The matrix U is not computed. However, see the
83*>                 description of A.
84*> \endverbatim
85*>
86*> \param[in] JOBV
87*> \verbatim
88*>          JOBV is CHARACTER*1
89*>          Specifies whether to compute the right singular vectors, that
90*>          is, the matrix V:
91*>          = 'V' or 'J': the matrix V is computed and returned in the array V
92*>          = 'A':  the Jacobi rotations are applied to the MV-by-N
93*>                  array V. In other words, the right singular vector
94*>                  matrix V is not computed explicitly; instead it is
95*>                  applied to an MV-by-N matrix initially stored in the
96*>                  first MV rows of V.
97*>          = 'N':  the matrix V is not computed and the array V is not
98*>                  referenced
99*> \endverbatim
100*>
101*> \param[in] M
102*> \verbatim
103*>          M is INTEGER
104*>          The number of rows of the input matrix A. 1/SLAMCH('E') > M >= 0.
105*> \endverbatim
106*>
107*> \param[in] N
108*> \verbatim
109*>          N is INTEGER
110*>          The number of columns of the input matrix A.
111*>          M >= N >= 0.
112*> \endverbatim
113*>
114*> \param[in,out] A
115*> \verbatim
116*>          A is COMPLEX array, dimension (LDA,N)
117*>          On entry, the M-by-N matrix A.
118*>          On exit,
119*>          If JOBU = 'U' .OR. JOBU = 'C':
120*>                 If INFO = 0 :
121*>                 RANKA orthonormal columns of U are returned in the
122*>                 leading RANKA columns of the array A. Here RANKA <= N
123*>                 is the number of computed singular values of A that are
124*>                 above the underflow threshold SLAMCH('S'). The singular
125*>                 vectors corresponding to underflowed or zero singular
126*>                 values are not computed. The value of RANKA is returned
127*>                 in the array RWORK as RANKA=NINT(RWORK(2)). Also see the
128*>                 descriptions of SVA and RWORK. The computed columns of U
129*>                 are mutually numerically orthogonal up to approximately
130*>                 TOL=SQRT(M)*EPS (default); or TOL=CTOL*EPS (JOBU = 'C'),
131*>                 see the description of JOBU.
132*>                 If INFO > 0,
133*>                 the procedure CGESVJ did not converge in the given number
134*>                 of iterations (sweeps). In that case, the computed
135*>                 columns of U may not be orthogonal up to TOL. The output
136*>                 U (stored in A), SIGMA (given by the computed singular
137*>                 values in SVA(1:N)) and V is still a decomposition of the
138*>                 input matrix A in the sense that the residual
139*>                 || A - SCALE * U * SIGMA * V^* ||_2 / ||A||_2 is small.
140*>          If JOBU = 'N':
141*>                 If INFO = 0 :
142*>                 Note that the left singular vectors are 'for free' in the
143*>                 one-sided Jacobi SVD algorithm. However, if only the
144*>                 singular values are needed, the level of numerical
145*>                 orthogonality of U is not an issue and iterations are
146*>                 stopped when the columns of the iterated matrix are
147*>                 numerically orthogonal up to approximately M*EPS. Thus,
148*>                 on exit, A contains the columns of U scaled with the
149*>                 corresponding singular values.
150*>                 If INFO > 0 :
151*>                 the procedure CGESVJ did not converge in the given number
152*>                 of iterations (sweeps).
153*> \endverbatim
154*>
155*> \param[in] LDA
156*> \verbatim
157*>          LDA is INTEGER
158*>          The leading dimension of the array A.  LDA >= max(1,M).
159*> \endverbatim
160*>
161*> \param[out] SVA
162*> \verbatim
163*>          SVA is REAL array, dimension (N)
164*>          On exit,
165*>          If INFO = 0 :
166*>          depending on the value SCALE = RWORK(1), we have:
167*>                 If SCALE = ONE:
168*>                 SVA(1:N) contains the computed singular values of A.
169*>                 During the computation SVA contains the Euclidean column
170*>                 norms of the iterated matrices in the array A.
171*>                 If SCALE .NE. ONE:
172*>                 The singular values of A are SCALE*SVA(1:N), and this
173*>                 factored representation is due to the fact that some of the
174*>                 singular values of A might underflow or overflow.
175*>
176*>          If INFO > 0 :
177*>          the procedure CGESVJ did not converge in the given number of
178*>          iterations (sweeps) and SCALE*SVA(1:N) may not be accurate.
179*> \endverbatim
180*>
181*> \param[in] MV
182*> \verbatim
183*>          MV is INTEGER
184*>          If JOBV = 'A', then the product of Jacobi rotations in CGESVJ
185*>          is applied to the first MV rows of V. See the description of JOBV.
186*> \endverbatim
187*>
188*> \param[in,out] V
189*> \verbatim
190*>          V is COMPLEX array, dimension (LDV,N)
191*>          If JOBV = 'V', then V contains on exit the N-by-N matrix of
192*>                         the right singular vectors;
193*>          If JOBV = 'A', then V contains the product of the computed right
194*>                         singular vector matrix and the initial matrix in
195*>                         the array V.
196*>          If JOBV = 'N', then V is not referenced.
197*> \endverbatim
198*>
199*> \param[in] LDV
200*> \verbatim
201*>          LDV is INTEGER
202*>          The leading dimension of the array V, LDV >= 1.
203*>          If JOBV = 'V', then LDV >= max(1,N).
204*>          If JOBV = 'A', then LDV >= max(1,MV) .
205*> \endverbatim
206*>
207*> \param[in,out] CWORK
208*> \verbatim
209*>          CWORK is COMPLEX array, dimension (max(1,LWORK))
210*>          Used as workspace.
211*>          If on entry LWORK = -1, then a workspace query is assumed and
212*>          no computation is done; CWORK(1) is set to the minial (and optimal)
213*>          length of CWORK.
214*> \endverbatim
215*>
216*> \param[in] LWORK
217*> \verbatim
218*>          LWORK is INTEGER.
219*>          Length of CWORK, LWORK >= M+N.
220*> \endverbatim
221*>
222*> \param[in,out] RWORK
223*> \verbatim
224*>          RWORK is REAL array, dimension (max(6,LRWORK))
225*>          On entry,
226*>          If JOBU = 'C' :
227*>          RWORK(1) = CTOL, where CTOL defines the threshold for convergence.
228*>                    The process stops if all columns of A are mutually
229*>                    orthogonal up to CTOL*EPS, EPS=SLAMCH('E').
230*>                    It is required that CTOL >= ONE, i.e. it is not
231*>                    allowed to force the routine to obtain orthogonality
232*>                    below EPSILON.
233*>          On exit,
234*>          RWORK(1) = SCALE is the scaling factor such that SCALE*SVA(1:N)
235*>                    are the computed singular values of A.
236*>                    (See description of SVA().)
237*>          RWORK(2) = NINT(RWORK(2)) is the number of the computed nonzero
238*>                    singular values.
239*>          RWORK(3) = NINT(RWORK(3)) is the number of the computed singular
240*>                    values that are larger than the underflow threshold.
241*>          RWORK(4) = NINT(RWORK(4)) is the number of sweeps of Jacobi
242*>                    rotations needed for numerical convergence.
243*>          RWORK(5) = max_{i.NE.j} |COS(A(:,i),A(:,j))| in the last sweep.
244*>                    This is useful information in cases when CGESVJ did
245*>                    not converge, as it can be used to estimate whether
246*>                    the output is still useful and for post festum analysis.
247*>          RWORK(6) = the largest absolute value over all sines of the
248*>                    Jacobi rotation angles in the last sweep. It can be
249*>                    useful for a post festum analysis.
250*>         If on entry LRWORK = -1, then a workspace query is assumed and
251*>         no computation is done; RWORK(1) is set to the minial (and optimal)
252*>         length of RWORK.
253*> \endverbatim
254*>
255*> \param[in] LRWORK
256*> \verbatim
257*>         LRWORK is INTEGER
258*>         Length of RWORK, LRWORK >= MAX(6,N).
259*> \endverbatim
260*>
261*> \param[out] INFO
262*> \verbatim
263*>          INFO is INTEGER
264*>          = 0:  successful exit.
265*>          < 0:  if INFO = -i, then the i-th argument had an illegal value
266*>          > 0:  CGESVJ did not converge in the maximal allowed number
267*>                (NSWEEP=30) of sweeps. The output may still be useful.
268*>                See the description of RWORK.
269*> \endverbatim
270*>
271*  Authors:
272*  ========
273*
274*> \author Univ. of Tennessee
275*> \author Univ. of California Berkeley
276*> \author Univ. of Colorado Denver
277*> \author NAG Ltd.
278*
279*> \ingroup complexGEcomputational
280*
281*> \par Further Details:
282*  =====================
283*>
284*> \verbatim
285*>
286*> The orthogonal N-by-N matrix V is obtained as a product of Jacobi plane
287*> rotations. In the case of underflow of the tangent of the Jacobi angle, a
288*> modified Jacobi transformation of Drmac [3] is used. Pivot strategy uses
289*> column interchanges of de Rijk [1]. The relative accuracy of the computed
290*> singular values and the accuracy of the computed singular vectors (in
291*> angle metric) is as guaranteed by the theory of Demmel and Veselic [2].
292*> The condition number that determines the accuracy in the full rank case
293*> is essentially min_{D=diag} kappa(A*D), where kappa(.) is the
294*> spectral condition number. The best performance of this Jacobi SVD
295*> procedure is achieved if used in an  accelerated version of Drmac and
296*> Veselic [4,5], and it is the kernel routine in the SIGMA library [6].
297*> Some tuning parameters (marked with [TP]) are available for the
298*> implementer.
299*> The computational range for the nonzero singular values is the  machine
300*> number interval ( UNDERFLOW , OVERFLOW ). In extreme cases, even
301*> denormalized singular values can be computed with the corresponding
302*> gradual loss of accurate digits.
303*> \endverbatim
304*
305*> \par Contributor:
306*  ==================
307*>
308*> \verbatim
309*>
310*>  ============
311*>
312*>  Zlatko Drmac (Zagreb, Croatia)
313*>
314*> \endverbatim
315*
316*> \par References:
317*  ================
318*>
319*> \verbatim
320*>
321*> [1] P. P. M. De Rijk: A one-sided Jacobi algorithm for computing the
322*>    singular value decomposition on a vector computer.
323*>    SIAM J. Sci. Stat. Comp., Vol. 10 (1998), pp. 359-371.
324*> [2] J. Demmel and K. Veselic: Jacobi method is more accurate than QR.
325*> [3] Z. Drmac: Implementation of Jacobi rotations for accurate singular
326*>    value computation in floating point arithmetic.
327*>    SIAM J. Sci. Comp., Vol. 18 (1997), pp. 1200-1222.
328*> [4] Z. Drmac and K. Veselic: New fast and accurate Jacobi SVD algorithm I.
329*>    SIAM J. Matrix Anal. Appl. Vol. 35, No. 2 (2008), pp. 1322-1342.
330*>    LAPACK Working note 169.
331*> [5] Z. Drmac and K. Veselic: New fast and accurate Jacobi SVD algorithm II.
332*>    SIAM J. Matrix Anal. Appl. Vol. 35, No. 2 (2008), pp. 1343-1362.
333*>    LAPACK Working note 170.
334*> [6] Z. Drmac: SIGMA - mathematical software library for accurate SVD, PSV,
335*>    QSVD, (H,K)-SVD computations.
336*>    Department of Mathematics, University of Zagreb, 2008, 2015.
337*> \endverbatim
338*
339*> \par Bugs, examples and comments:
340*  =================================
341*>
342*> \verbatim
343*>  ===========================
344*>  Please report all bugs and send interesting test examples and comments to
345*>  drmac@math.hr. Thank you.
346*> \endverbatim
347*>
348*  =====================================================================
349      SUBROUTINE CGESVJ( JOBA, JOBU, JOBV, M, N, A, LDA, SVA, MV, V,
350     $                   LDV, CWORK, LWORK, RWORK, LRWORK, INFO )
351*
352*  -- LAPACK computational routine --
353*  -- LAPACK is a software package provided by Univ. of Tennessee,    --
354*  -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..--
355*
356      IMPLICIT NONE
357*     .. Scalar Arguments ..
358      INTEGER            INFO, LDA, LDV, LWORK, LRWORK, M, MV, N
359      CHARACTER*1        JOBA, JOBU, JOBV
360*     ..
361*     .. Array Arguments ..
362      COMPLEX            A( LDA, * ),  V( LDV, * ), CWORK( LWORK )
363      REAL               RWORK( LRWORK ), SVA( N )
364*     ..
365*
366*  =====================================================================
367*
368*     .. Local Parameters ..
369      REAL         ZERO,         HALF,         ONE
370      PARAMETER  ( ZERO = 0.0E0, HALF = 0.5E0, ONE = 1.0E0)
371      COMPLEX      CZERO,                  CONE
372      PARAMETER  ( CZERO = (0.0E0, 0.0E0), CONE = (1.0E0, 0.0E0) )
373      INTEGER      NSWEEP
374      PARAMETER  ( NSWEEP = 30 )
375*     ..
376*     .. Local Scalars ..
377      COMPLEX AAPQ, OMPQ
378      REAL    AAPP, AAPP0, AAPQ1, AAQQ, APOAQ, AQOAP, BIG,
379     $        BIGTHETA, CS, CTOL, EPSLN, MXAAPQ,
380     $        MXSINJ, ROOTBIG, ROOTEPS, ROOTSFMIN, ROOTTOL,
381     $        SKL, SFMIN, SMALL, SN, T, TEMP1, THETA, THSIGN, TOL
382      INTEGER BLSKIP, EMPTSW, i, ibr, IERR, igl, IJBLSK, ir1,
383     $        ISWROT, jbc, jgl, KBL, LKAHEAD, MVL, N2, N34,
384     $        N4, NBL, NOTROT, p, PSKIPPED, q, ROWSKIP, SWBAND
385      LOGICAL APPLV, GOSCALE, LOWER, LQUERY, LSVEC, NOSCALE, ROTOK,
386     $        RSVEC, UCTOL, UPPER
387*     ..
388*     ..
389*     .. Intrinsic Functions ..
390      INTRINSIC ABS, MAX, MIN, CONJG, REAL, SIGN, SQRT
391*     ..
392*     .. External Functions ..
393*     ..
394*     from BLAS
395      REAL               SCNRM2
396      COMPLEX            CDOTC
397      EXTERNAL           CDOTC, SCNRM2
398      INTEGER            ISAMAX
399      EXTERNAL           ISAMAX
400*     from LAPACK
401      REAL               SLAMCH
402      EXTERNAL           SLAMCH
403      LOGICAL            LSAME
404      EXTERNAL           LSAME
405*     ..
406*     .. External Subroutines ..
407*     ..
408*     from BLAS
409      EXTERNAL           CCOPY, CROT, CSSCAL, CSWAP, CAXPY
410*     from LAPACK
411      EXTERNAL           CLASCL, CLASET, CLASSQ, SLASCL, XERBLA
412      EXTERNAL           CGSVJ0, CGSVJ1
413*     ..
414*     .. Executable Statements ..
415*
416*     Test the input arguments
417*
418      LSVEC = LSAME( JOBU, 'U' ) .OR. LSAME( JOBU, 'F' )
419      UCTOL = LSAME( JOBU, 'C' )
420      RSVEC = LSAME( JOBV, 'V' ) .OR. LSAME( JOBV, 'J' )
421      APPLV = LSAME( JOBV, 'A' )
422      UPPER = LSAME( JOBA, 'U' )
423      LOWER = LSAME( JOBA, 'L' )
424*
425      LQUERY = ( LWORK .EQ. -1 ) .OR. ( LRWORK .EQ. -1 )
426      IF( .NOT.( UPPER .OR. LOWER .OR. LSAME( JOBA, 'G' ) ) ) THEN
427         INFO = -1
428      ELSE IF( .NOT.( LSVEC .OR. UCTOL .OR. LSAME( JOBU, 'N' ) ) ) THEN
429         INFO = -2
430      ELSE IF( .NOT.( RSVEC .OR. APPLV .OR. LSAME( JOBV, 'N' ) ) ) THEN
431         INFO = -3
432      ELSE IF( M.LT.0 ) THEN
433         INFO = -4
434      ELSE IF( ( N.LT.0 ) .OR. ( N.GT.M ) ) THEN
435         INFO = -5
436      ELSE IF( LDA.LT.M ) THEN
437         INFO = -7
438      ELSE IF( MV.LT.0 ) THEN
439         INFO = -9
440      ELSE IF( ( RSVEC .AND. ( LDV.LT.N ) ) .OR.
441     $          ( APPLV .AND. ( LDV.LT.MV ) ) ) THEN
442         INFO = -11
443      ELSE IF( UCTOL .AND. ( RWORK( 1 ).LE.ONE ) ) THEN
444         INFO = -12
445      ELSE IF( LWORK.LT.( M+N ) .AND. ( .NOT.LQUERY ) ) THEN
446         INFO = -13
447      ELSE IF( LRWORK.LT.MAX( N, 6 ) .AND. ( .NOT.LQUERY ) ) THEN
448         INFO = -15
449      ELSE
450         INFO = 0
451      END IF
452*
453*     #:(
454      IF( INFO.NE.0 ) THEN
455         CALL XERBLA( 'CGESVJ', -INFO )
456         RETURN
457      ELSE IF ( LQUERY ) THEN
458         CWORK(1) = M + N
459         RWORK(1) = MAX( N, 6 )
460         RETURN
461      END IF
462*
463* #:) Quick return for void matrix
464*
465      IF( ( M.EQ.0 ) .OR. ( N.EQ.0 ) )RETURN
466*
467*     Set numerical parameters
468*     The stopping criterion for Jacobi rotations is
469*
470*     max_{i<>j}|A(:,i)^* * A(:,j)| / (||A(:,i)||*||A(:,j)||) < CTOL*EPS
471*
472*     where EPS is the round-off and CTOL is defined as follows:
473*
474      IF( UCTOL ) THEN
475*        ... user controlled
476         CTOL = RWORK( 1 )
477      ELSE
478*        ... default
479         IF( LSVEC .OR. RSVEC .OR. APPLV ) THEN
480            CTOL = SQRT( REAL( M ) )
481         ELSE
482            CTOL = REAL( M )
483         END IF
484      END IF
485*     ... and the machine dependent parameters are
486*[!]  (Make sure that SLAMCH() works properly on the target machine.)
487*
488      EPSLN = SLAMCH( 'Epsilon' )
489      ROOTEPS = SQRT( EPSLN )
490      SFMIN = SLAMCH( 'SafeMinimum' )
491      ROOTSFMIN = SQRT( SFMIN )
492      SMALL = SFMIN / EPSLN
493*      BIG = SLAMCH( 'Overflow' )
494      BIG     = ONE  / SFMIN
495      ROOTBIG = ONE / ROOTSFMIN
496*     LARGE = BIG / SQRT( REAL( M*N ) )
497      BIGTHETA = ONE / ROOTEPS
498*
499      TOL = CTOL*EPSLN
500      ROOTTOL = SQRT( TOL )
501*
502      IF( REAL( M )*EPSLN.GE.ONE ) THEN
503         INFO = -4
504         CALL XERBLA( 'CGESVJ', -INFO )
505         RETURN
506      END IF
507*
508*     Initialize the right singular vector matrix.
509*
510      IF( RSVEC ) THEN
511         MVL = N
512         CALL CLASET( 'A', MVL, N, CZERO, CONE, V, LDV )
513      ELSE IF( APPLV ) THEN
514         MVL = MV
515      END IF
516      RSVEC = RSVEC .OR. APPLV
517*
518*     Initialize SVA( 1:N ) = ( ||A e_i||_2, i = 1:N )
519*(!)  If necessary, scale A to protect the largest singular value
520*     from overflow. It is possible that saving the largest singular
521*     value destroys the information about the small ones.
522*     This initial scaling is almost minimal in the sense that the
523*     goal is to make sure that no column norm overflows, and that
524*     SQRT(N)*max_i SVA(i) does not overflow. If INFinite entries
525*     in A are detected, the procedure returns with INFO=-6.
526*
527      SKL = ONE / SQRT( REAL( M )*REAL( N ) )
528      NOSCALE = .TRUE.
529      GOSCALE = .TRUE.
530*
531      IF( LOWER ) THEN
532*        the input matrix is M-by-N lower triangular (trapezoidal)
533         DO 1874 p = 1, N
534            AAPP = ZERO
535            AAQQ = ONE
536            CALL CLASSQ( M-p+1, A( p, p ), 1, AAPP, AAQQ )
537            IF( AAPP.GT.BIG ) THEN
538               INFO = -6
539               CALL XERBLA( 'CGESVJ', -INFO )
540               RETURN
541            END IF
542            AAQQ = SQRT( AAQQ )
543            IF( ( AAPP.LT.( BIG / AAQQ ) ) .AND. NOSCALE ) THEN
544               SVA( p ) = AAPP*AAQQ
545            ELSE
546               NOSCALE = .FALSE.
547               SVA( p ) = AAPP*( AAQQ*SKL )
548               IF( GOSCALE ) THEN
549                  GOSCALE = .FALSE.
550                  DO 1873 q = 1, p - 1
551                     SVA( q ) = SVA( q )*SKL
552 1873             CONTINUE
553               END IF
554            END IF
555 1874    CONTINUE
556      ELSE IF( UPPER ) THEN
557*        the input matrix is M-by-N upper triangular (trapezoidal)
558         DO 2874 p = 1, N
559            AAPP = ZERO
560            AAQQ = ONE
561            CALL CLASSQ( p, A( 1, p ), 1, AAPP, AAQQ )
562            IF( AAPP.GT.BIG ) THEN
563               INFO = -6
564               CALL XERBLA( 'CGESVJ', -INFO )
565               RETURN
566            END IF
567            AAQQ = SQRT( AAQQ )
568            IF( ( AAPP.LT.( BIG / AAQQ ) ) .AND. NOSCALE ) THEN
569               SVA( p ) = AAPP*AAQQ
570            ELSE
571               NOSCALE = .FALSE.
572               SVA( p ) = AAPP*( AAQQ*SKL )
573               IF( GOSCALE ) THEN
574                  GOSCALE = .FALSE.
575                  DO 2873 q = 1, p - 1
576                     SVA( q ) = SVA( q )*SKL
577 2873             CONTINUE
578               END IF
579            END IF
580 2874    CONTINUE
581      ELSE
582*        the input matrix is M-by-N general dense
583         DO 3874 p = 1, N
584            AAPP = ZERO
585            AAQQ = ONE
586            CALL CLASSQ( M, A( 1, p ), 1, AAPP, AAQQ )
587            IF( AAPP.GT.BIG ) THEN
588               INFO = -6
589               CALL XERBLA( 'CGESVJ', -INFO )
590               RETURN
591            END IF
592            AAQQ = SQRT( AAQQ )
593            IF( ( AAPP.LT.( BIG / AAQQ ) ) .AND. NOSCALE ) THEN
594               SVA( p ) = AAPP*AAQQ
595            ELSE
596               NOSCALE = .FALSE.
597               SVA( p ) = AAPP*( AAQQ*SKL )
598               IF( GOSCALE ) THEN
599                  GOSCALE = .FALSE.
600                  DO 3873 q = 1, p - 1
601                     SVA( q ) = SVA( q )*SKL
602 3873             CONTINUE
603               END IF
604            END IF
605 3874    CONTINUE
606      END IF
607*
608      IF( NOSCALE )SKL = ONE
609*
610*     Move the smaller part of the spectrum from the underflow threshold
611*(!)  Start by determining the position of the nonzero entries of the
612*     array SVA() relative to ( SFMIN, BIG ).
613*
614      AAPP = ZERO
615      AAQQ = BIG
616      DO 4781 p = 1, N
617         IF( SVA( p ).NE.ZERO )AAQQ = MIN( AAQQ, SVA( p ) )
618         AAPP = MAX( AAPP, SVA( p ) )
619 4781 CONTINUE
620*
621* #:) Quick return for zero matrix
622*
623      IF( AAPP.EQ.ZERO ) THEN
624         IF( LSVEC )CALL CLASET( 'G', M, N, CZERO, CONE, A, LDA )
625         RWORK( 1 ) = ONE
626         RWORK( 2 ) = ZERO
627         RWORK( 3 ) = ZERO
628         RWORK( 4 ) = ZERO
629         RWORK( 5 ) = ZERO
630         RWORK( 6 ) = ZERO
631         RETURN
632      END IF
633*
634* #:) Quick return for one-column matrix
635*
636      IF( N.EQ.1 ) THEN
637         IF( LSVEC )CALL CLASCL( 'G', 0, 0, SVA( 1 ), SKL, M, 1,
638     $                           A( 1, 1 ), LDA, IERR )
639         RWORK( 1 ) = ONE / SKL
640         IF( SVA( 1 ).GE.SFMIN ) THEN
641            RWORK( 2 ) = ONE
642         ELSE
643            RWORK( 2 ) = ZERO
644         END IF
645         RWORK( 3 ) = ZERO
646         RWORK( 4 ) = ZERO
647         RWORK( 5 ) = ZERO
648         RWORK( 6 ) = ZERO
649         RETURN
650      END IF
651*
652*     Protect small singular values from underflow, and try to
653*     avoid underflows/overflows in computing Jacobi rotations.
654*
655      SN = SQRT( SFMIN / EPSLN )
656      TEMP1 = SQRT( BIG / REAL( N ) )
657      IF( ( AAPP.LE.SN ) .OR. ( AAQQ.GE.TEMP1 ) .OR.
658     $    ( ( SN.LE.AAQQ ) .AND. ( AAPP.LE.TEMP1 ) ) ) THEN
659         TEMP1 = MIN( BIG, TEMP1 / AAPP )
660*         AAQQ  = AAQQ*TEMP1
661*         AAPP  = AAPP*TEMP1
662      ELSE IF( ( AAQQ.LE.SN ) .AND. ( AAPP.LE.TEMP1 ) ) THEN
663         TEMP1 = MIN( SN / AAQQ, BIG / ( AAPP*SQRT( REAL( N ) ) ) )
664*         AAQQ  = AAQQ*TEMP1
665*         AAPP  = AAPP*TEMP1
666      ELSE IF( ( AAQQ.GE.SN ) .AND. ( AAPP.GE.TEMP1 ) ) THEN
667         TEMP1 = MAX( SN / AAQQ, TEMP1 / AAPP )
668*         AAQQ  = AAQQ*TEMP1
669*         AAPP  = AAPP*TEMP1
670      ELSE IF( ( AAQQ.LE.SN ) .AND. ( AAPP.GE.TEMP1 ) ) THEN
671         TEMP1 = MIN( SN / AAQQ, BIG / ( SQRT( REAL( N ) )*AAPP ) )
672*         AAQQ  = AAQQ*TEMP1
673*         AAPP  = AAPP*TEMP1
674      ELSE
675         TEMP1 = ONE
676      END IF
677*
678*     Scale, if necessary
679*
680      IF( TEMP1.NE.ONE ) THEN
681         CALL SLASCL( 'G', 0, 0, ONE, TEMP1, N, 1, SVA, N, IERR )
682      END IF
683      SKL = TEMP1*SKL
684      IF( SKL.NE.ONE ) THEN
685         CALL CLASCL( JOBA, 0, 0, ONE, SKL, M, N, A, LDA, IERR )
686         SKL = ONE / SKL
687      END IF
688*
689*     Row-cyclic Jacobi SVD algorithm with column pivoting
690*
691      EMPTSW = ( N*( N-1 ) ) / 2
692      NOTROT = 0
693
694      DO 1868 q = 1, N
695         CWORK( q ) = CONE
696 1868 CONTINUE
697*
698*
699*
700      SWBAND = 3
701*[TP] SWBAND is a tuning parameter [TP]. It is meaningful and effective
702*     if CGESVJ is used as a computational routine in the preconditioned
703*     Jacobi SVD algorithm CGEJSV. For sweeps i=1:SWBAND the procedure
704*     works on pivots inside a band-like region around the diagonal.
705*     The boundaries are determined dynamically, based on the number of
706*     pivots above a threshold.
707*
708      KBL = MIN( 8, N )
709*[TP] KBL is a tuning parameter that defines the tile size in the
710*     tiling of the p-q loops of pivot pairs. In general, an optimal
711*     value of KBL depends on the matrix dimensions and on the
712*     parameters of the computer's memory.
713*
714      NBL = N / KBL
715      IF( ( NBL*KBL ).NE.N )NBL = NBL + 1
716*
717      BLSKIP = KBL**2
718*[TP] BLKSKIP is a tuning parameter that depends on SWBAND and KBL.
719*
720      ROWSKIP = MIN( 5, KBL )
721*[TP] ROWSKIP is a tuning parameter.
722*
723      LKAHEAD = 1
724*[TP] LKAHEAD is a tuning parameter.
725*
726*     Quasi block transformations, using the lower (upper) triangular
727*     structure of the input matrix. The quasi-block-cycling usually
728*     invokes cubic convergence. Big part of this cycle is done inside
729*     canonical subspaces of dimensions less than M.
730*
731      IF( ( LOWER .OR. UPPER ) .AND. ( N.GT.MAX( 64, 4*KBL ) ) ) THEN
732*[TP] The number of partition levels and the actual partition are
733*     tuning parameters.
734         N4 = N / 4
735         N2 = N / 2
736         N34 = 3*N4
737         IF( APPLV ) THEN
738            q = 0
739         ELSE
740            q = 1
741         END IF
742*
743         IF( LOWER ) THEN
744*
745*     This works very well on lower triangular matrices, in particular
746*     in the framework of the preconditioned Jacobi SVD (xGEJSV).
747*     The idea is simple:
748*     [+ 0 0 0]   Note that Jacobi transformations of [0 0]
749*     [+ + 0 0]                                       [0 0]
750*     [+ + x 0]   actually work on [x 0]              [x 0]
751*     [+ + x x]                    [x x].             [x x]
752*
753            CALL CGSVJ0( JOBV, M-N34, N-N34, A( N34+1, N34+1 ), LDA,
754     $                   CWORK( N34+1 ), SVA( N34+1 ), MVL,
755     $                   V( N34*q+1, N34+1 ), LDV, EPSLN, SFMIN, TOL,
756     $                   2, CWORK( N+1 ), LWORK-N, IERR )
757
758            CALL CGSVJ0( JOBV, M-N2, N34-N2, A( N2+1, N2+1 ), LDA,
759     $                   CWORK( N2+1 ), SVA( N2+1 ), MVL,
760     $                   V( N2*q+1, N2+1 ), LDV, EPSLN, SFMIN, TOL, 2,
761     $                   CWORK( N+1 ), LWORK-N, IERR )
762
763            CALL CGSVJ1( JOBV, M-N2, N-N2, N4, A( N2+1, N2+1 ), LDA,
764     $                   CWORK( N2+1 ), SVA( N2+1 ), MVL,
765     $                   V( N2*q+1, N2+1 ), LDV, EPSLN, SFMIN, TOL, 1,
766     $                   CWORK( N+1 ), LWORK-N, IERR )
767*
768            CALL CGSVJ0( JOBV, M-N4, N2-N4, A( N4+1, N4+1 ), LDA,
769     $                   CWORK( N4+1 ), SVA( N4+1 ), MVL,
770     $                   V( N4*q+1, N4+1 ), LDV, EPSLN, SFMIN, TOL, 1,
771     $                   CWORK( N+1 ), LWORK-N, IERR )
772*
773            CALL CGSVJ0( JOBV, M, N4, A, LDA, CWORK, SVA, MVL, V, LDV,
774     $                   EPSLN, SFMIN, TOL, 1, CWORK( N+1 ), LWORK-N,
775     $                   IERR )
776*
777            CALL CGSVJ1( JOBV, M, N2, N4, A, LDA, CWORK, SVA, MVL, V,
778     $                   LDV, EPSLN, SFMIN, TOL, 1, CWORK( N+1 ),
779     $                   LWORK-N, IERR )
780*
781*
782         ELSE IF( UPPER ) THEN
783*
784*
785            CALL CGSVJ0( JOBV, N4, N4, A, LDA, CWORK, SVA, MVL, V, LDV,
786     $                   EPSLN, SFMIN, TOL, 2, CWORK( N+1 ), LWORK-N,
787     $                   IERR )
788*
789            CALL CGSVJ0( JOBV, N2, N4, A( 1, N4+1 ), LDA, CWORK( N4+1 ),
790     $                   SVA( N4+1 ), MVL, V( N4*q+1, N4+1 ), LDV,
791     $                   EPSLN, SFMIN, TOL, 1, CWORK( N+1 ), LWORK-N,
792     $                   IERR )
793*
794            CALL CGSVJ1( JOBV, N2, N2, N4, A, LDA, CWORK, SVA, MVL, V,
795     $                   LDV, EPSLN, SFMIN, TOL, 1, CWORK( N+1 ),
796     $                   LWORK-N, IERR )
797*
798            CALL CGSVJ0( JOBV, N2+N4, N4, A( 1, N2+1 ), LDA,
799     $                   CWORK( N2+1 ), SVA( N2+1 ), MVL,
800     $                   V( N2*q+1, N2+1 ), LDV, EPSLN, SFMIN, TOL, 1,
801     $                   CWORK( N+1 ), LWORK-N, IERR )
802
803         END IF
804*
805      END IF
806*
807*     .. Row-cyclic pivot strategy with de Rijk's pivoting ..
808*
809      DO 1993 i = 1, NSWEEP
810*
811*     .. go go go ...
812*
813         MXAAPQ = ZERO
814         MXSINJ = ZERO
815         ISWROT = 0
816*
817         NOTROT = 0
818         PSKIPPED = 0
819*
820*     Each sweep is unrolled using KBL-by-KBL tiles over the pivot pairs
821*     1 <= p < q <= N. This is the first step toward a blocked implementation
822*     of the rotations. New implementation, based on block transformations,
823*     is under development.
824*
825         DO 2000 ibr = 1, NBL
826*
827            igl = ( ibr-1 )*KBL + 1
828*
829            DO 1002 ir1 = 0, MIN( LKAHEAD, NBL-ibr )
830*
831               igl = igl + ir1*KBL
832*
833               DO 2001 p = igl, MIN( igl+KBL-1, N-1 )
834*
835*     .. de Rijk's pivoting
836*
837                  q = ISAMAX( N-p+1, SVA( p ), 1 ) + p - 1
838                  IF( p.NE.q ) THEN
839                     CALL CSWAP( M, A( 1, p ), 1, A( 1, q ), 1 )
840                     IF( RSVEC )CALL CSWAP( MVL, V( 1, p ), 1,
841     $                                           V( 1, q ), 1 )
842                     TEMP1 = SVA( p )
843                     SVA( p ) = SVA( q )
844                     SVA( q ) = TEMP1
845                     AAPQ = CWORK(p)
846                     CWORK(p) = CWORK(q)
847                     CWORK(q) = AAPQ
848                  END IF
849*
850                  IF( ir1.EQ.0 ) THEN
851*
852*        Column norms are periodically updated by explicit
853*        norm computation.
854*[!]     Caveat:
855*        Unfortunately, some BLAS implementations compute SCNRM2(M,A(1,p),1)
856*        as SQRT(S=CDOTC(M,A(1,p),1,A(1,p),1)), which may cause the result to
857*        overflow for ||A(:,p)||_2 > SQRT(overflow_threshold), and to
858*        underflow for ||A(:,p)||_2 < SQRT(underflow_threshold).
859*        Hence, SCNRM2 cannot be trusted, not even in the case when
860*        the true norm is far from the under(over)flow boundaries.
861*        If properly implemented SCNRM2 is available, the IF-THEN-ELSE-END IF
862*        below should be replaced with "AAPP = SCNRM2( M, A(1,p), 1 )".
863*
864                     IF( ( SVA( p ).LT.ROOTBIG ) .AND.
865     $                    ( SVA( p ).GT.ROOTSFMIN ) ) THEN
866                        SVA( p ) = SCNRM2( M, A( 1, p ), 1 )
867                     ELSE
868                        TEMP1 = ZERO
869                        AAPP = ONE
870                        CALL CLASSQ( M, A( 1, p ), 1, TEMP1, AAPP )
871                        SVA( p ) = TEMP1*SQRT( AAPP )
872                     END IF
873                     AAPP = SVA( p )
874                  ELSE
875                     AAPP = SVA( p )
876                  END IF
877*
878                  IF( AAPP.GT.ZERO ) THEN
879*
880                     PSKIPPED = 0
881*
882                     DO 2002 q = p + 1, MIN( igl+KBL-1, N )
883*
884                        AAQQ = SVA( q )
885*
886                        IF( AAQQ.GT.ZERO ) THEN
887*
888                           AAPP0 = AAPP
889                           IF( AAQQ.GE.ONE ) THEN
890                              ROTOK = ( SMALL*AAPP ).LE.AAQQ
891                              IF( AAPP.LT.( BIG / AAQQ ) ) THEN
892                                 AAPQ = ( CDOTC( M, A( 1, p ), 1,
893     $                                   A( 1, q ), 1 ) / AAQQ ) / AAPP
894                              ELSE
895                                 CALL CCOPY( M, A( 1, p ), 1,
896     $                                        CWORK(N+1), 1 )
897                                 CALL CLASCL( 'G', 0, 0, AAPP, ONE,
898     $                                M, 1, CWORK(N+1), LDA, IERR )
899                                 AAPQ = CDOTC( M, CWORK(N+1), 1,
900     $                                   A( 1, q ), 1 ) / AAQQ
901                              END IF
902                           ELSE
903                              ROTOK = AAPP.LE.( AAQQ / SMALL )
904                              IF( AAPP.GT.( SMALL / AAQQ ) ) THEN
905                                 AAPQ = ( CDOTC( M, A( 1, p ), 1,
906     $                                    A( 1, q ), 1 ) / AAPP ) / AAQQ
907                              ELSE
908                                 CALL CCOPY( M, A( 1, q ), 1,
909     $                                        CWORK(N+1), 1 )
910                                 CALL CLASCL( 'G', 0, 0, AAQQ,
911     $                                         ONE, M, 1,
912     $                                         CWORK(N+1), LDA, IERR )
913                                 AAPQ = CDOTC( M, A(1, p ), 1,
914     $                                   CWORK(N+1), 1 ) / AAPP
915                              END IF
916                           END IF
917*
918*                           AAPQ = AAPQ * CONJG( CWORK(p) ) * CWORK(q)
919                           AAPQ1  = -ABS(AAPQ)
920                           MXAAPQ = MAX( MXAAPQ, -AAPQ1 )
921*
922*        TO rotate or NOT to rotate, THAT is the question ...
923*
924                           IF( ABS( AAPQ1 ).GT.TOL ) THEN
925                               OMPQ = AAPQ / ABS(AAPQ)
926*
927*           .. rotate
928*[RTD]      ROTATED = ROTATED + ONE
929*
930                              IF( ir1.EQ.0 ) THEN
931                                 NOTROT = 0
932                                 PSKIPPED = 0
933                                 ISWROT = ISWROT + 1
934                              END IF
935*
936                              IF( ROTOK ) THEN
937*
938                                 AQOAP = AAQQ / AAPP
939                                 APOAQ = AAPP / AAQQ
940                                 THETA = -HALF*ABS( AQOAP-APOAQ )/AAPQ1
941*
942                                 IF( ABS( THETA ).GT.BIGTHETA ) THEN
943*
944                                    T  = HALF / THETA
945                                    CS = ONE
946
947                                    CALL CROT( M, A(1,p), 1, A(1,q), 1,
948     $                                          CS, CONJG(OMPQ)*T )
949                                    IF ( RSVEC ) THEN
950                                        CALL CROT( MVL, V(1,p), 1,
951     $                                  V(1,q), 1, CS, CONJG(OMPQ)*T )
952                                    END IF
953
954                                    SVA( q ) = AAQQ*SQRT( MAX( ZERO,
955     $                                          ONE+T*APOAQ*AAPQ1 ) )
956                                    AAPP = AAPP*SQRT( MAX( ZERO,
957     $                                          ONE-T*AQOAP*AAPQ1 ) )
958                                    MXSINJ = MAX( MXSINJ, ABS( T ) )
959*
960                                 ELSE
961*
962*                 .. choose correct signum for THETA and rotate
963*
964                                    THSIGN = -SIGN( ONE, AAPQ1 )
965                                    T = ONE / ( THETA+THSIGN*
966     $                                   SQRT( ONE+THETA*THETA ) )
967                                    CS = SQRT( ONE / ( ONE+T*T ) )
968                                    SN = T*CS
969*
970                                    MXSINJ = MAX( MXSINJ, ABS( SN ) )
971                                    SVA( q ) = AAQQ*SQRT( MAX( ZERO,
972     $                                          ONE+T*APOAQ*AAPQ1 ) )
973                                    AAPP = AAPP*SQRT( MAX( ZERO,
974     $                                      ONE-T*AQOAP*AAPQ1 ) )
975*
976                                    CALL CROT( M, A(1,p), 1, A(1,q), 1,
977     $                                          CS, CONJG(OMPQ)*SN )
978                                    IF ( RSVEC ) THEN
979                                        CALL CROT( MVL, V(1,p), 1,
980     $                                  V(1,q), 1, CS, CONJG(OMPQ)*SN )
981                                    END IF
982                                 END IF
983                                 CWORK(p) = -CWORK(q) * OMPQ
984*
985                                 ELSE
986*              .. have to use modified Gram-Schmidt like transformation
987                                 CALL CCOPY( M, A( 1, p ), 1,
988     $                                       CWORK(N+1), 1 )
989                                 CALL CLASCL( 'G', 0, 0, AAPP, ONE, M,
990     $                                        1, CWORK(N+1), LDA,
991     $                                        IERR )
992                                 CALL CLASCL( 'G', 0, 0, AAQQ, ONE, M,
993     $                                        1, A( 1, q ), LDA, IERR )
994                                 CALL CAXPY( M, -AAPQ, CWORK(N+1), 1,
995     $                                       A( 1, q ), 1 )
996                                 CALL CLASCL( 'G', 0, 0, ONE, AAQQ, M,
997     $                                        1, A( 1, q ), LDA, IERR )
998                                 SVA( q ) = AAQQ*SQRT( MAX( ZERO,
999     $                                      ONE-AAPQ1*AAPQ1 ) )
1000                                 MXSINJ = MAX( MXSINJ, SFMIN )
1001                              END IF
1002*           END IF ROTOK THEN ... ELSE
1003*
1004*           In the case of cancellation in updating SVA(q), SVA(p)
1005*           recompute SVA(q), SVA(p).
1006*
1007                              IF( ( SVA( q ) / AAQQ )**2.LE.ROOTEPS )
1008     $                            THEN
1009                                 IF( ( AAQQ.LT.ROOTBIG ) .AND.
1010     $                               ( AAQQ.GT.ROOTSFMIN ) ) THEN
1011                                    SVA( q ) = SCNRM2( M, A( 1, q ), 1 )
1012                                 ELSE
1013                                    T = ZERO
1014                                    AAQQ = ONE
1015                                    CALL CLASSQ( M, A( 1, q ), 1, T,
1016     $                                           AAQQ )
1017                                    SVA( q ) = T*SQRT( AAQQ )
1018                                 END IF
1019                              END IF
1020                              IF( ( AAPP / AAPP0 ).LE.ROOTEPS ) THEN
1021                                 IF( ( AAPP.LT.ROOTBIG ) .AND.
1022     $                               ( AAPP.GT.ROOTSFMIN ) ) THEN
1023                                    AAPP = SCNRM2( M, A( 1, p ), 1 )
1024                                 ELSE
1025                                    T = ZERO
1026                                    AAPP = ONE
1027                                    CALL CLASSQ( M, A( 1, p ), 1, T,
1028     $                                           AAPP )
1029                                    AAPP = T*SQRT( AAPP )
1030                                 END IF
1031                                 SVA( p ) = AAPP
1032                              END IF
1033*
1034                           ELSE
1035*                             A(:,p) and A(:,q) already numerically orthogonal
1036                              IF( ir1.EQ.0 )NOTROT = NOTROT + 1
1037*[RTD]      SKIPPED  = SKIPPED + 1
1038                              PSKIPPED = PSKIPPED + 1
1039                           END IF
1040                        ELSE
1041*                          A(:,q) is zero column
1042                           IF( ir1.EQ.0 )NOTROT = NOTROT + 1
1043                           PSKIPPED = PSKIPPED + 1
1044                        END IF
1045*
1046                        IF( ( i.LE.SWBAND ) .AND.
1047     $                      ( PSKIPPED.GT.ROWSKIP ) ) THEN
1048                           IF( ir1.EQ.0 )AAPP = -AAPP
1049                           NOTROT = 0
1050                           GO TO 2103
1051                        END IF
1052*
1053 2002                CONTINUE
1054*     END q-LOOP
1055*
1056 2103                CONTINUE
1057*     bailed out of q-loop
1058*
1059                     SVA( p ) = AAPP
1060*
1061                  ELSE
1062                     SVA( p ) = AAPP
1063                     IF( ( ir1.EQ.0 ) .AND. ( AAPP.EQ.ZERO ) )
1064     $                   NOTROT = NOTROT + MIN( igl+KBL-1, N ) - p
1065                  END IF
1066*
1067 2001          CONTINUE
1068*     end of the p-loop
1069*     end of doing the block ( ibr, ibr )
1070 1002       CONTINUE
1071*     end of ir1-loop
1072*
1073* ... go to the off diagonal blocks
1074*
1075            igl = ( ibr-1 )*KBL + 1
1076*
1077            DO 2010 jbc = ibr + 1, NBL
1078*
1079               jgl = ( jbc-1 )*KBL + 1
1080*
1081*        doing the block at ( ibr, jbc )
1082*
1083               IJBLSK = 0
1084               DO 2100 p = igl, MIN( igl+KBL-1, N )
1085*
1086                  AAPP = SVA( p )
1087                  IF( AAPP.GT.ZERO ) THEN
1088*
1089                     PSKIPPED = 0
1090*
1091                     DO 2200 q = jgl, MIN( jgl+KBL-1, N )
1092*
1093                        AAQQ = SVA( q )
1094                        IF( AAQQ.GT.ZERO ) THEN
1095                           AAPP0 = AAPP
1096*
1097*     .. M x 2 Jacobi SVD ..
1098*
1099*        Safe Gram matrix computation
1100*
1101                           IF( AAQQ.GE.ONE ) THEN
1102                              IF( AAPP.GE.AAQQ ) THEN
1103                                 ROTOK = ( SMALL*AAPP ).LE.AAQQ
1104                              ELSE
1105                                 ROTOK = ( SMALL*AAQQ ).LE.AAPP
1106                              END IF
1107                              IF( AAPP.LT.( BIG / AAQQ ) ) THEN
1108                                 AAPQ = ( CDOTC( M, A( 1, p ), 1,
1109     $                                  A( 1, q ), 1 ) / AAQQ ) / AAPP
1110                              ELSE
1111                                 CALL CCOPY( M, A( 1, p ), 1,
1112     $                                       CWORK(N+1), 1 )
1113                                 CALL CLASCL( 'G', 0, 0, AAPP,
1114     $                                        ONE, M, 1,
1115     $                                        CWORK(N+1), LDA, IERR )
1116                                 AAPQ = CDOTC( M, CWORK(N+1), 1,
1117     $                                  A( 1, q ), 1 ) / AAQQ
1118                              END IF
1119                           ELSE
1120                              IF( AAPP.GE.AAQQ ) THEN
1121                                 ROTOK = AAPP.LE.( AAQQ / SMALL )
1122                              ELSE
1123                                 ROTOK = AAQQ.LE.( AAPP / SMALL )
1124                              END IF
1125                              IF( AAPP.GT.( SMALL / AAQQ ) ) THEN
1126                                 AAPQ = ( CDOTC( M, A( 1, p ), 1,
1127     $                                 A( 1, q ), 1 ) / MAX(AAQQ,AAPP) )
1128     $                                                / MIN(AAQQ,AAPP)
1129                              ELSE
1130                                 CALL CCOPY( M, A( 1, q ), 1,
1131     $                                       CWORK(N+1), 1 )
1132                                 CALL CLASCL( 'G', 0, 0, AAQQ,
1133     $                                        ONE, M, 1,
1134     $                                        CWORK(N+1), LDA, IERR )
1135                                 AAPQ = CDOTC( M, A( 1, p ), 1,
1136     $                                  CWORK(N+1),  1 ) / AAPP
1137                              END IF
1138                           END IF
1139*
1140*                           AAPQ = AAPQ * CONJG(CWORK(p))*CWORK(q)
1141                           AAPQ1  = -ABS(AAPQ)
1142                           MXAAPQ = MAX( MXAAPQ, -AAPQ1 )
1143*
1144*        TO rotate or NOT to rotate, THAT is the question ...
1145*
1146                           IF( ABS( AAPQ1 ).GT.TOL ) THEN
1147                              OMPQ = AAPQ / ABS(AAPQ)
1148                              NOTROT = 0
1149*[RTD]      ROTATED  = ROTATED + 1
1150                              PSKIPPED = 0
1151                              ISWROT = ISWROT + 1
1152*
1153                              IF( ROTOK ) THEN
1154*
1155                                 AQOAP = AAQQ / AAPP
1156                                 APOAQ = AAPP / AAQQ
1157                                 THETA = -HALF*ABS( AQOAP-APOAQ )/ AAPQ1
1158                                 IF( AAQQ.GT.AAPP0 )THETA = -THETA
1159*
1160                                 IF( ABS( THETA ).GT.BIGTHETA ) THEN
1161                                    T  = HALF / THETA
1162                                    CS = ONE
1163                                    CALL CROT( M, A(1,p), 1, A(1,q), 1,
1164     $                                          CS, CONJG(OMPQ)*T )
1165                                    IF( RSVEC ) THEN
1166                                        CALL CROT( MVL, V(1,p), 1,
1167     $                                  V(1,q), 1, CS, CONJG(OMPQ)*T )
1168                                    END IF
1169                                    SVA( q ) = AAQQ*SQRT( MAX( ZERO,
1170     $                                         ONE+T*APOAQ*AAPQ1 ) )
1171                                    AAPP = AAPP*SQRT( MAX( ZERO,
1172     $                                     ONE-T*AQOAP*AAPQ1 ) )
1173                                    MXSINJ = MAX( MXSINJ, ABS( T ) )
1174                                 ELSE
1175*
1176*                 .. choose correct signum for THETA and rotate
1177*
1178                                    THSIGN = -SIGN( ONE, AAPQ1 )
1179                                    IF( AAQQ.GT.AAPP0 )THSIGN = -THSIGN
1180                                    T = ONE / ( THETA+THSIGN*
1181     $                                  SQRT( ONE+THETA*THETA ) )
1182                                    CS = SQRT( ONE / ( ONE+T*T ) )
1183                                    SN = T*CS
1184                                    MXSINJ = MAX( MXSINJ, ABS( SN ) )
1185                                    SVA( q ) = AAQQ*SQRT( MAX( ZERO,
1186     $                                         ONE+T*APOAQ*AAPQ1 ) )
1187                                    AAPP = AAPP*SQRT( MAX( ZERO,
1188     $                                         ONE-T*AQOAP*AAPQ1 ) )
1189*
1190                                    CALL CROT( M, A(1,p), 1, A(1,q), 1,
1191     $                                          CS, CONJG(OMPQ)*SN )
1192                                    IF( RSVEC ) THEN
1193                                        CALL CROT( MVL, V(1,p), 1,
1194     $                                  V(1,q), 1, CS, CONJG(OMPQ)*SN )
1195                                    END IF
1196                                 END IF
1197                                 CWORK(p) = -CWORK(q) * OMPQ
1198*
1199                              ELSE
1200*              .. have to use modified Gram-Schmidt like transformation
1201                               IF( AAPP.GT.AAQQ ) THEN
1202                                    CALL CCOPY( M, A( 1, p ), 1,
1203     $                                          CWORK(N+1), 1 )
1204                                    CALL CLASCL( 'G', 0, 0, AAPP, ONE,
1205     $                                           M, 1, CWORK(N+1),LDA,
1206     $                                           IERR )
1207                                    CALL CLASCL( 'G', 0, 0, AAQQ, ONE,
1208     $                                           M, 1, A( 1, q ), LDA,
1209     $                                           IERR )
1210                                    CALL CAXPY( M, -AAPQ, CWORK(N+1),
1211     $                                          1, A( 1, q ), 1 )
1212                                    CALL CLASCL( 'G', 0, 0, ONE, AAQQ,
1213     $                                           M, 1, A( 1, q ), LDA,
1214     $                                           IERR )
1215                                    SVA( q ) = AAQQ*SQRT( MAX( ZERO,
1216     $                                         ONE-AAPQ1*AAPQ1 ) )
1217                                    MXSINJ = MAX( MXSINJ, SFMIN )
1218                               ELSE
1219                                   CALL CCOPY( M, A( 1, q ), 1,
1220     $                                          CWORK(N+1), 1 )
1221                                    CALL CLASCL( 'G', 0, 0, AAQQ, ONE,
1222     $                                           M, 1, CWORK(N+1),LDA,
1223     $                                           IERR )
1224                                    CALL CLASCL( 'G', 0, 0, AAPP, ONE,
1225     $                                           M, 1, A( 1, p ), LDA,
1226     $                                           IERR )
1227                                    CALL CAXPY( M, -CONJG(AAPQ),
1228     $                                   CWORK(N+1), 1, A( 1, p ), 1 )
1229                                    CALL CLASCL( 'G', 0, 0, ONE, AAPP,
1230     $                                           M, 1, A( 1, p ), LDA,
1231     $                                           IERR )
1232                                    SVA( p ) = AAPP*SQRT( MAX( ZERO,
1233     $                                         ONE-AAPQ1*AAPQ1 ) )
1234                                    MXSINJ = MAX( MXSINJ, SFMIN )
1235                               END IF
1236                              END IF
1237*           END IF ROTOK THEN ... ELSE
1238*
1239*           In the case of cancellation in updating SVA(q), SVA(p)
1240*           .. recompute SVA(q), SVA(p)
1241                              IF( ( SVA( q ) / AAQQ )**2.LE.ROOTEPS )
1242     $                            THEN
1243                                 IF( ( AAQQ.LT.ROOTBIG ) .AND.
1244     $                               ( AAQQ.GT.ROOTSFMIN ) ) THEN
1245                                    SVA( q ) = SCNRM2( M, A( 1, q ), 1)
1246                                  ELSE
1247                                    T = ZERO
1248                                    AAQQ = ONE
1249                                    CALL CLASSQ( M, A( 1, q ), 1, T,
1250     $                                           AAQQ )
1251                                    SVA( q ) = T*SQRT( AAQQ )
1252                                 END IF
1253                              END IF
1254                              IF( ( AAPP / AAPP0 )**2.LE.ROOTEPS ) THEN
1255                                 IF( ( AAPP.LT.ROOTBIG ) .AND.
1256     $                               ( AAPP.GT.ROOTSFMIN ) ) THEN
1257                                    AAPP = SCNRM2( M, A( 1, p ), 1 )
1258                                 ELSE
1259                                    T = ZERO
1260                                    AAPP = ONE
1261                                    CALL CLASSQ( M, A( 1, p ), 1, T,
1262     $                                           AAPP )
1263                                    AAPP = T*SQRT( AAPP )
1264                                 END IF
1265                                 SVA( p ) = AAPP
1266                              END IF
1267*              end of OK rotation
1268                           ELSE
1269                              NOTROT = NOTROT + 1
1270*[RTD]      SKIPPED  = SKIPPED  + 1
1271                              PSKIPPED = PSKIPPED + 1
1272                              IJBLSK = IJBLSK + 1
1273                           END IF
1274                        ELSE
1275                           NOTROT = NOTROT + 1
1276                           PSKIPPED = PSKIPPED + 1
1277                           IJBLSK = IJBLSK + 1
1278                        END IF
1279*
1280                        IF( ( i.LE.SWBAND ) .AND. ( IJBLSK.GE.BLSKIP ) )
1281     $                      THEN
1282                           SVA( p ) = AAPP
1283                           NOTROT = 0
1284                           GO TO 2011
1285                        END IF
1286                        IF( ( i.LE.SWBAND ) .AND.
1287     $                      ( PSKIPPED.GT.ROWSKIP ) ) THEN
1288                           AAPP = -AAPP
1289                           NOTROT = 0
1290                           GO TO 2203
1291                        END IF
1292*
1293 2200                CONTINUE
1294*        end of the q-loop
1295 2203                CONTINUE
1296*
1297                     SVA( p ) = AAPP
1298*
1299                  ELSE
1300*
1301                     IF( AAPP.EQ.ZERO )NOTROT = NOTROT +
1302     $                   MIN( jgl+KBL-1, N ) - jgl + 1
1303                     IF( AAPP.LT.ZERO )NOTROT = 0
1304*
1305                  END IF
1306*
1307 2100          CONTINUE
1308*     end of the p-loop
1309 2010       CONTINUE
1310*     end of the jbc-loop
1311 2011       CONTINUE
1312*2011 bailed out of the jbc-loop
1313            DO 2012 p = igl, MIN( igl+KBL-1, N )
1314               SVA( p ) = ABS( SVA( p ) )
1315 2012       CONTINUE
1316***
1317 2000    CONTINUE
1318*2000 :: end of the ibr-loop
1319*
1320*     .. update SVA(N)
1321         IF( ( SVA( N ).LT.ROOTBIG ) .AND. ( SVA( N ).GT.ROOTSFMIN ) )
1322     $       THEN
1323            SVA( N ) = SCNRM2( M, A( 1, N ), 1 )
1324         ELSE
1325            T = ZERO
1326            AAPP = ONE
1327            CALL CLASSQ( M, A( 1, N ), 1, T, AAPP )
1328            SVA( N ) = T*SQRT( AAPP )
1329         END IF
1330*
1331*     Additional steering devices
1332*
1333         IF( ( i.LT.SWBAND ) .AND. ( ( MXAAPQ.LE.ROOTTOL ) .OR.
1334     $       ( ISWROT.LE.N ) ) )SWBAND = i
1335*
1336         IF( ( i.GT.SWBAND+1 ) .AND. ( MXAAPQ.LT.SQRT( REAL( N ) )*
1337     $       TOL ) .AND. ( REAL( N )*MXAAPQ*MXSINJ.LT.TOL ) ) THEN
1338            GO TO 1994
1339         END IF
1340*
1341         IF( NOTROT.GE.EMPTSW )GO TO 1994
1342*
1343 1993 CONTINUE
1344*     end i=1:NSWEEP loop
1345*
1346* #:( Reaching this point means that the procedure has not converged.
1347      INFO = NSWEEP - 1
1348      GO TO 1995
1349*
1350 1994 CONTINUE
1351* #:) Reaching this point means numerical convergence after the i-th
1352*     sweep.
1353*
1354      INFO = 0
1355* #:) INFO = 0 confirms successful iterations.
1356 1995 CONTINUE
1357*
1358*     Sort the singular values and find how many are above
1359*     the underflow threshold.
1360*
1361      N2 = 0
1362      N4 = 0
1363      DO 5991 p = 1, N - 1
1364         q = ISAMAX( N-p+1, SVA( p ), 1 ) + p - 1
1365         IF( p.NE.q ) THEN
1366            TEMP1 = SVA( p )
1367            SVA( p ) = SVA( q )
1368            SVA( q ) = TEMP1
1369            CALL CSWAP( M, A( 1, p ), 1, A( 1, q ), 1 )
1370            IF( RSVEC )CALL CSWAP( MVL, V( 1, p ), 1, V( 1, q ), 1 )
1371         END IF
1372         IF( SVA( p ).NE.ZERO ) THEN
1373            N4 = N4 + 1
1374            IF( SVA( p )*SKL.GT.SFMIN )N2 = N2 + 1
1375         END IF
1376 5991 CONTINUE
1377      IF( SVA( N ).NE.ZERO ) THEN
1378         N4 = N4 + 1
1379         IF( SVA( N )*SKL.GT.SFMIN )N2 = N2 + 1
1380      END IF
1381*
1382*     Normalize the left singular vectors.
1383*
1384      IF( LSVEC .OR. UCTOL ) THEN
1385         DO 1998 p = 1, N4
1386*           CALL CSSCAL( M, ONE / SVA( p ), A( 1, p ), 1 )
1387            CALL CLASCL( 'G',0,0, SVA(p), ONE, M, 1, A(1,p), M, IERR )
1388 1998    CONTINUE
1389      END IF
1390*
1391*     Scale the product of Jacobi rotations.
1392*
1393      IF( RSVEC ) THEN
1394            DO 2399 p = 1, N
1395               TEMP1 = ONE / SCNRM2( MVL, V( 1, p ), 1 )
1396               CALL CSSCAL( MVL, TEMP1, V( 1, p ), 1 )
1397 2399       CONTINUE
1398      END IF
1399*
1400*     Undo scaling, if necessary (and possible).
1401      IF( ( ( SKL.GT.ONE ) .AND. ( SVA( 1 ).LT.( BIG / SKL ) ) )
1402     $    .OR. ( ( SKL.LT.ONE ) .AND. ( SVA( MAX( N2, 1 ) ) .GT.
1403     $    ( SFMIN / SKL ) ) ) ) THEN
1404         DO 2400 p = 1, N
1405            SVA( P ) = SKL*SVA( P )
1406 2400    CONTINUE
1407         SKL = ONE
1408      END IF
1409*
1410      RWORK( 1 ) = SKL
1411*     The singular values of A are SKL*SVA(1:N). If SKL.NE.ONE
1412*     then some of the singular values may overflow or underflow and
1413*     the spectrum is given in this factored representation.
1414*
1415      RWORK( 2 ) = REAL( N4 )
1416*     N4 is the number of computed nonzero singular values of A.
1417*
1418      RWORK( 3 ) = REAL( N2 )
1419*     N2 is the number of singular values of A greater than SFMIN.
1420*     If N2<N, SVA(N2:N) contains ZEROS and/or denormalized numbers
1421*     that may carry some information.
1422*
1423      RWORK( 4 ) = REAL( i )
1424*     i is the index of the last sweep before declaring convergence.
1425*
1426      RWORK( 5 ) = MXAAPQ
1427*     MXAAPQ is the largest absolute value of scaled pivots in the
1428*     last sweep
1429*
1430      RWORK( 6 ) = MXSINJ
1431*     MXSINJ is the largest absolute value of the sines of Jacobi angles
1432*     in the last sweep
1433*
1434      RETURN
1435*     ..
1436*     .. END OF CGESVJ
1437*     ..
1438      END
1439*
1440