3
* =========== DOCUMENTATION ===========
5
* Online html documentation available at
6
* http://www.netlib.org/lapack/explore-html/
9
*> Download DBDSQR + dependencies
10
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/dbdsqr.f">
12
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/dbdsqr.f">
14
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/dbdsqr.f">
21
* SUBROUTINE DBDSQR( UPLO, N, NCVT, NRU, NCC, D, E, VT, LDVT, U,
22
* LDU, C, LDC, WORK, INFO )
24
* .. Scalar Arguments ..
26
* INTEGER INFO, LDC, LDU, LDVT, N, NCC, NCVT, NRU
28
* .. Array Arguments ..
29
* DOUBLE PRECISION C( LDC, * ), D( * ), E( * ), U( LDU, * ),
30
* $ VT( LDVT, * ), WORK( * )
39
*> DBDSQR computes the singular values and, optionally, the right and/or
40
*> left singular vectors from the singular value decomposition (SVD) of
41
*> a real N-by-N (upper or lower) bidiagonal matrix B using the implicit
42
*> zero-shift QR algorithm. The SVD of B has the form
46
*> where S is the diagonal matrix of singular values, Q is an orthogonal
47
*> matrix of left singular vectors, and P is an orthogonal matrix of
48
*> right singular vectors. If left singular vectors are requested, this
49
*> subroutine actually returns U*Q instead of Q, and, if right singular
50
*> vectors are requested, this subroutine returns P**T*VT instead of
51
*> P**T, for given real input matrices U and VT. When U and VT are the
52
*> orthogonal matrices that reduce a general matrix A to bidiagonal
53
*> form: A = U*B*VT, as computed by DGEBRD, then
55
*> A = (U*Q) * S * (P**T*VT)
57
*> is the SVD of A. Optionally, the subroutine may also compute Q**T*C
58
*> for a given real input matrix C.
60
*> See "Computing Small Singular Values of Bidiagonal Matrices With
61
*> Guaranteed High Relative Accuracy," by J. Demmel and W. Kahan,
62
*> LAPACK Working Note #3 (or SIAM J. Sci. Statist. Comput. vol. 11,
63
*> no. 5, pp. 873-912, Sept 1990) and
64
*> "Accurate singular values and differential qd algorithms," by
65
*> B. Parlett and V. Fernando, Technical Report CPAM-554, Mathematics
66
*> Department, University of California at Berkeley, July 1992
67
*> for a detailed description of the algorithm.
75
*> UPLO is CHARACTER*1
76
*> = 'U': B is upper bidiagonal;
77
*> = 'L': B is lower bidiagonal.
83
*> The order of the matrix B. N >= 0.
89
*> The number of columns of the matrix VT. NCVT >= 0.
95
*> The number of rows of the matrix U. NRU >= 0.
101
*> The number of columns of the matrix C. NCC >= 0.
106
*> D is DOUBLE PRECISION array, dimension (N)
107
*> On entry, the n diagonal elements of the bidiagonal matrix B.
108
*> On exit, if INFO=0, the singular values of B in decreasing
114
*> E is DOUBLE PRECISION array, dimension (N-1)
115
*> On entry, the N-1 offdiagonal elements of the bidiagonal
117
*> On exit, if INFO = 0, E is destroyed; if INFO > 0, D and E
118
*> will contain the diagonal and superdiagonal elements of a
119
*> bidiagonal matrix orthogonally equivalent to the one given
125
*> VT is DOUBLE PRECISION array, dimension (LDVT, NCVT)
126
*> On entry, an N-by-NCVT matrix VT.
127
*> On exit, VT is overwritten by P**T * VT.
128
*> Not referenced if NCVT = 0.
134
*> The leading dimension of the array VT.
135
*> LDVT >= max(1,N) if NCVT > 0; LDVT >= 1 if NCVT = 0.
140
*> U is DOUBLE PRECISION array, dimension (LDU, N)
141
*> On entry, an NRU-by-N matrix U.
142
*> On exit, U is overwritten by U * Q.
143
*> Not referenced if NRU = 0.
149
*> The leading dimension of the array U. LDU >= max(1,NRU).
154
*> C is DOUBLE PRECISION array, dimension (LDC, NCC)
155
*> On entry, an N-by-NCC matrix C.
156
*> On exit, C is overwritten by Q**T * C.
157
*> Not referenced if NCC = 0.
163
*> The leading dimension of the array C.
164
*> LDC >= max(1,N) if NCC > 0; LDC >=1 if NCC = 0.
169
*> WORK is DOUBLE PRECISION array, dimension (4*N)
175
*> = 0: successful exit
176
*> < 0: If INFO = -i, the i-th argument had an illegal value
178
*> if NCVT = NRU = NCC = 0,
179
*> = 1, a split was marked by a positive value in E
180
*> = 2, current block of Z not diagonalized after 30*N
181
*> iterations (in inner while loop)
182
*> = 3, termination criterion of outer while loop not met
183
*> (program created more than N unreduced blocks)
184
*> else NCVT = NRU = NCC = 0,
185
*> the algorithm did not converge; D and E contain the
186
*> elements of a bidiagonal matrix which is orthogonally
187
*> similar to the input matrix B; if INFO = i, i
188
*> elements of E have not converged to zero.
191
*> \par Internal Parameters:
192
* =========================
195
*> TOLMUL DOUBLE PRECISION, default = max(10,min(100,EPS**(-1/8)))
196
*> TOLMUL controls the convergence criterion of the QR loop.
197
*> If it is positive, TOLMUL*EPS is the desired relative
198
*> precision in the computed singular values.
199
*> If it is negative, abs(TOLMUL*EPS*sigma_max) is the
200
*> desired absolute accuracy in the computed singular
201
*> values (corresponds to relative accuracy
202
*> abs(TOLMUL*EPS) in the largest singular value.
203
*> abs(TOLMUL) should be between 1 and 1/EPS, and preferably
204
*> between 10 (for fast convergence) and .1/EPS
205
*> (for there to be some accuracy in the results).
206
*> Default is to lose at either one eighth or 2 of the
207
*> available decimal digits in each computed singular value
208
*> (whichever is smaller).
210
*> MAXITR INTEGER, default = 6
211
*> MAXITR controls the maximum number of passes of the
212
*> algorithm through its inner loop. The algorithms stops
213
*> (and so fails to converge) if the number of passes
214
*> through the inner loop exceeds MAXITR*N**2.
220
*> \author Univ. of Tennessee
221
*> \author Univ. of California Berkeley
222
*> \author Univ. of Colorado Denver
225
*> \date November 2011
227
*> \ingroup auxOTHERcomputational
229
* =====================================================================
230
SUBROUTINE DBDSQR( UPLO, N, NCVT, NRU, NCC, D, E, VT, LDVT, U,
231
$ LDU, C, LDC, WORK, INFO )
233
* -- LAPACK computational routine (version 3.4.0) --
234
* -- LAPACK is a software package provided by Univ. of Tennessee, --
235
* -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..--
238
* .. Scalar Arguments ..
240
INTEGER INFO, LDC, LDU, LDVT, N, NCC, NCVT, NRU
242
* .. Array Arguments ..
243
DOUBLE PRECISION C( LDC, * ), D( * ), E( * ), U( LDU, * ),
244
$ VT( LDVT, * ), WORK( * )
247
* =====================================================================
250
DOUBLE PRECISION ZERO
251
PARAMETER ( ZERO = 0.0D0 )
253
PARAMETER ( ONE = 1.0D0 )
254
DOUBLE PRECISION NEGONE
255
PARAMETER ( NEGONE = -1.0D0 )
256
DOUBLE PRECISION HNDRTH
257
PARAMETER ( HNDRTH = 0.01D0 )
259
PARAMETER ( TEN = 10.0D0 )
260
DOUBLE PRECISION HNDRD
261
PARAMETER ( HNDRD = 100.0D0 )
262
DOUBLE PRECISION MEIGTH
263
PARAMETER ( MEIGTH = -0.125D0 )
265
PARAMETER ( MAXITR = 6 )
267
* .. Local Scalars ..
268
LOGICAL LOWER, ROTATE
269
INTEGER I, IDIR, ISUB, ITER, J, LL, LLL, M, MAXIT, NM1,
270
$ NM12, NM13, OLDLL, OLDM
271
DOUBLE PRECISION ABSE, ABSS, COSL, COSR, CS, EPS, F, G, H, MU,
272
$ OLDCS, OLDSN, R, SHIFT, SIGMN, SIGMX, SINL,
273
$ SINR, SLL, SMAX, SMIN, SMINL, SMINOA,
274
$ SN, THRESH, TOL, TOLMUL, UNFL
276
* .. External Functions ..
278
DOUBLE PRECISION DLAMCH
279
EXTERNAL LSAME, DLAMCH
281
* .. External Subroutines ..
282
EXTERNAL DLARTG, DLAS2, DLASQ1, DLASR, DLASV2, DROT,
283
$ DSCAL, DSWAP, XERBLA
285
* .. Intrinsic Functions ..
286
INTRINSIC ABS, DBLE, MAX, MIN, SIGN, SQRT
288
* .. Executable Statements ..
290
* Test the input parameters.
293
LOWER = LSAME( UPLO, 'L' )
294
IF( .NOT.LSAME( UPLO, 'U' ) .AND. .NOT.LOWER ) THEN
296
ELSE IF( N.LT.0 ) THEN
298
ELSE IF( NCVT.LT.0 ) THEN
300
ELSE IF( NRU.LT.0 ) THEN
302
ELSE IF( NCC.LT.0 ) THEN
304
ELSE IF( ( NCVT.EQ.0 .AND. LDVT.LT.1 ) .OR.
305
$ ( NCVT.GT.0 .AND. LDVT.LT.MAX( 1, N ) ) ) THEN
307
ELSE IF( LDU.LT.MAX( 1, NRU ) ) THEN
309
ELSE IF( ( NCC.EQ.0 .AND. LDC.LT.1 ) .OR.
310
$ ( NCC.GT.0 .AND. LDC.LT.MAX( 1, N ) ) ) THEN
314
CALL XERBLA( 'DBDSQR', -INFO )
322
* ROTATE is true if any singular vectors desired, false otherwise
324
ROTATE = ( NCVT.GT.0 ) .OR. ( NRU.GT.0 ) .OR. ( NCC.GT.0 )
326
* If no singular vectors desired, use qd algorithm
328
IF( .NOT.ROTATE ) THEN
329
CALL DLASQ1( N, D, E, WORK, INFO )
331
* If INFO equals 2, dqds didn't finish, try to finish
333
IF( INFO .NE. 2 ) RETURN
342
* Get machine constants
344
EPS = DLAMCH( 'Epsilon' )
345
UNFL = DLAMCH( 'Safe minimum' )
347
* If matrix lower bidiagonal, rotate to be upper bidiagonal
348
* by applying Givens rotations on the left
352
CALL DLARTG( D( I ), E( I ), CS, SN, R )
355
D( I+1 ) = CS*D( I+1 )
360
* Update singular vectors if desired
363
$ CALL DLASR( 'R', 'V', 'F', NRU, N, WORK( 1 ), WORK( N ), U,
366
$ CALL DLASR( 'L', 'V', 'F', N, NCC, WORK( 1 ), WORK( N ), C,
370
* Compute singular values to relative accuracy TOL
371
* (By setting TOL to be negative, algorithm will compute
372
* singular values to absolute accuracy ABS(TOL)*norm(input matrix))
374
TOLMUL = MAX( TEN, MIN( HNDRD, EPS**MEIGTH ) )
377
* Compute approximate maximum, minimum singular values
381
SMAX = MAX( SMAX, ABS( D( I ) ) )
384
SMAX = MAX( SMAX, ABS( E( I ) ) )
387
IF( TOL.GE.ZERO ) THEN
389
* Relative accuracy desired
391
SMINOA = ABS( D( 1 ) )
396
MU = ABS( D( I ) )*( MU / ( MU+ABS( E( I-1 ) ) ) )
397
SMINOA = MIN( SMINOA, MU )
402
SMINOA = SMINOA / SQRT( DBLE( N ) )
403
THRESH = MAX( TOL*SMINOA, MAXITR*N*N*UNFL )
406
* Absolute accuracy desired
408
THRESH = MAX( ABS( TOL )*SMAX, MAXITR*N*N*UNFL )
411
* Prepare for main iteration loop for the singular values
412
* (MAXIT is the maximum number of passes through the inner
413
* loop permitted before nonconvergence signalled.)
420
* M points to last element of unconverged part of matrix
424
* Begin main iteration loop
428
* Check for convergence or exceeding iteration count
435
* Find diagonal block of matrix to work on
437
IF( TOL.LT.ZERO .AND. ABS( D( M ) ).LE.THRESH )
443
ABSS = ABS( D( LL ) )
444
ABSE = ABS( E( LL ) )
445
IF( TOL.LT.ZERO .AND. ABSS.LE.THRESH )
449
SMIN = MIN( SMIN, ABSS )
450
SMAX = MAX( SMAX, ABSS, ABSE )
457
* Matrix splits since E(LL) = 0
461
* Convergence of bottom singular value, return to top of loop
469
* E(LL) through E(M-1) are nonzero, E(LL-1) is zero
473
* 2 by 2 block, handle separately
475
CALL DLASV2( D( M-1 ), E( M-1 ), D( M ), SIGMN, SIGMX, SINR,
481
* Compute singular vectors, if desired
484
$ CALL DROT( NCVT, VT( M-1, 1 ), LDVT, VT( M, 1 ), LDVT, COSR,
487
$ CALL DROT( NRU, U( 1, M-1 ), 1, U( 1, M ), 1, COSL, SINL )
489
$ CALL DROT( NCC, C( M-1, 1 ), LDC, C( M, 1 ), LDC, COSL,
495
* If working on new submatrix, choose shift direction
496
* (from larger end diagonal element towards smaller)
498
IF( LL.GT.OLDM .OR. M.LT.OLDLL ) THEN
499
IF( ABS( D( LL ) ).GE.ABS( D( M ) ) ) THEN
501
* Chase bulge from top (big end) to bottom (small end)
506
* Chase bulge from bottom (big end) to top (small end)
512
* Apply convergence tests
516
* Run convergence test in forward direction
517
* First apply standard test to bottom of matrix
519
IF( ABS( E( M-1 ) ).LE.ABS( TOL )*ABS( D( M ) ) .OR.
520
$ ( TOL.LT.ZERO .AND. ABS( E( M-1 ) ).LE.THRESH ) ) THEN
525
IF( TOL.GE.ZERO ) THEN
527
* If relative accuracy desired,
528
* apply convergence criterion forward
532
DO 100 LLL = LL, M - 1
533
IF( ABS( E( LLL ) ).LE.TOL*MU ) THEN
537
MU = ABS( D( LLL+1 ) )*( MU / ( MU+ABS( E( LLL ) ) ) )
538
SMINL = MIN( SMINL, MU )
544
* Run convergence test in backward direction
545
* First apply standard test to top of matrix
547
IF( ABS( E( LL ) ).LE.ABS( TOL )*ABS( D( LL ) ) .OR.
548
$ ( TOL.LT.ZERO .AND. ABS( E( LL ) ).LE.THRESH ) ) THEN
553
IF( TOL.GE.ZERO ) THEN
555
* If relative accuracy desired,
556
* apply convergence criterion backward
560
DO 110 LLL = M - 1, LL, -1
561
IF( ABS( E( LLL ) ).LE.TOL*MU ) THEN
565
MU = ABS( D( LLL ) )*( MU / ( MU+ABS( E( LLL ) ) ) )
566
SMINL = MIN( SMINL, MU )
573
* Compute shift. First, test if shifting would ruin relative
574
* accuracy, and if so set the shift to zero.
576
IF( TOL.GE.ZERO .AND. N*TOL*( SMINL / SMAX ).LE.
577
$ MAX( EPS, HNDRTH*TOL ) ) THEN
579
* Use a zero shift to avoid loss of relative accuracy
584
* Compute the shift from 2-by-2 block at end of matrix
588
CALL DLAS2( D( M-1 ), E( M-1 ), D( M ), SHIFT, R )
591
CALL DLAS2( D( LL ), E( LL ), D( LL+1 ), SHIFT, R )
594
* Test if shift negligible, and if so set to zero
596
IF( SLL.GT.ZERO ) THEN
597
IF( ( SHIFT / SLL )**2.LT.EPS )
602
* Increment iteration count
606
* If SHIFT = 0, do simplified QR iteration
608
IF( SHIFT.EQ.ZERO ) THEN
611
* Chase bulge from top to bottom
612
* Save cosines and sines for later singular vector updates
617
CALL DLARTG( D( I )*CS, E( I ), CS, SN, R )
620
CALL DLARTG( OLDCS*R, D( I+1 )*SN, OLDCS, OLDSN, D( I ) )
622
WORK( I-LL+1+NM1 ) = SN
623
WORK( I-LL+1+NM12 ) = OLDCS
624
WORK( I-LL+1+NM13 ) = OLDSN
630
* Update singular vectors
633
$ CALL DLASR( 'L', 'V', 'F', M-LL+1, NCVT, WORK( 1 ),
634
$ WORK( N ), VT( LL, 1 ), LDVT )
636
$ CALL DLASR( 'R', 'V', 'F', NRU, M-LL+1, WORK( NM12+1 ),
637
$ WORK( NM13+1 ), U( 1, LL ), LDU )
639
$ CALL DLASR( 'L', 'V', 'F', M-LL+1, NCC, WORK( NM12+1 ),
640
$ WORK( NM13+1 ), C( LL, 1 ), LDC )
644
IF( ABS( E( M-1 ) ).LE.THRESH )
649
* Chase bulge from bottom to top
650
* Save cosines and sines for later singular vector updates
654
DO 130 I = M, LL + 1, -1
655
CALL DLARTG( D( I )*CS, E( I-1 ), CS, SN, R )
658
CALL DLARTG( OLDCS*R, D( I-1 )*SN, OLDCS, OLDSN, D( I ) )
660
WORK( I-LL+NM1 ) = -SN
661
WORK( I-LL+NM12 ) = OLDCS
662
WORK( I-LL+NM13 ) = -OLDSN
668
* Update singular vectors
671
$ CALL DLASR( 'L', 'V', 'B', M-LL+1, NCVT, WORK( NM12+1 ),
672
$ WORK( NM13+1 ), VT( LL, 1 ), LDVT )
674
$ CALL DLASR( 'R', 'V', 'B', NRU, M-LL+1, WORK( 1 ),
675
$ WORK( N ), U( 1, LL ), LDU )
677
$ CALL DLASR( 'L', 'V', 'B', M-LL+1, NCC, WORK( 1 ),
678
$ WORK( N ), C( LL, 1 ), LDC )
682
IF( ABS( E( LL ) ).LE.THRESH )
691
* Chase bulge from top to bottom
692
* Save cosines and sines for later singular vector updates
694
F = ( ABS( D( LL ) )-SHIFT )*
695
$ ( SIGN( ONE, D( LL ) )+SHIFT / D( LL ) )
698
CALL DLARTG( F, G, COSR, SINR, R )
701
F = COSR*D( I ) + SINR*E( I )
702
E( I ) = COSR*E( I ) - SINR*D( I )
704
D( I+1 ) = COSR*D( I+1 )
705
CALL DLARTG( F, G, COSL, SINL, R )
707
F = COSL*E( I ) + SINL*D( I+1 )
708
D( I+1 ) = COSL*D( I+1 ) - SINL*E( I )
711
E( I+1 ) = COSL*E( I+1 )
713
WORK( I-LL+1 ) = COSR
714
WORK( I-LL+1+NM1 ) = SINR
715
WORK( I-LL+1+NM12 ) = COSL
716
WORK( I-LL+1+NM13 ) = SINL
720
* Update singular vectors
723
$ CALL DLASR( 'L', 'V', 'F', M-LL+1, NCVT, WORK( 1 ),
724
$ WORK( N ), VT( LL, 1 ), LDVT )
726
$ CALL DLASR( 'R', 'V', 'F', NRU, M-LL+1, WORK( NM12+1 ),
727
$ WORK( NM13+1 ), U( 1, LL ), LDU )
729
$ CALL DLASR( 'L', 'V', 'F', M-LL+1, NCC, WORK( NM12+1 ),
730
$ WORK( NM13+1 ), C( LL, 1 ), LDC )
734
IF( ABS( E( M-1 ) ).LE.THRESH )
739
* Chase bulge from bottom to top
740
* Save cosines and sines for later singular vector updates
742
F = ( ABS( D( M ) )-SHIFT )*( SIGN( ONE, D( M ) )+SHIFT /
745
DO 150 I = M, LL + 1, -1
746
CALL DLARTG( F, G, COSR, SINR, R )
749
F = COSR*D( I ) + SINR*E( I-1 )
750
E( I-1 ) = COSR*E( I-1 ) - SINR*D( I )
752
D( I-1 ) = COSR*D( I-1 )
753
CALL DLARTG( F, G, COSL, SINL, R )
755
F = COSL*E( I-1 ) + SINL*D( I-1 )
756
D( I-1 ) = COSL*D( I-1 ) - SINL*E( I-1 )
759
E( I-2 ) = COSL*E( I-2 )
762
WORK( I-LL+NM1 ) = -SINR
763
WORK( I-LL+NM12 ) = COSL
764
WORK( I-LL+NM13 ) = -SINL
770
IF( ABS( E( LL ) ).LE.THRESH )
773
* Update singular vectors if desired
776
$ CALL DLASR( 'L', 'V', 'B', M-LL+1, NCVT, WORK( NM12+1 ),
777
$ WORK( NM13+1 ), VT( LL, 1 ), LDVT )
779
$ CALL DLASR( 'R', 'V', 'B', NRU, M-LL+1, WORK( 1 ),
780
$ WORK( N ), U( 1, LL ), LDU )
782
$ CALL DLASR( 'L', 'V', 'B', M-LL+1, NCC, WORK( 1 ),
783
$ WORK( N ), C( LL, 1 ), LDC )
787
* QR iteration finished, go back and check convergence
791
* All singular values converged, so make them positive
795
IF( D( I ).LT.ZERO ) THEN
798
* Change sign of singular vectors, if desired
801
$ CALL DSCAL( NCVT, NEGONE, VT( I, 1 ), LDVT )
805
* Sort the singular values into decreasing order (insertion sort on
806
* singular values, but only one transposition per singular vector)
810
* Scan for smallest D(I)
814
DO 180 J = 2, N + 1 - I
815
IF( D( J ).LE.SMIN ) THEN
820
IF( ISUB.NE.N+1-I ) THEN
822
* Swap singular values and vectors
824
D( ISUB ) = D( N+1-I )
827
$ CALL DSWAP( NCVT, VT( ISUB, 1 ), LDVT, VT( N+1-I, 1 ),
830
$ CALL DSWAP( NRU, U( 1, ISUB ), 1, U( 1, N+1-I ), 1 )
832
$ CALL DSWAP( NCC, C( ISUB, 1 ), LDC, C( N+1-I, 1 ), LDC )
837
* Maximum number of iterations exceeded, failure to converge