summaryrefslogtreecommitdiff
path: root/SRC/zcposv.f
blob: 3159c3dd987851e77f500ea080ee77e8e91a1ce5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
*> \brief <b> ZCPOSV computes the solution to system of linear equations A * X = B for PO matrices</b>
*
*  =========== DOCUMENTATION ===========
*
* Online html documentation available at
*            http://www.netlib.org/lapack/explore-html/
*
*> \htmlonly
*> Download ZCPOSV + dependencies
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/zcposv.f">
*> [TGZ]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/zcposv.f">
*> [ZIP]</a>
*> <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/zcposv.f">
*> [TXT]</a>
*> \endhtmlonly
*
*  Definition:
*  ===========
*
*       SUBROUTINE ZCPOSV( UPLO, N, NRHS, A, LDA, B, LDB, X, LDX, WORK,
*                          SWORK, RWORK, ITER, INFO )
*
*       .. Scalar Arguments ..
*       CHARACTER          UPLO
*       INTEGER            INFO, ITER, LDA, LDB, LDX, N, NRHS
*       ..
*       .. Array Arguments ..
*       DOUBLE PRECISION   RWORK( * )
*       COMPLEX            SWORK( * )
*       COMPLEX*16         A( LDA, * ), B( LDB, * ), WORK( N, * ),
*      $                   X( LDX, * )
*       ..
*
*
*> \par Purpose:
*  =============
*>
*> \verbatim
*>
*> ZCPOSV computes the solution to a complex system of linear equations
*>    A * X = B,
*> where A is an N-by-N Hermitian positive definite matrix and X and B
*> are N-by-NRHS matrices.
*>
*> ZCPOSV first attempts to factorize the matrix in COMPLEX and use this
*> factorization within an iterative refinement procedure to produce a
*> solution with COMPLEX*16 normwise backward error quality (see below).
*> If the approach fails the method switches to a COMPLEX*16
*> factorization and solve.
*>
*> The iterative refinement is not going to be a winning strategy if
*> the ratio COMPLEX performance over COMPLEX*16 performance is too
*> small. A reasonable strategy should take the number of right-hand
*> sides and the size of the matrix into account. This might be done
*> with a call to ILAENV in the future. Up to now, we always try
*> iterative refinement.
*>
*> The iterative refinement process is stopped if
*>     ITER > ITERMAX
*> or for all the RHS we have:
*>     RNRM < SQRT(N)*XNRM*ANRM*EPS*BWDMAX
*> where
*>     o ITER is the number of the current iteration in the iterative
*>       refinement process
*>     o RNRM is the infinity-norm of the residual
*>     o XNRM is the infinity-norm of the solution
*>     o ANRM is the infinity-operator-norm of the matrix A
*>     o EPS is the machine epsilon returned by DLAMCH('Epsilon')
*> The value ITERMAX and BWDMAX are fixed to 30 and 1.0D+00
*> respectively.
*> \endverbatim
*
*  Arguments:
*  ==========
*
*> \param[in] UPLO
*> \verbatim
*>          UPLO is CHARACTER*1
*>          = 'U':  Upper triangle of A is stored;
*>          = 'L':  Lower triangle of A is stored.
*> \endverbatim
*>
*> \param[in] N
*> \verbatim
*>          N is INTEGER
*>          The number of linear equations, i.e., the order of the
*>          matrix A.  N >= 0.
*> \endverbatim
*>
*> \param[in] NRHS
*> \verbatim
*>          NRHS is INTEGER
*>          The number of right hand sides, i.e., the number of columns
*>          of the matrix B.  NRHS >= 0.
*> \endverbatim
*>
*> \param[in,out] A
*> \verbatim
*>          A is COMPLEX*16 array,
*>          dimension (LDA,N)
*>          On entry, the Hermitian matrix A. If UPLO = 'U', the leading
*>          N-by-N upper triangular part of A contains the upper
*>          triangular part of the matrix A, and the strictly lower
*>          triangular part of A is not referenced.  If UPLO = 'L', the
*>          leading N-by-N lower triangular part of A contains the lower
*>          triangular part of the matrix A, and the strictly upper
*>          triangular part of A is not referenced.
*>
*>          Note that the imaginary parts of the diagonal
*>          elements need not be set and are assumed to be zero.
*>
*>          On exit, if iterative refinement has been successfully used
*>          (INFO.EQ.0 and ITER.GE.0, see description below), then A is
*>          unchanged, if double precision factorization has been used
*>          (INFO.EQ.0 and ITER.LT.0, see description below), then the
*>          array A contains the factor U or L from the Cholesky
*>          factorization A = U**H*U or A = L*L**H.
*> \endverbatim
*>
*> \param[in] LDA
*> \verbatim
*>          LDA is INTEGER
*>          The leading dimension of the array A.  LDA >= max(1,N).
*> \endverbatim
*>
*> \param[in] B
*> \verbatim
*>          B is COMPLEX*16 array, dimension (LDB,NRHS)
*>          The N-by-NRHS right hand side matrix B.
*> \endverbatim
*>
*> \param[in] LDB
*> \verbatim
*>          LDB is INTEGER
*>          The leading dimension of the array B.  LDB >= max(1,N).
*> \endverbatim
*>
*> \param[out] X
*> \verbatim
*>          X is COMPLEX*16 array, dimension (LDX,NRHS)
*>          If INFO = 0, the N-by-NRHS solution matrix X.
*> \endverbatim
*>
*> \param[in] LDX
*> \verbatim
*>          LDX is INTEGER
*>          The leading dimension of the array X.  LDX >= max(1,N).
*> \endverbatim
*>
*> \param[out] WORK
*> \verbatim
*>          WORK is COMPLEX*16 array, dimension (N*NRHS)
*>          This array is used to hold the residual vectors.
*> \endverbatim
*>
*> \param[out] SWORK
*> \verbatim
*>          SWORK is COMPLEX array, dimension (N*(N+NRHS))
*>          This array is used to use the single precision matrix and the
*>          right-hand sides or solutions in single precision.
*> \endverbatim
*>
*> \param[out] RWORK
*> \verbatim
*>          RWORK is DOUBLE PRECISION array, dimension (N)
*> \endverbatim
*>
*> \param[out] ITER
*> \verbatim
*>          ITER is INTEGER
*>          < 0: iterative refinement has failed, COMPLEX*16
*>               factorization has been performed
*>               -1 : the routine fell back to full precision for
*>                    implementation- or machine-specific reasons
*>               -2 : narrowing the precision induced an overflow,
*>                    the routine fell back to full precision
*>               -3 : failure of CPOTRF
*>               -31: stop the iterative refinement after the 30th
*>                    iterations
*>          > 0: iterative refinement has been successfully used.
*>               Returns the number of iterations
*> \endverbatim
*>
*> \param[out] INFO
*> \verbatim
*>          INFO is INTEGER
*>          = 0:  successful exit
*>          < 0:  if INFO = -i, the i-th argument had an illegal value
*>          > 0:  if INFO = i, the leading minor of order i of
*>                (COMPLEX*16) A is not positive definite, so the
*>                factorization could not be completed, and the solution
*>                has not been computed.
*> \endverbatim
*
*  Authors:
*  ========
*
*> \author Univ. of Tennessee
*> \author Univ. of California Berkeley
*> \author Univ. of Colorado Denver
*> \author NAG Ltd.
*
*> \date June 2016
*
*> \ingroup complex16POsolve
*
*  =====================================================================
      SUBROUTINE ZCPOSV( UPLO, N, NRHS, A, LDA, B, LDB, X, LDX, WORK,
     $                   SWORK, RWORK, ITER, INFO )
*
*  -- LAPACK driver routine (version 3.7.0) --
*  -- LAPACK is a software package provided by Univ. of Tennessee,    --
*  -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..--
*     June 2016
*
*     .. Scalar Arguments ..
      CHARACTER          UPLO
      INTEGER            INFO, ITER, LDA, LDB, LDX, N, NRHS
*     ..
*     .. Array Arguments ..
      DOUBLE PRECISION   RWORK( * )
      COMPLEX            SWORK( * )
      COMPLEX*16         A( LDA, * ), B( LDB, * ), WORK( N, * ),
     $                   X( LDX, * )
*     ..
*
*  =====================================================================
*
*     .. Parameters ..
      LOGICAL            DOITREF
      PARAMETER          ( DOITREF = .TRUE. )
*
      INTEGER            ITERMAX
      PARAMETER          ( ITERMAX = 30 )
*
      DOUBLE PRECISION   BWDMAX
      PARAMETER          ( BWDMAX = 1.0E+00 )
*
      COMPLEX*16         NEGONE, ONE
      PARAMETER          ( NEGONE = ( -1.0D+00, 0.0D+00 ),
     $                   ONE = ( 1.0D+00, 0.0D+00 ) )
*
*     .. Local Scalars ..
      INTEGER            I, IITER, PTSA, PTSX
      DOUBLE PRECISION   ANRM, CTE, EPS, RNRM, XNRM
      COMPLEX*16         ZDUM
*
*     .. External Subroutines ..
      EXTERNAL           ZAXPY, ZHEMM, ZLACPY, ZLAT2C, ZLAG2C, CLAG2Z,
     $                   CPOTRF, CPOTRS, XERBLA
*     ..
*     .. External Functions ..
      INTEGER            IZAMAX
      DOUBLE PRECISION   DLAMCH, ZLANHE
      LOGICAL            LSAME
      EXTERNAL           IZAMAX, DLAMCH, ZLANHE, LSAME
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          ABS, DBLE, MAX, SQRT
*     .. Statement Functions ..
      DOUBLE PRECISION   CABS1
*     ..
*     .. Statement Function definitions ..
      CABS1( ZDUM ) = ABS( DBLE( ZDUM ) ) + ABS( DIMAG( ZDUM ) )
*     ..
*     .. Executable Statements ..
*
      INFO = 0
      ITER = 0
*
*     Test the input parameters.
*
      IF( .NOT.LSAME( UPLO, 'U' ) .AND. .NOT.LSAME( UPLO, 'L' ) ) THEN
         INFO = -1
      ELSE IF( N.LT.0 ) THEN
         INFO = -2
      ELSE IF( NRHS.LT.0 ) THEN
         INFO = -3
      ELSE IF( LDA.LT.MAX( 1, N ) ) THEN
         INFO = -5
      ELSE IF( LDB.LT.MAX( 1, N ) ) THEN
         INFO = -7
      ELSE IF( LDX.LT.MAX( 1, N ) ) THEN
         INFO = -9
      END IF
      IF( INFO.NE.0 ) THEN
         CALL XERBLA( 'ZCPOSV', -INFO )
         RETURN
      END IF
*
*     Quick return if (N.EQ.0).
*
      IF( N.EQ.0 )
     $   RETURN
*
*     Skip single precision iterative refinement if a priori slower
*     than double precision factorization.
*
      IF( .NOT.DOITREF ) THEN
         ITER = -1
         GO TO 40
      END IF
*
*     Compute some constants.
*
      ANRM = ZLANHE( 'I', UPLO, N, A, LDA, RWORK )
      EPS = DLAMCH( 'Epsilon' )
      CTE = ANRM*EPS*SQRT( DBLE( N ) )*BWDMAX
*
*     Set the indices PTSA, PTSX for referencing SA and SX in SWORK.
*
      PTSA = 1
      PTSX = PTSA + N*N
*
*     Convert B from double precision to single precision and store the
*     result in SX.
*
      CALL ZLAG2C( N, NRHS, B, LDB, SWORK( PTSX ), N, INFO )
*
      IF( INFO.NE.0 ) THEN
         ITER = -2
         GO TO 40
      END IF
*
*     Convert A from double precision to single precision and store the
*     result in SA.
*
      CALL ZLAT2C( UPLO, N, A, LDA, SWORK( PTSA ), N, INFO )
*
      IF( INFO.NE.0 ) THEN
         ITER = -2
         GO TO 40
      END IF
*
*     Compute the Cholesky factorization of SA.
*
      CALL CPOTRF( UPLO, N, SWORK( PTSA ), N, INFO )
*
      IF( INFO.NE.0 ) THEN
         ITER = -3
         GO TO 40
      END IF
*
*     Solve the system SA*SX = SB.
*
      CALL CPOTRS( UPLO, N, NRHS, SWORK( PTSA ), N, SWORK( PTSX ), N,
     $             INFO )
*
*     Convert SX back to COMPLEX*16
*
      CALL CLAG2Z( N, NRHS, SWORK( PTSX ), N, X, LDX, INFO )
*
*     Compute R = B - AX (R is WORK).
*
      CALL ZLACPY( 'All', N, NRHS, B, LDB, WORK, N )
*
      CALL ZHEMM( 'Left', UPLO, N, NRHS, NEGONE, A, LDA, X, LDX, ONE,
     $            WORK, N )
*
*     Check whether the NRHS normwise backward errors satisfy the
*     stopping criterion. If yes, set ITER=0 and return.
*
      DO I = 1, NRHS
         XNRM = CABS1( X( IZAMAX( N, X( 1, I ), 1 ), I ) )
         RNRM = CABS1( WORK( IZAMAX( N, WORK( 1, I ), 1 ), I ) )
         IF( RNRM.GT.XNRM*CTE )
     $      GO TO 10
      END DO
*
*     If we are here, the NRHS normwise backward errors satisfy the
*     stopping criterion. We are good to exit.
*
      ITER = 0
      RETURN
*
   10 CONTINUE
*
      DO 30 IITER = 1, ITERMAX
*
*        Convert R (in WORK) from double precision to single precision
*        and store the result in SX.
*
         CALL ZLAG2C( N, NRHS, WORK, N, SWORK( PTSX ), N, INFO )
*
         IF( INFO.NE.0 ) THEN
            ITER = -2
            GO TO 40
         END IF
*
*        Solve the system SA*SX = SR.
*
         CALL CPOTRS( UPLO, N, NRHS, SWORK( PTSA ), N, SWORK( PTSX ), N,
     $                INFO )
*
*        Convert SX back to double precision and update the current
*        iterate.
*
         CALL CLAG2Z( N, NRHS, SWORK( PTSX ), N, WORK, N, INFO )
*
         DO I = 1, NRHS
            CALL ZAXPY( N, ONE, WORK( 1, I ), 1, X( 1, I ), 1 )
         END DO
*
*        Compute R = B - AX (R is WORK).
*
         CALL ZLACPY( 'All', N, NRHS, B, LDB, WORK, N )
*
         CALL ZHEMM( 'L', UPLO, N, NRHS, NEGONE, A, LDA, X, LDX, ONE,
     $               WORK, N )
*
*        Check whether the NRHS normwise backward errors satisfy the
*        stopping criterion. If yes, set ITER=IITER>0 and return.
*
         DO I = 1, NRHS
            XNRM = CABS1( X( IZAMAX( N, X( 1, I ), 1 ), I ) )
            RNRM = CABS1( WORK( IZAMAX( N, WORK( 1, I ), 1 ), I ) )
            IF( RNRM.GT.XNRM*CTE )
     $         GO TO 20
         END DO
*
*        If we are here, the NRHS normwise backward errors satisfy the
*        stopping criterion, we are good to exit.
*
         ITER = IITER
*
         RETURN
*
   20    CONTINUE
*
   30 CONTINUE
*
*     If we are at this place of the code, this is because we have
*     performed ITER=ITERMAX iterations and never satisified the
*     stopping criterion, set up the ITER flag accordingly and follow
*     up on double precision routine.
*
      ITER = -ITERMAX - 1
*
   40 CONTINUE
*
*     Single-precision iterative refinement failed to converge to a
*     satisfactory solution, so we resort to double precision.
*
      CALL ZPOTRF( UPLO, N, A, LDA, INFO )
*
      IF( INFO.NE.0 )
     $   RETURN
*
      CALL ZLACPY( 'All', N, NRHS, B, LDB, X, LDX )
      CALL ZPOTRS( UPLO, N, NRHS, A, LDA, X, LDX, INFO )
*
      RETURN
*
*     End of ZCPOSV.
*
      END