aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clapack/dlaed7.c
blob: 93a18489348f44e7b81e463f07eca059e4f4186f (plain) (blame)
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
/* dlaed7.f -- translated by f2c (version 20061008).
   You must link the resulting object file with libf2c:
	on Microsoft Windows system, link with libf2c.lib;
	on Linux or Unix systems, link with .../path/to/libf2c.a -lm
	or, if you install libf2c.a in a standard place, with -lf2c -lm
	-- in that order, at the end of the command line, as in
		cc *.o -lf2c -lm
	Source for libf2c is in /netlib/f2c/libf2c.zip, e.g.,

		http://www.netlib.org/f2c/libf2c.zip
*/

#include "f2c.h"
#include "blaswrap.h"

/* Table of constant values */

static integer c__2 = 2;
static integer c__1 = 1;
static doublereal c_b10 = 1.;
static doublereal c_b11 = 0.;
static integer c_n1 = -1;

/* Subroutine */ int dlaed7_(integer *icompq, integer *n, integer *qsiz, 
	integer *tlvls, integer *curlvl, integer *curpbm, doublereal *d__, 
	doublereal *q, integer *ldq, integer *indxq, doublereal *rho, integer 
	*cutpnt, doublereal *qstore, integer *qptr, integer *prmptr, integer *
	perm, integer *givptr, integer *givcol, doublereal *givnum, 
	doublereal *work, integer *iwork, integer *info)
{
    /* System generated locals */
    integer q_dim1, q_offset, i__1, i__2;

    /* Builtin functions */
    integer pow_ii(integer *, integer *);

    /* Local variables */
    integer i__, k, n1, n2, is, iw, iz, iq2, ptr, ldq2, indx, curr;
    extern /* Subroutine */ int dgemm_(char *, char *, integer *, integer *, 
	    integer *, doublereal *, doublereal *, integer *, doublereal *, 
	    integer *, doublereal *, doublereal *, integer *);
    integer indxc, indxp;
    extern /* Subroutine */ int dlaed8_(integer *, integer *, integer *, 
	    integer *, doublereal *, doublereal *, integer *, integer *, 
	    doublereal *, integer *, doublereal *, doublereal *, doublereal *, 
	     integer *, doublereal *, integer *, integer *, integer *, 
	    doublereal *, integer *, integer *, integer *), dlaed9_(integer *, 
	     integer *, integer *, integer *, doublereal *, doublereal *, 
	    integer *, doublereal *, doublereal *, doublereal *, doublereal *, 
	     integer *, integer *), dlaeda_(integer *, integer *, integer *, 
	    integer *, integer *, integer *, integer *, integer *, doublereal 
	    *, doublereal *, integer *, doublereal *, doublereal *, integer *)
	    ;
    integer idlmda;
    extern /* Subroutine */ int dlamrg_(integer *, integer *, doublereal *, 
	    integer *, integer *, integer *), xerbla_(char *, integer *);
    integer coltyp;


/*  -- LAPACK routine (version 3.2) -- */
/*     Univ. of Tennessee, Univ. of California Berkeley and NAG Ltd.. */
/*     November 2006 */

/*     .. Scalar Arguments .. */
/*     .. */
/*     .. Array Arguments .. */
/*     .. */

/*  Purpose */
/*  ======= */

/*  DLAED7 computes the updated eigensystem of a diagonal */
/*  matrix after modification by a rank-one symmetric matrix. This */
/*  routine is used only for the eigenproblem which requires all */
/*  eigenvalues and optionally eigenvectors of a dense symmetric matrix */
/*  that has been reduced to tridiagonal form.  DLAED1 handles */
/*  the case in which all eigenvalues and eigenvectors of a symmetric */
/*  tridiagonal matrix are desired. */

/*    T = Q(in) ( D(in) + RHO * Z*Z' ) Q'(in) = Q(out) * D(out) * Q'(out) */

/*     where Z = Q'u, u is a vector of length N with ones in the */
/*     CUTPNT and CUTPNT + 1 th elements and zeros elsewhere. */

/*     The eigenvectors of the original matrix are stored in Q, and the */
/*     eigenvalues are in D.  The algorithm consists of three stages: */

/*        The first stage consists of deflating the size of the problem */
/*        when there are multiple eigenvalues or if there is a zero in */
/*        the Z vector.  For each such occurence the dimension of the */
/*        secular equation problem is reduced by one.  This stage is */
/*        performed by the routine DLAED8. */

/*        The second stage consists of calculating the updated */
/*        eigenvalues. This is done by finding the roots of the secular */
/*        equation via the routine DLAED4 (as called by DLAED9). */
/*        This routine also calculates the eigenvectors of the current */
/*        problem. */

/*        The final stage consists of computing the updated eigenvectors */
/*        directly using the updated eigenvalues.  The eigenvectors for */
/*        the current problem are multiplied with the eigenvectors from */
/*        the overall problem. */

/*  Arguments */
/*  ========= */

/*  ICOMPQ  (input) INTEGER */
/*          = 0:  Compute eigenvalues only. */
/*          = 1:  Compute eigenvectors of original dense symmetric matrix */
/*                also.  On entry, Q contains the orthogonal matrix used */
/*                to reduce the original matrix to tridiagonal form. */

/*  N      (input) INTEGER */
/*         The dimension of the symmetric tridiagonal matrix.  N >= 0. */

/*  QSIZ   (input) INTEGER */
/*         The dimension of the orthogonal matrix used to reduce */
/*         the full matrix to tridiagonal form.  QSIZ >= N if ICOMPQ = 1. */

/*  TLVLS  (input) INTEGER */
/*         The total number of merging levels in the overall divide and */
/*         conquer tree. */

/*  CURLVL (input) INTEGER */
/*         The current level in the overall merge routine, */
/*         0 <= CURLVL <= TLVLS. */

/*  CURPBM (input) INTEGER */
/*         The current problem in the current level in the overall */
/*         merge routine (counting from upper left to lower right). */

/*  D      (input/output) DOUBLE PRECISION array, dimension (N) */
/*         On entry, the eigenvalues of the rank-1-perturbed matrix. */
/*         On exit, the eigenvalues of the repaired matrix. */

/*  Q      (input/output) DOUBLE PRECISION array, dimension (LDQ, N) */
/*         On entry, the eigenvectors of the rank-1-perturbed matrix. */
/*         On exit, the eigenvectors of the repaired tridiagonal matrix. */

/*  LDQ    (input) INTEGER */
/*         The leading dimension of the array Q.  LDQ >= max(1,N). */

/*  INDXQ  (output) INTEGER array, dimension (N) */
/*         The permutation which will reintegrate the subproblem just */
/*         solved back into sorted order, i.e., D( INDXQ( I = 1, N ) ) */
/*         will be in ascending order. */

/*  RHO    (input) DOUBLE PRECISION */
/*         The subdiagonal element used to create the rank-1 */
/*         modification. */

/*  CUTPNT (input) INTEGER */
/*         Contains the location of the last eigenvalue in the leading */
/*         sub-matrix.  min(1,N) <= CUTPNT <= N. */

/*  QSTORE (input/output) DOUBLE PRECISION array, dimension (N**2+1) */
/*         Stores eigenvectors of submatrices encountered during */
/*         divide and conquer, packed together. QPTR points to */
/*         beginning of the submatrices. */

/*  QPTR   (input/output) INTEGER array, dimension (N+2) */
/*         List of indices pointing to beginning of submatrices stored */
/*         in QSTORE. The submatrices are numbered starting at the */
/*         bottom left of the divide and conquer tree, from left to */
/*         right and bottom to top. */

/*  PRMPTR (input) INTEGER array, dimension (N lg N) */
/*         Contains a list of pointers which indicate where in PERM a */
/*         level's permutation is stored.  PRMPTR(i+1) - PRMPTR(i) */
/*         indicates the size of the permutation and also the size of */
/*         the full, non-deflated problem. */

/*  PERM   (input) INTEGER array, dimension (N lg N) */
/*         Contains the permutations (from deflation and sorting) to be */
/*         applied to each eigenblock. */

/*  GIVPTR (input) INTEGER array, dimension (N lg N) */
/*         Contains a list of pointers which indicate where in GIVCOL a */
/*         level's Givens rotations are stored.  GIVPTR(i+1) - GIVPTR(i) */
/*         indicates the number of Givens rotations. */

/*  GIVCOL (input) INTEGER array, dimension (2, N lg N) */
/*         Each pair of numbers indicates a pair of columns to take place */
/*         in a Givens rotation. */

/*  GIVNUM (input) DOUBLE PRECISION array, dimension (2, N lg N) */
/*         Each number indicates the S value to be used in the */
/*         corresponding Givens rotation. */

/*  WORK   (workspace) DOUBLE PRECISION array, dimension (3*N+QSIZ*N) */

/*  IWORK  (workspace) INTEGER array, dimension (4*N) */

/*  INFO   (output) INTEGER */
/*          = 0:  successful exit. */
/*          < 0:  if INFO = -i, the i-th argument had an illegal value. */
/*          > 0:  if INFO = 1, an eigenvalue did not converge */

/*  Further Details */
/*  =============== */

/*  Based on contributions by */
/*     Jeff Rutter, Computer Science Division, University of California */
/*     at Berkeley, USA */

/*  ===================================================================== */

/*     .. Parameters .. */
/*     .. */
/*     .. Local Scalars .. */
/*     .. */
/*     .. External Subroutines .. */
/*     .. */
/*     .. Intrinsic Functions .. */
/*     .. */
/*     .. Executable Statements .. */

/*     Test the input parameters. */

    /* Parameter adjustments */
    --d__;
    q_dim1 = *ldq;
    q_offset = 1 + q_dim1;
    q -= q_offset;
    --indxq;
    --qstore;
    --qptr;
    --prmptr;
    --perm;
    --givptr;
    givcol -= 3;
    givnum -= 3;
    --work;
    --iwork;

    /* Function Body */
    *info = 0;

    if (*icompq < 0 || *icompq > 1) {
	*info = -1;
    } else if (*n < 0) {
	*info = -2;
    } else if (*icompq == 1 && *qsiz < *n) {
	*info = -4;
    } else if (*ldq < max(1,*n)) {
	*info = -9;
    } else if (min(1,*n) > *cutpnt || *n < *cutpnt) {
	*info = -12;
    }
    if (*info != 0) {
	i__1 = -(*info);
	xerbla_("DLAED7", &i__1);
	return 0;
    }

/*     Quick return if possible */

    if (*n == 0) {
	return 0;
    }

/*     The following values are for bookkeeping purposes only.  They are */
/*     integer pointers which indicate the portion of the workspace */
/*     used by a particular array in DLAED8 and DLAED9. */

    if (*icompq == 1) {
	ldq2 = *qsiz;
    } else {
	ldq2 = *n;
    }

    iz = 1;
    idlmda = iz + *n;
    iw = idlmda + *n;
    iq2 = iw + *n;
    is = iq2 + *n * ldq2;

    indx = 1;
    indxc = indx + *n;
    coltyp = indxc + *n;
    indxp = coltyp + *n;

/*     Form the z-vector which consists of the last row of Q_1 and the */
/*     first row of Q_2. */

    ptr = pow_ii(&c__2, tlvls) + 1;
    i__1 = *curlvl - 1;
    for (i__ = 1; i__ <= i__1; ++i__) {
	i__2 = *tlvls - i__;
	ptr += pow_ii(&c__2, &i__2);
/* L10: */
    }
    curr = ptr + *curpbm;
    dlaeda_(n, tlvls, curlvl, curpbm, &prmptr[1], &perm[1], &givptr[1], &
	    givcol[3], &givnum[3], &qstore[1], &qptr[1], &work[iz], &work[iz 
	    + *n], info);

/*     When solving the final problem, we no longer need the stored data, */
/*     so we will overwrite the data from this level onto the previously */
/*     used storage space. */

    if (*curlvl == *tlvls) {
	qptr[curr] = 1;
	prmptr[curr] = 1;
	givptr[curr] = 1;
    }

/*     Sort and Deflate eigenvalues. */

    dlaed8_(icompq, &k, n, qsiz, &d__[1], &q[q_offset], ldq, &indxq[1], rho, 
	    cutpnt, &work[iz], &work[idlmda], &work[iq2], &ldq2, &work[iw], &
	    perm[prmptr[curr]], &givptr[curr + 1], &givcol[(givptr[curr] << 1)
	     + 1], &givnum[(givptr[curr] << 1) + 1], &iwork[indxp], &iwork[
	    indx], info);
    prmptr[curr + 1] = prmptr[curr] + *n;
    givptr[curr + 1] += givptr[curr];

/*     Solve Secular Equation. */

    if (k != 0) {
	dlaed9_(&k, &c__1, &k, n, &d__[1], &work[is], &k, rho, &work[idlmda], 
		&work[iw], &qstore[qptr[curr]], &k, info);
	if (*info != 0) {
	    goto L30;
	}
	if (*icompq == 1) {
	    dgemm_("N", "N", qsiz, &k, &k, &c_b10, &work[iq2], &ldq2, &qstore[
		    qptr[curr]], &k, &c_b11, &q[q_offset], ldq);
	}
/* Computing 2nd power */
	i__1 = k;
	qptr[curr + 1] = qptr[curr] + i__1 * i__1;

/*     Prepare the INDXQ sorting permutation. */

	n1 = k;
	n2 = *n - k;
	dlamrg_(&n1, &n2, &d__[1], &c__1, &c_n1, &indxq[1]);
    } else {
	qptr[curr + 1] = qptr[curr];
	i__1 = *n;
	for (i__ = 1; i__ <= i__1; ++i__) {
	    indxq[i__] = i__;
/* L20: */
	}
    }

L30:
    return 0;

/*     End of DLAED7 */

} /* dlaed7_ */