aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clapack/dlatrd.c
blob: 6d07750611cb0371c38b183566d1c9060282c805 (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
355
/* dlatrd.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 doublereal c_b5 = -1.;
static doublereal c_b6 = 1.;
static integer c__1 = 1;
static doublereal c_b16 = 0.;

/* Subroutine */ int dlatrd_(char *uplo, integer *n, integer *nb, doublereal *
	a, integer *lda, doublereal *e, doublereal *tau, doublereal *w, 
	integer *ldw)
{
    /* System generated locals */
    integer a_dim1, a_offset, w_dim1, w_offset, i__1, i__2, i__3;

    /* Local variables */
    integer i__, iw;
    extern doublereal ddot_(integer *, doublereal *, integer *, doublereal *, 
	    integer *);
    doublereal alpha;
    extern /* Subroutine */ int dscal_(integer *, doublereal *, doublereal *, 
	    integer *);
    extern logical lsame_(char *, char *);
    extern /* Subroutine */ int dgemv_(char *, integer *, integer *, 
	    doublereal *, doublereal *, integer *, doublereal *, integer *, 
	    doublereal *, doublereal *, integer *), daxpy_(integer *, 
	    doublereal *, doublereal *, integer *, doublereal *, integer *), 
	    dsymv_(char *, integer *, doublereal *, doublereal *, integer *, 
	    doublereal *, integer *, doublereal *, doublereal *, integer *), dlarfg_(integer *, doublereal *, doublereal *, integer *, 
	     doublereal *);


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

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

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

/*  DLATRD reduces NB rows and columns of a real symmetric matrix A to */
/*  symmetric tridiagonal form by an orthogonal similarity */
/*  transformation Q' * A * Q, and returns the matrices V and W which are */
/*  needed to apply the transformation to the unreduced part of A. */

/*  If UPLO = 'U', DLATRD reduces the last NB rows and columns of a */
/*  matrix, of which the upper triangle is supplied; */
/*  if UPLO = 'L', DLATRD reduces the first NB rows and columns of a */
/*  matrix, of which the lower triangle is supplied. */

/*  This is an auxiliary routine called by DSYTRD. */

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

/*  UPLO    (input) CHARACTER*1 */
/*          Specifies whether the upper or lower triangular part of the */
/*          symmetric matrix A is stored: */
/*          = 'U': Upper triangular */
/*          = 'L': Lower triangular */

/*  N       (input) INTEGER */
/*          The order of the matrix A. */

/*  NB      (input) INTEGER */
/*          The number of rows and columns to be reduced. */

/*  A       (input/output) DOUBLE PRECISION array, dimension (LDA,N) */
/*          On entry, the symmetric 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. */
/*          On exit: */
/*          if UPLO = 'U', the last NB columns have been reduced to */
/*            tridiagonal form, with the diagonal elements overwriting */
/*            the diagonal elements of A; the elements above the diagonal */
/*            with the array TAU, represent the orthogonal matrix Q as a */
/*            product of elementary reflectors; */
/*          if UPLO = 'L', the first NB columns have been reduced to */
/*            tridiagonal form, with the diagonal elements overwriting */
/*            the diagonal elements of A; the elements below the diagonal */
/*            with the array TAU, represent the  orthogonal matrix Q as a */
/*            product of elementary reflectors. */
/*          See Further Details. */

/*  LDA     (input) INTEGER */
/*          The leading dimension of the array A.  LDA >= (1,N). */

/*  E       (output) DOUBLE PRECISION array, dimension (N-1) */
/*          If UPLO = 'U', E(n-nb:n-1) contains the superdiagonal */
/*          elements of the last NB columns of the reduced matrix; */
/*          if UPLO = 'L', E(1:nb) contains the subdiagonal elements of */
/*          the first NB columns of the reduced matrix. */

/*  TAU     (output) DOUBLE PRECISION array, dimension (N-1) */
/*          The scalar factors of the elementary reflectors, stored in */
/*          TAU(n-nb:n-1) if UPLO = 'U', and in TAU(1:nb) if UPLO = 'L'. */
/*          See Further Details. */

/*  W       (output) DOUBLE PRECISION array, dimension (LDW,NB) */
/*          The n-by-nb matrix W required to update the unreduced part */
/*          of A. */

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

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

/*  If UPLO = 'U', the matrix Q is represented as a product of elementary */
/*  reflectors */

/*     Q = H(n) H(n-1) . . . H(n-nb+1). */

/*  Each H(i) has the form */

/*     H(i) = I - tau * v * v' */

/*  where tau is a real scalar, and v is a real vector with */
/*  v(i:n) = 0 and v(i-1) = 1; v(1:i-1) is stored on exit in A(1:i-1,i), */
/*  and tau in TAU(i-1). */

/*  If UPLO = 'L', the matrix Q is represented as a product of elementary */
/*  reflectors */

/*     Q = H(1) H(2) . . . H(nb). */

/*  Each H(i) has the form */

/*     H(i) = I - tau * v * v' */

/*  where tau is a real scalar, and v is a real vector with */
/*  v(1:i) = 0 and v(i+1) = 1; v(i+1:n) is stored on exit in A(i+1:n,i), */
/*  and tau in TAU(i). */

/*  The elements of the vectors v together form the n-by-nb matrix V */
/*  which is needed, with W, to apply the transformation to the unreduced */
/*  part of the matrix, using a symmetric rank-2k update of the form: */
/*  A := A - V*W' - W*V'. */

/*  The contents of A on exit are illustrated by the following examples */
/*  with n = 5 and nb = 2: */

/*  if UPLO = 'U':                       if UPLO = 'L': */

/*    (  a   a   a   v4  v5 )              (  d                  ) */
/*    (      a   a   v4  v5 )              (  1   d              ) */
/*    (          a   1   v5 )              (  v1  1   a          ) */
/*    (              d   1  )              (  v1  v2  a   a      ) */
/*    (                  d  )              (  v1  v2  a   a   a  ) */

/*  where d denotes a diagonal element of the reduced matrix, a denotes */
/*  an element of the original matrix that is unchanged, and vi denotes */
/*  an element of the vector defining H(i). */

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

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

/*     Quick return if possible */

    /* Parameter adjustments */
    a_dim1 = *lda;
    a_offset = 1 + a_dim1;
    a -= a_offset;
    --e;
    --tau;
    w_dim1 = *ldw;
    w_offset = 1 + w_dim1;
    w -= w_offset;

    /* Function Body */
    if (*n <= 0) {
	return 0;
    }

    if (lsame_(uplo, "U")) {

/*        Reduce last NB columns of upper triangle */

	i__1 = *n - *nb + 1;
	for (i__ = *n; i__ >= i__1; --i__) {
	    iw = i__ - *n + *nb;
	    if (i__ < *n) {

/*              Update A(1:i,i) */

		i__2 = *n - i__;
		dgemv_("No transpose", &i__, &i__2, &c_b5, &a[(i__ + 1) * 
			a_dim1 + 1], lda, &w[i__ + (iw + 1) * w_dim1], ldw, &
			c_b6, &a[i__ * a_dim1 + 1], &c__1);
		i__2 = *n - i__;
		dgemv_("No transpose", &i__, &i__2, &c_b5, &w[(iw + 1) * 
			w_dim1 + 1], ldw, &a[i__ + (i__ + 1) * a_dim1], lda, &
			c_b6, &a[i__ * a_dim1 + 1], &c__1);
	    }
	    if (i__ > 1) {

/*              Generate elementary reflector H(i) to annihilate */
/*              A(1:i-2,i) */

		i__2 = i__ - 1;
		dlarfg_(&i__2, &a[i__ - 1 + i__ * a_dim1], &a[i__ * a_dim1 + 
			1], &c__1, &tau[i__ - 1]);
		e[i__ - 1] = a[i__ - 1 + i__ * a_dim1];
		a[i__ - 1 + i__ * a_dim1] = 1.;

/*              Compute W(1:i-1,i) */

		i__2 = i__ - 1;
		dsymv_("Upper", &i__2, &c_b6, &a[a_offset], lda, &a[i__ * 
			a_dim1 + 1], &c__1, &c_b16, &w[iw * w_dim1 + 1], &
			c__1);
		if (i__ < *n) {
		    i__2 = i__ - 1;
		    i__3 = *n - i__;
		    dgemv_("Transpose", &i__2, &i__3, &c_b6, &w[(iw + 1) * 
			    w_dim1 + 1], ldw, &a[i__ * a_dim1 + 1], &c__1, &
			    c_b16, &w[i__ + 1 + iw * w_dim1], &c__1);
		    i__2 = i__ - 1;
		    i__3 = *n - i__;
		    dgemv_("No transpose", &i__2, &i__3, &c_b5, &a[(i__ + 1) *
			     a_dim1 + 1], lda, &w[i__ + 1 + iw * w_dim1], &
			    c__1, &c_b6, &w[iw * w_dim1 + 1], &c__1);
		    i__2 = i__ - 1;
		    i__3 = *n - i__;
		    dgemv_("Transpose", &i__2, &i__3, &c_b6, &a[(i__ + 1) * 
			    a_dim1 + 1], lda, &a[i__ * a_dim1 + 1], &c__1, &
			    c_b16, &w[i__ + 1 + iw * w_dim1], &c__1);
		    i__2 = i__ - 1;
		    i__3 = *n - i__;
		    dgemv_("No transpose", &i__2, &i__3, &c_b5, &w[(iw + 1) * 
			    w_dim1 + 1], ldw, &w[i__ + 1 + iw * w_dim1], &
			    c__1, &c_b6, &w[iw * w_dim1 + 1], &c__1);
		}
		i__2 = i__ - 1;
		dscal_(&i__2, &tau[i__ - 1], &w[iw * w_dim1 + 1], &c__1);
		i__2 = i__ - 1;
		alpha = tau[i__ - 1] * -.5 * ddot_(&i__2, &w[iw * w_dim1 + 1], 
			 &c__1, &a[i__ * a_dim1 + 1], &c__1);
		i__2 = i__ - 1;
		daxpy_(&i__2, &alpha, &a[i__ * a_dim1 + 1], &c__1, &w[iw * 
			w_dim1 + 1], &c__1);
	    }

/* L10: */
	}
    } else {

/*        Reduce first NB columns of lower triangle */

	i__1 = *nb;
	for (i__ = 1; i__ <= i__1; ++i__) {

/*           Update A(i:n,i) */

	    i__2 = *n - i__ + 1;
	    i__3 = i__ - 1;
	    dgemv_("No transpose", &i__2, &i__3, &c_b5, &a[i__ + a_dim1], lda, 
		     &w[i__ + w_dim1], ldw, &c_b6, &a[i__ + i__ * a_dim1], &
		    c__1);
	    i__2 = *n - i__ + 1;
	    i__3 = i__ - 1;
	    dgemv_("No transpose", &i__2, &i__3, &c_b5, &w[i__ + w_dim1], ldw, 
		     &a[i__ + a_dim1], lda, &c_b6, &a[i__ + i__ * a_dim1], &
		    c__1);
	    if (i__ < *n) {

/*              Generate elementary reflector H(i) to annihilate */
/*              A(i+2:n,i) */

		i__2 = *n - i__;
/* Computing MIN */
		i__3 = i__ + 2;
		dlarfg_(&i__2, &a[i__ + 1 + i__ * a_dim1], &a[min(i__3, *n)+ 
			i__ * a_dim1], &c__1, &tau[i__]);
		e[i__] = a[i__ + 1 + i__ * a_dim1];
		a[i__ + 1 + i__ * a_dim1] = 1.;

/*              Compute W(i+1:n,i) */

		i__2 = *n - i__;
		dsymv_("Lower", &i__2, &c_b6, &a[i__ + 1 + (i__ + 1) * a_dim1]
, lda, &a[i__ + 1 + i__ * a_dim1], &c__1, &c_b16, &w[
			i__ + 1 + i__ * w_dim1], &c__1);
		i__2 = *n - i__;
		i__3 = i__ - 1;
		dgemv_("Transpose", &i__2, &i__3, &c_b6, &w[i__ + 1 + w_dim1], 
			 ldw, &a[i__ + 1 + i__ * a_dim1], &c__1, &c_b16, &w[
			i__ * w_dim1 + 1], &c__1);
		i__2 = *n - i__;
		i__3 = i__ - 1;
		dgemv_("No transpose", &i__2, &i__3, &c_b5, &a[i__ + 1 + 
			a_dim1], lda, &w[i__ * w_dim1 + 1], &c__1, &c_b6, &w[
			i__ + 1 + i__ * w_dim1], &c__1);
		i__2 = *n - i__;
		i__3 = i__ - 1;
		dgemv_("Transpose", &i__2, &i__3, &c_b6, &a[i__ + 1 + a_dim1], 
			 lda, &a[i__ + 1 + i__ * a_dim1], &c__1, &c_b16, &w[
			i__ * w_dim1 + 1], &c__1);
		i__2 = *n - i__;
		i__3 = i__ - 1;
		dgemv_("No transpose", &i__2, &i__3, &c_b5, &w[i__ + 1 + 
			w_dim1], ldw, &w[i__ * w_dim1 + 1], &c__1, &c_b6, &w[
			i__ + 1 + i__ * w_dim1], &c__1);
		i__2 = *n - i__;
		dscal_(&i__2, &tau[i__], &w[i__ + 1 + i__ * w_dim1], &c__1);
		i__2 = *n - i__;
		alpha = tau[i__] * -.5 * ddot_(&i__2, &w[i__ + 1 + i__ * 
			w_dim1], &c__1, &a[i__ + 1 + i__ * a_dim1], &c__1);
		i__2 = *n - i__;
		daxpy_(&i__2, &alpha, &a[i__ + 1 + i__ * a_dim1], &c__1, &w[
			i__ + 1 + i__ * w_dim1], &c__1);
	    }

/* L20: */
	}
    }

    return 0;

/*     End of DLATRD */

} /* dlatrd_ */