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
|
SUBROUTINE PSGEBRD( M, N, A, IA, JA, DESCA, D, E, TAUQ, TAUP,
$ WORK, LWORK, INFO )
*
* -- ScaLAPACK routine (version 1.7) --
* University of Tennessee, Knoxville, Oak Ridge National Laboratory,
* and University of California, Berkeley.
* May 25, 2001
*
* .. Scalar Arguments ..
INTEGER IA, INFO, JA, LWORK, M, N
* ..
* .. Array Arguments ..
INTEGER DESCA( * )
REAL A( * ), D( * ), E( * ), TAUP( * ), TAUQ( * ),
$ WORK( * )
* ..
*
* Purpose
* =======
*
* PSGEBRD reduces a real general M-by-N distributed matrix
* sub( A ) = A(IA:IA+M-1,JA:JA+N-1) to upper or lower bidiagonal
* form B by an orthogonal transformation: Q' * sub( A ) * P = B.
*
* If M >= N, B is upper bidiagonal; if M < N, B is lower bidiagonal.
*
* Notes
* =====
*
* Each global data object is described by an associated description
* vector. This vector stores the information required to establish
* the mapping between an object element and its corresponding process
* and memory location.
*
* Let A be a generic term for any 2D block cyclicly distributed array.
* Such a global array has an associated description vector DESCA.
* In the following comments, the character _ should be read as
* "of the global array".
*
* NOTATION STORED IN EXPLANATION
* --------------- -------------- --------------------------------------
* DTYPE_A(global) DESCA( DTYPE_ )The descriptor type. In this case,
* DTYPE_A = 1.
* CTXT_A (global) DESCA( CTXT_ ) The BLACS context handle, indicating
* the BLACS process grid A is distribu-
* ted over. The context itself is glo-
* bal, but the handle (the integer
* value) may vary.
* M_A (global) DESCA( M_ ) The number of rows in the global
* array A.
* N_A (global) DESCA( N_ ) The number of columns in the global
* array A.
* MB_A (global) DESCA( MB_ ) The blocking factor used to distribute
* the rows of the array.
* NB_A (global) DESCA( NB_ ) The blocking factor used to distribute
* the columns of the array.
* RSRC_A (global) DESCA( RSRC_ ) The process row over which the first
* row of the array A is distributed.
* CSRC_A (global) DESCA( CSRC_ ) The process column over which the
* first column of the array A is
* distributed.
* LLD_A (local) DESCA( LLD_ ) The leading dimension of the local
* array. LLD_A >= MAX(1,LOCr(M_A)).
*
* Let K be the number of rows or columns of a distributed matrix,
* and assume that its process grid has dimension p x q.
* LOCr( K ) denotes the number of elements of K that a process
* would receive if K were distributed over the p processes of its
* process column.
* Similarly, LOCc( K ) denotes the number of elements of K that a
* process would receive if K were distributed over the q processes of
* its process row.
* The values of LOCr() and LOCc() may be determined via a call to the
* ScaLAPACK tool function, NUMROC:
* LOCr( M ) = NUMROC( M, MB_A, MYROW, RSRC_A, NPROW ),
* LOCc( N ) = NUMROC( N, NB_A, MYCOL, CSRC_A, NPCOL ).
* An upper bound for these quantities may be computed by:
* LOCr( M ) <= ceil( ceil(M/MB_A)/NPROW )*MB_A
* LOCc( N ) <= ceil( ceil(N/NB_A)/NPCOL )*NB_A
*
* Arguments
* =========
*
* M (global input) INTEGER
* The number of rows to be operated on, i.e. the number of rows
* of the distributed submatrix sub( A ). M >= 0.
*
* N (global input) INTEGER
* The number of columns to be operated on, i.e. the number of
* columns of the distributed submatrix sub( A ). N >= 0.
*
* A (local input/local output) REAL pointer into the
* local memory to an array of dimension (LLD_A,LOCc(JA+N-1)).
* On entry, this array contains the local pieces of the
* general distributed matrix sub( A ). On exit, if M >= N,
* the diagonal and the first superdiagonal of sub( A ) are
* overwritten with the upper bidiagonal matrix B; the elements
* below the diagonal, with the array TAUQ, represent the
* orthogonal matrix Q as a product of elementary reflectors,
* and the elements above the first superdiagonal, with the
* array TAUP, represent the orthogonal matrix P as a product
* of elementary reflectors. If M < N, the diagonal and the
* first subdiagonal are overwritten with the lower bidiagonal
* matrix B; the elements below the first subdiagonal, with the
* array TAUQ, represent the orthogonal matrix Q as a product of
* elementary reflectors, and the elements above the diagonal,
* with the array TAUP, represent the orthogonal matrix P as a
* product of elementary reflectors. See Further Details.
*
* IA (global input) INTEGER
* The row index in the global array A indicating the first
* row of sub( A ).
*
* JA (global input) INTEGER
* The column index in the global array A indicating the
* first column of sub( A ).
*
* DESCA (global and local input) INTEGER array of dimension DLEN_.
* The array descriptor for the distributed matrix A.
*
* D (local output) REAL array, dimension
* LOCc(JA+MIN(M,N)-1) if M >= N; LOCr(IA+MIN(M,N)-1) otherwise.
* The distributed diagonal elements of the bidiagonal matrix
* B: D(i) = A(i,i). D is tied to the distributed matrix A.
*
* E (local output) REAL array, dimension
* LOCr(IA+MIN(M,N)-1) if M >= N; LOCc(JA+MIN(M,N)-2) otherwise.
* The distributed off-diagonal elements of the bidiagonal
* distributed matrix B:
* if m >= n, E(i) = A(i,i+1) for i = 1,2,...,n-1;
* if m < n, E(i) = A(i+1,i) for i = 1,2,...,m-1.
* E is tied to the distributed matrix A.
*
* TAUQ (local output) REAL array dimension
* LOCc(JA+MIN(M,N)-1). The scalar factors of the elementary
* reflectors which represent the orthogonal matrix Q. TAUQ
* is tied to the distributed matrix A. See Further Details.
*
* TAUP (local output) REAL array, dimension
* LOCr(IA+MIN(M,N)-1). The scalar factors of the elementary
* reflectors which represent the orthogonal matrix P. TAUP
* is tied to the distributed matrix A. See Further Details.
*
* WORK (local workspace/local output) REAL array,
* dimension (LWORK)
* On exit, WORK( 1 ) returns the minimal and optimal LWORK.
*
* LWORK (local or global input) INTEGER
* The dimension of the array WORK.
* LWORK is local input and must be at least
* LWORK >= NB*( MpA0 + NqA0 + 1 ) + NqA0
*
* where NB = MB_A = NB_A,
* IROFFA = MOD( IA-1, NB ), ICOFFA = MOD( JA-1, NB ),
* IAROW = INDXG2P( IA, NB, MYROW, RSRC_A, NPROW ),
* IACOL = INDXG2P( JA, NB, MYCOL, CSRC_A, NPCOL ),
* MpA0 = NUMROC( M+IROFFA, NB, MYROW, IAROW, NPROW ),
* NqA0 = NUMROC( N+ICOFFA, NB, MYCOL, IACOL, NPCOL ).
*
* INDXG2P and NUMROC are ScaLAPACK tool functions;
* MYROW, MYCOL, NPROW and NPCOL can be determined by calling
* the subroutine BLACS_GRIDINFO.
*
* If LWORK = -1, then LWORK is global input and a workspace
* query is assumed; the routine only calculates the minimum
* and optimal size for all work arrays. Each of these
* values is returned in the first entry of the corresponding
* work array, and no error message is issued by PXERBLA.
*
* INFO (global output) INTEGER
* = 0: successful exit
* < 0: If the i-th argument is an array and the j-entry had
* an illegal value, then INFO = -(i*100+j), if the i-th
* argument is a scalar and had an illegal value, then
* INFO = -i.
*
* Further Details
* ===============
*
* The matrices Q and P are represented as products of elementary
* reflectors:
*
* If m >= n,
*
* Q = H(1) H(2) . . . H(n) and P = G(1) G(2) . . . G(n-1)
*
* Each H(i) and G(i) has the form:
*
* H(i) = I - tauq * v * v' and G(i) = I - taup * u * u'
*
* where tauq and taup are real scalars, and v and u are real vectors;
* v(1:i-1) = 0, v(i) = 1, and v(i+1:m) is stored on exit in
* A(ia+i:ia+m-1,ja+i-1);
* u(1:i) = 0, u(i+1) = 1, and u(i+2:n) is stored on exit in
* A(ia+i-1,ja+i+1:ja+n-1);
* tauq is stored in TAUQ(ja+i-1) and taup in TAUP(ia+i-1).
*
* If m < n,
*
* Q = H(1) H(2) . . . H(m-1) and P = G(1) G(2) . . . G(m)
*
* Each H(i) and G(i) has the form:
*
* H(i) = I - tauq * v * v' and G(i) = I - taup * u * u'
*
* where tauq and taup are real scalars, and v and u are real vectors;
* v(1:i) = 0, v(i+1) = 1, and v(i+2:m) is stored on exit in
* A(ia+i+1:ia+m-1,ja+i-1);
* u(1:i-1) = 0, u(i) = 1, and u(i+1:n) is stored on exit in
* A(ia+i-1,ja+i:ja+n-1);
* tauq is stored in TAUQ(ja+i-1) and taup in TAUP(ia+i-1).
*
* The contents of sub( A ) on exit are illustrated by the following
* examples:
*
* m = 6 and n = 5 (m > n): m = 5 and n = 6 (m < n):
*
* ( d e u1 u1 u1 ) ( d u1 u1 u1 u1 u1 )
* ( v1 d e u2 u2 ) ( e d u2 u2 u2 u2 )
* ( v1 v2 d e u3 ) ( v1 e d u3 u3 u3 )
* ( v1 v2 v3 d e ) ( v1 v2 e d u4 u4 )
* ( v1 v2 v3 v4 d ) ( v1 v2 v3 e d u5 )
* ( v1 v2 v3 v4 v5 )
*
* where d and e denote diagonal and off-diagonal elements of B, vi
* denotes an element of the vector defining H(i), and ui an element of
* the vector defining G(i).
*
* Alignment requirements
* ======================
*
* The distributed submatrix sub( A ) must verify some alignment proper-
* ties, namely the following expressions should be true:
* ( MB_A.EQ.NB_A .AND. IROFFA.EQ.ICOFFA )
*
* =====================================================================
*
* .. Parameters ..
INTEGER BLOCK_CYCLIC_2D, CSRC_, CTXT_, DLEN_, DTYPE_,
$ LLD_, MB_, M_, NB_, N_, RSRC_
PARAMETER ( BLOCK_CYCLIC_2D = 1, DLEN_ = 9, DTYPE_ = 1,
$ CTXT_ = 2, M_ = 3, N_ = 4, MB_ = 5, NB_ = 6,
$ RSRC_ = 7, CSRC_ = 8, LLD_ = 9 )
REAL ONE
PARAMETER ( ONE = 1.0E+0 )
* ..
* .. Local Scalars ..
LOGICAL LQUERY
CHARACTER COLCTOP, ROWCTOP
INTEGER I, IACOL, IAROW, ICTXT, IINFO, IOFF, IPW, IPY,
$ IW, J, JB, JS, JW, K, L, LWMIN, MN, MP, MYCOL,
$ MYROW, NB, NPCOL, NPROW, NQ
* ..
* .. Local Arrays ..
INTEGER DESCWX( DLEN_ ), DESCWY( DLEN_ ), IDUM1( 1 ),
$ IDUM2( 1 )
* ..
* .. External Subroutines ..
EXTERNAL BLACS_GRIDINFO, CHK1MAT, DESCSET, PCHK1MAT,
$ PSELSET, PSGEBD2, PSGEMM, PSLABRD,
$ PB_TOPGET, PB_TOPSET, PXERBLA
* ..
* .. External Functions ..
INTEGER INDXG2L, INDXG2P, NUMROC
EXTERNAL INDXG2L, INDXG2P, NUMROC
* ..
* .. Intrinsic Functions ..
INTRINSIC MAX, MIN, MOD, REAL
* ..
* .. Executable Statements ..
*
* Get grid parameters
*
ICTXT = DESCA( CTXT_ )
CALL BLACS_GRIDINFO( ICTXT, NPROW, NPCOL, MYROW, MYCOL )
*
* Test the input parameters
*
INFO = 0
IF( NPROW.EQ.-1 ) THEN
INFO = -(600+CTXT_)
ELSE
CALL CHK1MAT( M, 1, N, 2, IA, JA, DESCA, 6, INFO )
IF( INFO.EQ.0 ) THEN
NB = DESCA( MB_ )
IOFF = MOD( IA-1, DESCA( MB_ ) )
IAROW = INDXG2P( IA, NB, MYROW, DESCA( RSRC_ ), NPROW )
IACOL = INDXG2P( JA, NB, MYCOL, DESCA( CSRC_ ), NPCOL )
MP = NUMROC( M+IOFF, NB, MYROW, IAROW, NPROW )
NQ = NUMROC( N+IOFF, NB, MYCOL, IACOL, NPCOL )
LWMIN = NB*( MP+NQ+1 ) + NQ
*
WORK( 1 ) = REAL( LWMIN )
LQUERY = ( LWORK.EQ.-1 )
IF( IOFF.NE.MOD( JA-1, DESCA( NB_ ) ) ) THEN
INFO = -5
ELSE IF( NB.NE.DESCA( NB_ ) ) THEN
INFO = -(600+NB_)
ELSE IF( LWORK.LT.LWMIN .AND. .NOT.LQUERY ) THEN
INFO = -12
END IF
END IF
IF( LQUERY ) THEN
IDUM1( 1 ) = -1
ELSE
IDUM1( 1 ) = 1
END IF
IDUM2( 1 ) = 12
CALL PCHK1MAT( M, 1, N, 2, IA, JA, DESCA, 6, 1, IDUM1, IDUM2,
$ INFO )
END IF
*
IF( INFO.LT.0 ) THEN
CALL PXERBLA( ICTXT, 'PSGEBRD', -INFO )
RETURN
ELSE IF( LQUERY ) THEN
RETURN
END IF
*
* Quick return if possible
*
MN = MIN( M, N )
IF( MN.EQ.0 )
$ RETURN
*
* Initialize parameters.
*
CALL PB_TOPGET( ICTXT, 'Combine', 'Columnwise', COLCTOP )
CALL PB_TOPGET( ICTXT, 'Combine', 'Rowwise', ROWCTOP )
CALL PB_TOPSET( ICTXT, 'Combine', 'Columnwise', '1-tree' )
CALL PB_TOPSET( ICTXT, 'Combine', 'Rowwise', '1-tree' )
*
IPY = MP * NB + 1
IPW = NQ * NB + IPY
*
CALL DESCSET( DESCWX, M+IOFF, NB, NB, NB, IAROW, IACOL, ICTXT,
$ MAX( 1, MP ) )
CALL DESCSET( DESCWY, NB, N+IOFF, NB, NB, IAROW, IACOL, ICTXT,
$ NB )
*
MP = NUMROC( M+IA-1, NB, MYROW, DESCA( RSRC_ ), NPROW )
NQ = NUMROC( N+JA-1, NB, MYCOL, DESCA( CSRC_ ), NPCOL )
K = 1
JB = NB - IOFF
IW = IOFF + 1
JW = IOFF + 1
*
DO 10 L = 1, MN+IOFF-NB, NB
I = IA + K - 1
J = JA + K - 1
*
* Reduce rows and columns i:i+nb-1 to bidiagonal form and return
* the matrices X and Y which are needed to update the unreduced
* part of the matrix.
*
CALL PSLABRD( M-K+1, N-K+1, JB, A, I, J, DESCA, D, E, TAUQ,
$ TAUP, WORK, IW, JW, DESCWX, WORK( IPY ), IW,
$ JW, DESCWY, WORK( IPW ) )
*
* Update the trailing submatrix A(i+nb:ia+m-1,j+nb:ja+n-1), using
* an update of the form A := A - V*Y' - X*U'.
*
CALL PSGEMM( 'No transpose', 'No transpose', M-K-JB+1,
$ N-K-JB+1, JB, -ONE, A, I+JB, J, DESCA,
$ WORK( IPY ), IW, JW+JB, DESCWY, ONE, A, I+JB,
$ J+JB, DESCA )
CALL PSGEMM( 'No transpose', 'No transpose', M-K-JB+1,
$ N-K-JB+1, JB, -ONE, WORK, IW+JB, JW, DESCWX, A, I,
$ J+JB, DESCA, ONE, A, I+JB, J+JB, DESCA )
*
* Copy last off-diagonal elements of B back into sub( A ).
*
IF( M.GE.N ) THEN
JS = MIN( INDXG2L( I+JB-1, NB, 0, DESCA( RSRC_ ), NPROW ),
$ MP )
IF( JS.GT.0 )
$ CALL PSELSET( A, I+JB-1, J+JB, DESCA, E( JS ) )
ELSE
JS = MIN( INDXG2L( J+JB-1, NB, 0, DESCA( CSRC_ ), NPCOL ),
$ NQ )
IF( JS.GT.0 )
$ CALL PSELSET( A, I+JB, J+JB-1, DESCA, E( JS ) )
END IF
*
K = K + JB
JB = NB
IW = 1
JW = 1
DESCWX( M_ ) = DESCWX( M_ ) - JB
DESCWX( RSRC_ ) = MOD( DESCWX( RSRC_ ) + 1, NPROW )
DESCWX( CSRC_ ) = MOD( DESCWX( CSRC_ ) + 1, NPCOL )
DESCWY( N_ ) = DESCWY( N_ ) - JB
DESCWY( RSRC_ ) = MOD( DESCWY( RSRC_ ) + 1, NPROW )
DESCWY( CSRC_ ) = MOD( DESCWY( CSRC_ ) + 1, NPCOL )
*
10 CONTINUE
*
* Use unblocked code to reduce the remainder of the matrix.
*
CALL PSGEBD2( M-K+1, N-K+1, A, IA+K-1, JA+K-1, DESCA, D, E, TAUQ,
$ TAUP, WORK, LWORK, IINFO )
*
CALL PB_TOPSET( ICTXT, 'Combine', 'Columnwise', COLCTOP )
CALL PB_TOPSET( ICTXT, 'Combine', 'Rowwise', ROWCTOP )
*
WORK( 1 ) = REAL( LWMIN )
*
RETURN
*
* End of PSGEBRD
*
END
|
