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
|
SUBROUTINE PZNEPFCHK( N, A, IA, JA, DESCA, IASEED, Z, IZ, JZ,
$ DESCZ, ANORM, FRESID, WORK )
*
* -- ScaLAPACK testing routine (version 1.7) --
* University of Tennessee, Knoxville, Oak Ridge National Laboratory,
* and University of California, Berkeley.
* March, 2000
*
* .. Scalar Arguments ..
INTEGER IA, IASEED, IZ, JA, JZ, N
DOUBLE PRECISION ANORM, FRESID
* ..
* .. Array Arguments ..
INTEGER DESCA( * ), DESCZ( * )
COMPLEX*16 A( * ), WORK( * ), Z( * )
* ..
*
* Purpose
* =======
*
* PZNEPFCHK computes the residual
* || sub(Z)*sub( A )*sub(Z)**T - sub( Ao ) || / (||sub( Ao )||*eps*N),
* where Ao will be regenerated by the parallel random matrix generator,
* sub( A ) = A(IA:IA+M-1,JA:JA+N-1), sub( Z ) = Z(IZ:IZ+N-1,JZ:JZ+N-1)
* and ||.|| stands for the infinity norm.
*
* 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
* =========
*
* N (global input) INTEGER
* The order of sub( A ) and sub( Z ). N >= 0.
*
* A (local input/local output) COMPLEX*16 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 N-by-N
* distributed matrix sub( A ) to be checked. On exit, this
* array contains the local pieces of the difference
* sub(Z)*sub( A )*sub(Z)**T - sub( Ao ).
*
* IA (global input) INTEGER
* A's global row index, which points to the beginning of the
* submatrix which is to be operated on.
*
* JA (global input) INTEGER
* A's global column index, which points to the beginning of
* the submatrix which is to be operated on.
*
* DESCA (global and local input) INTEGER array of dimension DLEN_.
* The array descriptor for the distributed matrix A.
*
* IASEED (global input) INTEGER
* The seed number to generate the original matrix Ao.
*
* Z (local input) COMPLEX*16 pointer into the local memory
* to an array of dimension (LLD_Z,LOCc(JZ+N-1)). On entry, this
* array contains the local pieces of the N-by-N distributed
* matrix sub( Z ).
*
* IZ (global input) INTEGER
* Z's global row index, which points to the beginning of the
* submatrix which is to be operated on.
*
* JZ (global input) INTEGER
* Z's global column index, which points to the beginning of
* the submatrix which is to be operated on.
*
* DESCZ (global and local input) INTEGER array of dimension DLEN_.
* The array descriptor for the distributed matrix Z.
*
* ANORM (global input) DOUBLE PRECISION
* The Infinity norm of sub( A ).
*
* FRESID (global output) DOUBLE PRECISION
* The maximum (worst) factorizational error.
*
* WORK (local workspace) COMPLEX*16 array, dimension (LWORK).
* LWORK >= MAX( NpA0 * NB_A, MB_A * NqA0 ) where
*
* IROFFA = MOD( IA-1, MB_A ),
* ICOFFA = MOD( JA-1, NB_A ),
* IAROW = INDXG2P( IA, MB_A, MYROW, RSRC_A, NPROW ),
* IACOL = INDXG2P( JA, NB_A, MYCOL, CSRC_A, NPCOL ),
* NpA0 = NUMROC( N+IROFFA, MB_A, MYROW, IAROW, NPROW ),
* NqA0 = NUMROC( N+ICOFFA, NB_A, MYCOL, IACOL, NPCOL ),
*
* WORK is used to store a block of rows and a block of columns
* of sub( A ).
* INDXG2P and NUMROC are ScaLAPACK tool functions; MYROW,
* MYCOL, NPROW and NPCOL can be determined by calling the
* subroutine BLACS_GRIDINFO.
*
* Further Details
* ===============
*
* Contributed by Mark Fahey, March, 2000.
*
* =====================================================================
*
* .. 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 )
COMPLEX*16 ONE, ZERO
PARAMETER ( ONE = ( 1.0D+0, 0.0D+0 ),
$ ZERO = ( 0.0D+0, 0.0D+0 ) )
* ..
* .. Local Scalars ..
INTEGER I, IACOL, IAROW, IB, ICTXT, IIA, IOFFA, IROFF,
$ IW, J, JB, JJA, JN, LDA, LDW, MYCOL, MYROW, NP,
$ NPCOL, NPROW
DOUBLE PRECISION EPS
* ..
* .. Local Arrays ..
INTEGER DESCW( DLEN_ )
* ..
* .. External Subroutines ..
EXTERNAL BLACS_GRIDINFO, DESCSET, INFOG2L, PZGEMM,
$ PZLACPY, PZLASET, PZMATGEN, ZMATADD
* ..
* .. External Functions ..
INTEGER ICEIL, NUMROC
DOUBLE PRECISION PDLAMCH, PZLANGE
EXTERNAL ICEIL, NUMROC, PDLAMCH, PZLANGE
* ..
* .. Intrinsic Functions ..
INTRINSIC MAX, MIN, MOD
* ..
* .. Executable Statements ..
*
ICTXT = DESCA( CTXT_ )
CALL BLACS_GRIDINFO( ICTXT, NPROW, NPCOL, MYROW, MYCOL )
EPS = PDLAMCH( ICTXT, 'eps' )
*
CALL INFOG2L( IA, JA, DESCA, NPROW, NPCOL, MYROW, MYCOL, IIA, JJA,
$ IAROW, IACOL )
IROFF = MOD( IA-1, DESCA( MB_ ) )
NP = NUMROC( N+IROFF, DESCA( MB_ ), MYROW, IAROW, NPROW )
IF( MYROW.EQ.IAROW )
$ NP = NP - IROFF
LDW = MAX( 1, NP )
*
* First compute H <- H * Z**T
*
CALL DESCSET( DESCW, DESCA( MB_ ), N, DESCA( MB_ ), DESCA( NB_ ),
$ IAROW, IACOL, ICTXT, DESCA( MB_ ) )
*
DO 10 I = IA, IA + N - 1, DESCA( MB_ )
IB = MIN( IA+N-I, DESCA( MB_ ) )
*
CALL PZLACPY( 'All', IB, N, A, I, JA, DESCA, WORK, 1, 1,
$ DESCW )
CALL PZGEMM( 'No transpose', 'Cong Tran', IB, N, N, ONE, WORK,
$ 1, 1, DESCW, Z, IZ, JZ, DESCZ, ZERO, A, I, JA,
$ DESCA )
*
DESCW( RSRC_ ) = MOD( DESCW( RSRC_ )+1, NPROW )
*
10 CONTINUE
*
* Then compute H <- Z * H = Z * H0 * Z**T
*
CALL DESCSET( DESCW, N, DESCA( NB_ ), DESCA( MB_ ), DESCA( NB_ ),
$ IAROW, IACOL, ICTXT, LDW )
*
DO 20 J = JA, JA + N - 1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
CALL PZLACPY( 'All', N, JB, A, IA, J, DESCA, WORK, 1, 1,
$ DESCW )
CALL PZGEMM( 'No transpose', 'No transpose', N, JB, N, ONE, Z,
$ IZ, JZ, DESCZ, WORK, 1, 1, DESCW, ZERO, A, IA, J,
$ DESCA )
*
DESCW( CSRC_ ) = MOD( DESCW( CSRC_ )+1, NPCOL )
*
20 CONTINUE
*
* Compute H - H0
*
JN = MIN( ICEIL( JA, DESCA( NB_ ) )*DESCA( NB_ ), JA+N-1 )
LDA = DESCA( LLD_ )
IOFFA = IIA + ( JJA-1 )*LDA
IW = 1
JB = JN - JA + 1
DESCW( CSRC_ ) = IACOL
*
* Handle first block of columns separately
*
IF( MYCOL.EQ.DESCW( CSRC_ ) ) THEN
CALL PZMATGEN( ICTXT, 'N', 'N', DESCA( M_ ), DESCA( N_ ),
$ DESCA( MB_ ), DESCA( NB_ ), WORK, LDW,
$ DESCA( RSRC_ ), DESCA( CSRC_ ), IASEED, IIA-1,
$ NP, JJA-1, JB, MYROW, MYCOL, NPROW, NPCOL )
CALL PZLASET( 'Lower', MAX( 0, N-2 ), JB, ZERO, ZERO, WORK,
$ MIN( IW+2, N ), 1, DESCW )
CALL ZMATADD( NP, JB, -ONE, WORK, LDW, ONE, A( IOFFA ), LDA )
JJA = JJA + JB
IOFFA = IOFFA + JB*LDA
END IF
*
IW = IW + DESCA( MB_ )
DESCW( CSRC_ ) = MOD( DESCW( CSRC_ )+1, NPCOL )
*
DO 30 J = JN + 1, JA + N - 1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.DESCW( CSRC_ ) ) THEN
CALL PZMATGEN( ICTXT, 'N', 'N', DESCA( M_ ), DESCA( N_ ),
$ DESCA( MB_ ), DESCA( NB_ ), WORK, LDW,
$ DESCA( RSRC_ ), DESCA( CSRC_ ), IASEED,
$ IIA-1, NP, JJA-1, JB, MYROW, MYCOL, NPROW,
$ NPCOL )
CALL PZLASET( 'Lower', MAX( 0, N-IW-1 ), JB, ZERO, ZERO,
$ WORK, MIN( N, IW+2 ), 1, DESCW )
CALL ZMATADD( NP, JB, -ONE, WORK, LDW, ONE, A( IOFFA ),
$ LDA )
JJA = JJA + JB
IOFFA = IOFFA + JB*LDA
END IF
IW = IW + DESCA( MB_ )
DESCW( CSRC_ ) = MOD( DESCW( CSRC_ )+1, NPCOL )
30 CONTINUE
*
* Calculate factor residual
*
FRESID = PZLANGE( 'I', N, N, A, IA, JA, DESCA, WORK ) /
$ ( N*EPS*ANORM )
*
RETURN
*
* End PZNEPFCHK
*
END
|
