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
|
/* Implementation of the SUM intrinsic
Copyright 2002 Free Software Foundation, Inc.
Contributed by Paul Brook <paul@nowt.org>
This file is part of the GNU Fortran 95 runtime library (libgfortran).
Libgfortran is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public
License as published by the Free Software Foundation; either
version 2 of the License, or (at your option) any later version.
In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file. (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)
Libgfortran is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public
License along with libgfortran; see the file COPYING. If not,
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
#include "config.h"
#include <stdlib.h>
#include <assert.h>
#include "libgfortran.h"
extern void sum_r4 (gfc_array_r4 *, gfc_array_r4 *, index_type *);
export_proto(sum_r4);
void
sum_r4 (gfc_array_r4 *retarray, gfc_array_r4 *array, index_type *pdim)
{
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type sstride[GFC_MAX_DIMENSIONS];
index_type dstride[GFC_MAX_DIMENSIONS];
GFC_REAL_4 *base;
GFC_REAL_4 *dest;
index_type rank;
index_type n;
index_type len;
index_type delta;
index_type dim;
/* Make dim zero based to avoid confusion. */
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
/* TODO: It should be a front end job to correctly set the strides. */
if (array->dim[0].stride == 0)
array->dim[0].stride = 1;
len = array->dim[dim].ubound + 1 - array->dim[dim].lbound;
delta = array->dim[dim].stride;
for (n = 0; n < dim; n++)
{
sstride[n] = array->dim[n].stride;
extent[n] = array->dim[n].ubound + 1 - array->dim[n].lbound;
}
for (n = dim; n < rank; n++)
{
sstride[n] = array->dim[n + 1].stride;
extent[n] =
array->dim[n + 1].ubound + 1 - array->dim[n + 1].lbound;
}
if (retarray->data == NULL)
{
for (n = 0; n < rank; n++)
{
retarray->dim[n].lbound = 0;
retarray->dim[n].ubound = extent[n]-1;
if (n == 0)
retarray->dim[n].stride = 1;
else
retarray->dim[n].stride = retarray->dim[n-1].stride * extent[n-1];
}
retarray->data
= internal_malloc_size (sizeof (GFC_REAL_4)
* retarray->dim[rank-1].stride
* extent[rank-1]);
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
}
else
{
if (retarray->dim[0].stride == 0)
retarray->dim[0].stride = 1;
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect");
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = retarray->dim[n].stride;
if (extent[n] <= 0)
len = 0;
}
base = array->data;
dest = retarray->data;
while (base)
{
GFC_REAL_4 *src;
GFC_REAL_4 result;
src = base;
{
result = 0;
if (len <= 0)
*dest = 0;
else
{
for (n = 0; n < len; n++, src += delta)
{
result += *src;
}
*dest = result;
}
}
/* Advance to the next element. */
count[0]++;
base += sstride[0];
dest += dstride[0];
n = 0;
while (count[n] == extent[n])
{
/* When we get to the end of a dimension, reset it and increment
the next dimension. */
count[n] = 0;
/* We could precalculate these products, but this is a less
frequently used path so proabably not worth it. */
base -= sstride[n] * extent[n];
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
{
/* Break out of the look. */
base = NULL;
break;
}
else
{
count[n]++;
base += sstride[n];
dest += dstride[n];
}
}
}
}
extern void msum_r4 (gfc_array_r4 *, gfc_array_r4 *, index_type *,
gfc_array_l4 *);
export_proto(msum_r4);
void
msum_r4 (gfc_array_r4 * retarray, gfc_array_r4 * array,
index_type *pdim, gfc_array_l4 * mask)
{
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type sstride[GFC_MAX_DIMENSIONS];
index_type dstride[GFC_MAX_DIMENSIONS];
index_type mstride[GFC_MAX_DIMENSIONS];
GFC_REAL_4 *dest;
GFC_REAL_4 *base;
GFC_LOGICAL_4 *mbase;
int rank;
int dim;
index_type n;
index_type len;
index_type delta;
index_type mdelta;
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
/* TODO: It should be a front end job to correctly set the strides. */
if (array->dim[0].stride == 0)
array->dim[0].stride = 1;
if (mask->dim[0].stride == 0)
mask->dim[0].stride = 1;
len = array->dim[dim].ubound + 1 - array->dim[dim].lbound;
if (len <= 0)
return;
delta = array->dim[dim].stride;
mdelta = mask->dim[dim].stride;
for (n = 0; n < dim; n++)
{
sstride[n] = array->dim[n].stride;
mstride[n] = mask->dim[n].stride;
extent[n] = array->dim[n].ubound + 1 - array->dim[n].lbound;
}
for (n = dim; n < rank; n++)
{
sstride[n] = array->dim[n + 1].stride;
mstride[n] = mask->dim[n + 1].stride;
extent[n] =
array->dim[n + 1].ubound + 1 - array->dim[n + 1].lbound;
}
if (retarray->data == NULL)
{
for (n = 0; n < rank; n++)
{
retarray->dim[n].lbound = 0;
retarray->dim[n].ubound = extent[n]-1;
if (n == 0)
retarray->dim[n].stride = 1;
else
retarray->dim[n].stride = retarray->dim[n-1].stride * extent[n-1];
}
retarray->data
= internal_malloc_size (sizeof (GFC_REAL_4)
* retarray->dim[rank-1].stride
* extent[rank-1]);
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
}
else
{
if (retarray->dim[0].stride == 0)
retarray->dim[0].stride = 1;
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect");
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = retarray->dim[n].stride;
if (extent[n] <= 0)
return;
}
dest = retarray->data;
base = array->data;
mbase = mask->data;
if (GFC_DESCRIPTOR_SIZE (mask) != 4)
{
/* This allows the same loop to be used for all logical types. */
assert (GFC_DESCRIPTOR_SIZE (mask) == 8);
for (n = 0; n < rank; n++)
mstride[n] <<= 1;
mdelta <<= 1;
mbase = (GFOR_POINTER_L8_TO_L4 (mbase));
}
while (base)
{
GFC_REAL_4 *src;
GFC_LOGICAL_4 *msrc;
GFC_REAL_4 result;
src = base;
msrc = mbase;
{
result = 0;
if (len <= 0)
*dest = 0;
else
{
for (n = 0; n < len; n++, src += delta, msrc += mdelta)
{
if (*msrc)
result += *src;
}
*dest = result;
}
}
/* Advance to the next element. */
count[0]++;
base += sstride[0];
mbase += mstride[0];
dest += dstride[0];
n = 0;
while (count[n] == extent[n])
{
/* When we get to the end of a dimension, reset it and increment
the next dimension. */
count[n] = 0;
/* We could precalculate these products, but this is a less
frequently used path so proabably not worth it. */
base -= sstride[n] * extent[n];
mbase -= mstride[n] * extent[n];
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
{
/* Break out of the look. */
base = NULL;
break;
}
else
{
count[n]++;
base += sstride[n];
mbase += mstride[n];
dest += dstride[n];
}
}
}
}
|
