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
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
|
/* Implementation of the SUM intrinsic
Copyright 2002, 2007, 2009 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 3 of the License, or (at your option) any later version.
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.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>. */
#include "libgfortran.h"
#include <stdlib.h>
#include <assert.h>
#if defined (HAVE_GFC_REAL_8) && defined (HAVE_GFC_REAL_8)
extern void sum_r8 (gfc_array_r8 * const restrict,
gfc_array_r8 * const restrict, const index_type * const restrict);
export_proto(sum_r8);
void
sum_r8 (gfc_array_r8 * const restrict retarray,
gfc_array_r8 * const restrict array,
const index_type * const restrict 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];
const GFC_REAL_8 * restrict base;
GFC_REAL_8 * restrict dest;
index_type rank;
index_type n;
index_type len;
index_type delta;
index_type dim;
int continue_loop;
/* Make dim zero based to avoid confusion. */
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
len = GFC_DESCRIPTOR_EXTENT(array,dim);
if (len < 0)
len = 0;
delta = GFC_DESCRIPTOR_STRIDE(array,dim);
for (n = 0; n < dim; n++)
{
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
if (extent[n] < 0)
extent[n] = 0;
}
for (n = dim; n < rank; n++)
{
sstride[n] = GFC_DESCRIPTOR_STRIDE(array, n + 1);
extent[n] = GFC_DESCRIPTOR_EXTENT(array, n + 1);
if (extent[n] < 0)
extent[n] = 0;
}
if (retarray->base_addr == NULL)
{
size_t alloc_size, str;
for (n = 0; n < rank; n++)
{
if (n == 0)
str = 1;
else
str = GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
}
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
alloc_size = sizeof (GFC_REAL_8) * GFC_DESCRIPTOR_STRIDE(retarray,rank-1)
* extent[rank-1];
retarray->base_addr = xmalloc (alloc_size);
if (alloc_size == 0)
{
/* Make sure we have a zero-sized array. */
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
return;
}
}
else
{
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect in"
" SUM intrinsic: is %ld, should be %ld",
(long int) (GFC_DESCRIPTOR_RANK (retarray)),
(long int) rank);
if (unlikely (compile_options.bounds_check))
bounds_ifunction_return ((array_t *) retarray, extent,
"return value", "SUM");
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = GFC_DESCRIPTOR_STRIDE(retarray,n);
if (extent[n] <= 0)
return;
}
base = array->base_addr;
dest = retarray->base_addr;
continue_loop = 1;
while (continue_loop)
{
const GFC_REAL_8 * restrict src;
GFC_REAL_8 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 probably not worth it. */
base -= sstride[n] * extent[n];
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
{
/* Break out of the look. */
continue_loop = 0;
break;
}
else
{
count[n]++;
base += sstride[n];
dest += dstride[n];
}
}
}
}
extern void msum_r8 (gfc_array_r8 * const restrict,
gfc_array_r8 * const restrict, const index_type * const restrict,
gfc_array_l1 * const restrict);
export_proto(msum_r8);
void
msum_r8 (gfc_array_r8 * const restrict retarray,
gfc_array_r8 * const restrict array,
const index_type * const restrict pdim,
gfc_array_l1 * const restrict 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_8 * restrict dest;
const GFC_REAL_8 * restrict base;
const GFC_LOGICAL_1 * restrict mbase;
int rank;
int dim;
index_type n;
index_type len;
index_type delta;
index_type mdelta;
int mask_kind;
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
len = GFC_DESCRIPTOR_EXTENT(array,dim);
if (len <= 0)
return;
mbase = mask->base_addr;
mask_kind = GFC_DESCRIPTOR_SIZE (mask);
if (mask_kind == 1 || mask_kind == 2 || mask_kind == 4 || mask_kind == 8
#ifdef HAVE_GFC_LOGICAL_16
|| mask_kind == 16
#endif
)
mbase = GFOR_POINTER_TO_L1 (mbase, mask_kind);
else
runtime_error ("Funny sized logical array");
delta = GFC_DESCRIPTOR_STRIDE(array,dim);
mdelta = GFC_DESCRIPTOR_STRIDE_BYTES(mask,dim);
for (n = 0; n < dim; n++)
{
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
if (extent[n] < 0)
extent[n] = 0;
}
for (n = dim; n < rank; n++)
{
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n + 1);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask, n + 1);
extent[n] = GFC_DESCRIPTOR_EXTENT(array, n + 1);
if (extent[n] < 0)
extent[n] = 0;
}
if (retarray->base_addr == NULL)
{
size_t alloc_size, str;
for (n = 0; n < rank; n++)
{
if (n == 0)
str = 1;
else
str= GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
}
alloc_size = sizeof (GFC_REAL_8) * GFC_DESCRIPTOR_STRIDE(retarray,rank-1)
* extent[rank-1];
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
if (alloc_size == 0)
{
/* Make sure we have a zero-sized array. */
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
return;
}
else
retarray->base_addr = xmalloc (alloc_size);
}
else
{
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect in SUM intrinsic");
if (unlikely (compile_options.bounds_check))
{
bounds_ifunction_return ((array_t *) retarray, extent,
"return value", "SUM");
bounds_equal_extents ((array_t *) mask, (array_t *) array,
"MASK argument", "SUM");
}
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = GFC_DESCRIPTOR_STRIDE(retarray,n);
if (extent[n] <= 0)
return;
}
dest = retarray->base_addr;
base = array->base_addr;
while (base)
{
const GFC_REAL_8 * restrict src;
const GFC_LOGICAL_1 * restrict msrc;
GFC_REAL_8 result;
src = base;
msrc = mbase;
{
result = 0;
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 probably 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];
}
}
}
}
extern void ssum_r8 (gfc_array_r8 * const restrict,
gfc_array_r8 * const restrict, const index_type * const restrict,
GFC_LOGICAL_4 *);
export_proto(ssum_r8);
void
ssum_r8 (gfc_array_r8 * const restrict retarray,
gfc_array_r8 * const restrict array,
const index_type * const restrict pdim,
GFC_LOGICAL_4 * mask)
{
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type dstride[GFC_MAX_DIMENSIONS];
GFC_REAL_8 * restrict dest;
index_type rank;
index_type n;
index_type dim;
if (*mask)
{
sum_r8 (retarray, array, pdim);
return;
}
/* Make dim zero based to avoid confusion. */
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
for (n = 0; n < dim; n++)
{
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
if (extent[n] <= 0)
extent[n] = 0;
}
for (n = dim; n < rank; n++)
{
extent[n] =
GFC_DESCRIPTOR_EXTENT(array,n + 1);
if (extent[n] <= 0)
extent[n] = 0;
}
if (retarray->base_addr == NULL)
{
size_t alloc_size, str;
for (n = 0; n < rank; n++)
{
if (n == 0)
str = 1;
else
str = GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
}
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
alloc_size = sizeof (GFC_REAL_8) * GFC_DESCRIPTOR_STRIDE(retarray,rank-1)
* extent[rank-1];
if (alloc_size == 0)
{
/* Make sure we have a zero-sized array. */
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
return;
}
else
retarray->base_addr = xmalloc (alloc_size);
}
else
{
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect in"
" SUM intrinsic: is %ld, should be %ld",
(long int) (GFC_DESCRIPTOR_RANK (retarray)),
(long int) rank);
if (unlikely (compile_options.bounds_check))
{
for (n=0; n < rank; n++)
{
index_type ret_extent;
ret_extent = GFC_DESCRIPTOR_EXTENT(retarray,n);
if (extent[n] != ret_extent)
runtime_error ("Incorrect extent in return value of"
" SUM intrinsic in dimension %ld:"
" is %ld, should be %ld", (long int) n + 1,
(long int) ret_extent, (long int) extent[n]);
}
}
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = GFC_DESCRIPTOR_STRIDE(retarray,n);
}
dest = retarray->base_addr;
while(1)
{
*dest = 0;
count[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 probably not worth it. */
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
return;
else
{
count[n]++;
dest += dstride[n];
}
}
}
}
#endif
|