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
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
|
/* Inlining decision heuristics.
Copyright (C) 2003, 2004, 2007 Free Software Foundation, Inc.
Contributed by Jan Hubicka
This file is part of GCC.
GCC 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, or (at your option) any later
version.
GCC 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 GCC; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
/* Inlining decision heuristics
We separate inlining decisions from the inliner itself and store it
inside callgraph as so called inline plan. Refer to cgraph.c
documentation about particular representation of inline plans in the
callgraph.
There are three major parts of this file:
cgraph_mark_inline implementation
This function allows to mark given call inline and performs necessary
modifications of cgraph (production of the clones and updating overall
statistics)
inlining heuristics limits
These functions allow to check that particular inlining is allowed
by the limits specified by user (allowed function growth, overall unit
growth and so on).
inlining heuristics
This is implementation of IPA pass aiming to get as much of benefit
from inlining obeying the limits checked above.
The implementation of particular heuristics is separated from
the rest of code to make it easier to replace it with more complicated
implementation in the future. The rest of inlining code acts as a
library aimed to modify the callgraph and verify that the parameters
on code size growth fits.
To mark given call inline, use cgraph_mark_inline function, the
verification is performed by cgraph_default_inline_p and
cgraph_check_inline_limits.
The heuristics implements simple knapsack style algorithm ordering
all functions by their "profitability" (estimated by code size growth)
and inlining them in priority order.
cgraph_decide_inlining implements heuristics taking whole callgraph
into account, while cgraph_decide_inlining_incrementally considers
only one function at a time and is used in non-unit-at-a-time mode.
The inliner itself is split into several passes:
pass_inline_parameters
This pass computes local properties of functions that are used by inliner:
estimated function body size, whether function is inlinable at all and
stack frame consumption.
Before executing any of inliner passes, this local pass has to be applied
to each function in the callgraph (ie run as subpass of some earlier
IPA pass). The results are made out of date by any optimization applied
on the function body.
pass_early_inlining
Simple local inlining pass inlining callees into current function. This
pass makes no global whole compilation unit analysis and this when allowed
to do inlining expanding code size it might result in unbounded growth of
whole unit.
This is the main inlining pass in non-unit-at-a-time.
With unit-at-a-time the pass is run during conversion into SSA form.
Only functions already converted into SSA form are inlined, so the
conversion must happen in topological order on the callgraph (that is
maintained by pass manager). The functions after inlining are early
optimized so the early inliner sees unoptimized function itself, but
all considered callees are already optimized allowing it to unfold
abstraction penalty on C++ effectively and cheaply.
pass_ipa_early_inlining
With profiling, the early inlining is also necessary to reduce
instrumentation costs on program with high abstraction penalty (doing
many redundant calls). This can't happen in parallel with early
optimization and profile instrumentation, because we would end up
re-instrumenting already instrumented function bodies we brought in via
inlining.
To avoid this, this pass is executed as IPA pass before profiling. It is
simple wrapper to pass_early_inlining and ensures first inlining.
pass_ipa_inline
This is the main pass implementing simple greedy algorithm to do inlining
of small functions that results in overall growth of compilation unit and
inlining of functions called once. The pass compute just so called inline
plan (representation of inlining to be done in callgraph) and unlike early
inlining it is not performing the inlining itself.
pass_apply_inline
This pass performs actual inlining according to pass_ipa_inline on given
function. Possible the function body before inlining is saved when it is
needed for further inlining later.
*/
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "tree.h"
#include "tree-inline.h"
#include "langhooks.h"
#include "flags.h"
#include "cgraph.h"
#include "diagnostic.h"
#include "timevar.h"
#include "params.h"
#include "fibheap.h"
#include "intl.h"
#include "tree-pass.h"
#include "hashtab.h"
#include "coverage.h"
#include "ggc.h"
#include "tree-flow.h"
#include "rtl.h"
/* Mode incremental inliner operate on:
In ALWAYS_INLINE only functions marked
always_inline are inlined. This mode is used after detecting cycle during
flattening.
In SIZE mode, only functions that reduce function body size after inlining
are inlined, this is used during early inlining.
In SPEED mode, all small functions are inlined. This might result in
unbounded growth of compilation unit and is used only in non-unit-at-a-time
mode.
in ALL mode, everything is inlined. This is used during flattening. */
enum inlining_mode {
INLINE_NONE = 0,
INLINE_ALWAYS_INLINE,
INLINE_SIZE,
INLINE_SPEED,
INLINE_ALL
};
static bool
cgraph_decide_inlining_incrementally (struct cgraph_node *, enum inlining_mode,
int);
/* Statistics we collect about inlining algorithm. */
static int ncalls_inlined;
static int nfunctions_inlined;
static int overall_insns;
static gcov_type max_count;
/* Estimate size of the function after inlining WHAT into TO. */
static int
cgraph_estimate_size_after_inlining (int times, struct cgraph_node *to,
struct cgraph_node *what)
{
int size;
tree fndecl = what->decl, arg;
int call_insns = PARAM_VALUE (PARAM_INLINE_CALL_COST);
for (arg = DECL_ARGUMENTS (fndecl); arg; arg = TREE_CHAIN (arg))
call_insns += estimate_move_cost (TREE_TYPE (arg));
size = (what->global.insns - call_insns) * times + to->global.insns;
gcc_assert (size >= 0);
return size;
}
/* E is expected to be an edge being inlined. Clone destination node of
the edge and redirect it to the new clone.
DUPLICATE is used for bookkeeping on whether we are actually creating new
clones or re-using node originally representing out-of-line function call.
*/
void
cgraph_clone_inlined_nodes (struct cgraph_edge *e, bool duplicate, bool update_original)
{
HOST_WIDE_INT peak;
if (duplicate)
{
/* We may eliminate the need for out-of-line copy to be output.
In that case just go ahead and re-use it. */
if (!e->callee->callers->next_caller
&& !e->callee->needed
&& !cgraph_new_nodes
&& flag_unit_at_a_time)
{
gcc_assert (!e->callee->global.inlined_to);
if (DECL_SAVED_TREE (e->callee->decl))
overall_insns -= e->callee->global.insns, nfunctions_inlined++;
duplicate = false;
}
else
{
struct cgraph_node *n;
n = cgraph_clone_node (e->callee, e->count, e->frequency, e->loop_nest,
update_original);
cgraph_redirect_edge_callee (e, n);
}
}
if (e->caller->global.inlined_to)
e->callee->global.inlined_to = e->caller->global.inlined_to;
else
e->callee->global.inlined_to = e->caller;
e->callee->global.stack_frame_offset
= e->caller->global.stack_frame_offset + e->caller->local.estimated_self_stack_size;
peak = e->callee->global.stack_frame_offset + e->callee->local.estimated_self_stack_size;
if (e->callee->global.inlined_to->global.estimated_stack_size < peak)
e->callee->global.inlined_to->global.estimated_stack_size = peak;
/* Recursively clone all bodies. */
for (e = e->callee->callees; e; e = e->next_callee)
if (!e->inline_failed)
cgraph_clone_inlined_nodes (e, duplicate, update_original);
}
/* Mark edge E as inlined and update callgraph accordingly.
UPDATE_ORIGINAL specify whether profile of original function should be
updated. */
void
cgraph_mark_inline_edge (struct cgraph_edge *e, bool update_original)
{
int old_insns = 0, new_insns = 0;
struct cgraph_node *to = NULL, *what;
if (e->callee->inline_decl)
cgraph_redirect_edge_callee (e, cgraph_node (e->callee->inline_decl));
gcc_assert (e->inline_failed);
e->inline_failed = NULL;
if (!e->callee->global.inlined && flag_unit_at_a_time)
DECL_POSSIBLY_INLINED (e->callee->decl) = true;
e->callee->global.inlined = true;
cgraph_clone_inlined_nodes (e, true, update_original);
what = e->callee;
/* Now update size of caller and all functions caller is inlined into. */
for (;e && !e->inline_failed; e = e->caller->callers)
{
old_insns = e->caller->global.insns;
new_insns = cgraph_estimate_size_after_inlining (1, e->caller,
what);
gcc_assert (new_insns >= 0);
to = e->caller;
to->global.insns = new_insns;
}
gcc_assert (what->global.inlined_to == to);
if (new_insns > old_insns)
overall_insns += new_insns - old_insns;
ncalls_inlined++;
}
/* Mark all calls of EDGE->CALLEE inlined into EDGE->CALLER.
Return following unredirected edge in the list of callers
of EDGE->CALLEE */
static struct cgraph_edge *
cgraph_mark_inline (struct cgraph_edge *edge)
{
struct cgraph_node *to = edge->caller;
struct cgraph_node *what = edge->callee;
struct cgraph_edge *e, *next;
gcc_assert (!CALL_CANNOT_INLINE_P (edge->call_stmt));
/* Look for all calls, mark them inline and clone recursively
all inlined functions. */
for (e = what->callers; e; e = next)
{
next = e->next_caller;
if (e->caller == to && e->inline_failed)
{
cgraph_mark_inline_edge (e, true);
if (e == edge)
edge = next;
}
}
return edge;
}
/* Estimate the growth caused by inlining NODE into all callees. */
static int
cgraph_estimate_growth (struct cgraph_node *node)
{
int growth = 0;
struct cgraph_edge *e;
if (node->global.estimated_growth != INT_MIN)
return node->global.estimated_growth;
for (e = node->callers; e; e = e->next_caller)
if (e->inline_failed)
growth += (cgraph_estimate_size_after_inlining (1, e->caller, node)
- e->caller->global.insns);
/* ??? Wrong for self recursive functions or cases where we decide to not
inline for different reasons, but it is not big deal as in that case
we will keep the body around, but we will also avoid some inlining. */
if (!node->needed && !DECL_EXTERNAL (node->decl))
growth -= node->global.insns;
node->global.estimated_growth = growth;
return growth;
}
/* Return false when inlining WHAT into TO is not good idea
as it would cause too large growth of function bodies.
When ONE_ONLY is true, assume that only one call site is going
to be inlined, otherwise figure out how many call sites in
TO calls WHAT and verify that all can be inlined.
*/
static bool
cgraph_check_inline_limits (struct cgraph_node *to, struct cgraph_node *what,
const char **reason, bool one_only)
{
int times = 0;
struct cgraph_edge *e;
int newsize;
int limit;
HOST_WIDE_INT stack_size_limit, inlined_stack;
if (one_only)
times = 1;
else
for (e = to->callees; e; e = e->next_callee)
if (e->callee == what)
times++;
if (to->global.inlined_to)
to = to->global.inlined_to;
/* When inlining large function body called once into small function,
take the inlined function as base for limiting the growth. */
if (to->local.self_insns > what->local.self_insns)
limit = to->local.self_insns;
else
limit = what->local.self_insns;
limit += limit * PARAM_VALUE (PARAM_LARGE_FUNCTION_GROWTH) / 100;
/* Check the size after inlining against the function limits. But allow
the function to shrink if it went over the limits by forced inlining. */
newsize = cgraph_estimate_size_after_inlining (times, to, what);
if (newsize >= to->global.insns
&& newsize > PARAM_VALUE (PARAM_LARGE_FUNCTION_INSNS)
&& newsize > limit)
{
if (reason)
*reason = N_("--param large-function-growth limit reached");
return false;
}
stack_size_limit = to->local.estimated_self_stack_size;
stack_size_limit += stack_size_limit * PARAM_VALUE (PARAM_STACK_FRAME_GROWTH) / 100;
inlined_stack = (to->global.stack_frame_offset
+ to->local.estimated_self_stack_size
+ what->global.estimated_stack_size);
if (inlined_stack > stack_size_limit
&& inlined_stack > PARAM_VALUE (PARAM_LARGE_STACK_FRAME))
{
if (reason)
*reason = N_("--param large-stack-frame-growth limit reached");
return false;
}
return true;
}
/* Return true when function N is small enough to be inlined. */
bool
cgraph_default_inline_p (struct cgraph_node *n, const char **reason)
{
tree decl = n->decl;
if (n->inline_decl)
decl = n->inline_decl;
if (!flag_inline_small_functions && !DECL_DECLARED_INLINE_P (decl))
{
if (reason)
*reason = N_("function not inline candidate");
return false;
}
if (!DECL_STRUCT_FUNCTION (decl)->cfg)
{
if (reason)
*reason = N_("function body not available");
return false;
}
if (DECL_DECLARED_INLINE_P (decl))
{
if (n->global.insns >= MAX_INLINE_INSNS_SINGLE)
{
if (reason)
*reason = N_("--param max-inline-insns-single limit reached");
return false;
}
}
else
{
if (n->global.insns >= MAX_INLINE_INSNS_AUTO)
{
if (reason)
*reason = N_("--param max-inline-insns-auto limit reached");
return false;
}
}
return true;
}
/* Return true when inlining WHAT would create recursive inlining.
We call recursive inlining all cases where same function appears more than
once in the single recursion nest path in the inline graph. */
static bool
cgraph_recursive_inlining_p (struct cgraph_node *to,
struct cgraph_node *what,
const char **reason)
{
bool recursive;
if (to->global.inlined_to)
recursive = what->decl == to->global.inlined_to->decl;
else
recursive = what->decl == to->decl;
/* Marking recursive function inline has sane semantic and thus we should
not warn on it. */
if (recursive && reason)
*reason = (what->local.disregard_inline_limits
? N_("recursive inlining") : "");
return recursive;
}
/* Return true if the call can be hot. */
static bool
cgraph_maybe_hot_edge_p (struct cgraph_edge *edge)
{
if (profile_info && flag_branch_probabilities
&& (edge->count
<= profile_info->sum_max / PARAM_VALUE (HOT_BB_COUNT_FRACTION)))
return false;
if (lookup_attribute ("cold", DECL_ATTRIBUTES (edge->callee->decl))
|| lookup_attribute ("cold", DECL_ATTRIBUTES (edge->caller->decl)))
return false;
if (lookup_attribute ("hot", DECL_ATTRIBUTES (edge->caller->decl)))
return true;
if (flag_guess_branch_prob
&& edge->frequency < (CGRAPH_FREQ_MAX
/ PARAM_VALUE (HOT_BB_FREQUENCY_FRACTION)))
return false;
return true;
}
/* A cost model driving the inlining heuristics in a way so the edges with
smallest badness are inlined first. After each inlining is performed
the costs of all caller edges of nodes affected are recomputed so the
metrics may accurately depend on values such as number of inlinable callers
of the function or function body size. */
static int
cgraph_edge_badness (struct cgraph_edge *edge)
{
int badness;
int growth =
cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
growth -= edge->caller->global.insns;
/* Always prefer inlining saving code size. */
if (growth <= 0)
badness = INT_MIN - growth;
/* When profiling is available, base priorities -(#calls / growth).
So we optimize for overall number of "executed" inlined calls. */
else if (max_count)
badness = ((int)((double)edge->count * INT_MIN / max_count)) / growth;
/* When function local profile is available, base priorities on
growth / frequency, so we optimize for overall frequency of inlined
calls. This is not too accurate since while the call might be frequent
within function, the function itself is infrequent.
Other objective to optimize for is number of different calls inlined.
We add the estimated growth after inlining all functions to biass the
priorities slightly in this direction (so fewer times called functions
of the same size gets priority). */
else if (flag_guess_branch_prob)
{
int div = edge->frequency * 100 / CGRAPH_FREQ_BASE;
int growth =
cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
growth -= edge->caller->global.insns;
badness = growth * 256;
/* Decrease badness if call is nested. */
/* Compress the range so we don't overflow. */
if (div > 256)
div = 256 + ceil_log2 (div) - 8;
if (div < 1)
div = 1;
if (badness > 0)
badness /= div;
badness += cgraph_estimate_growth (edge->callee);
}
/* When function local profile is not available or it does not give
useful information (ie frequency is zero), base the cost on
loop nest and overall size growth, so we optimize for overall number
of functions fully inlined in program. */
else
{
int nest = MIN (edge->loop_nest, 8);
badness = cgraph_estimate_growth (edge->callee) * 256;
/* Decrease badness if call is nested. */
if (badness > 0)
badness >>= nest;
else
{
badness <<= nest;
}
}
/* Make recursive inlining happen always after other inlining is done. */
if (cgraph_recursive_inlining_p (edge->caller, edge->callee, NULL))
return badness + 1;
else
return badness;
}
/* Recompute heap nodes for each of caller edge. */
static void
update_caller_keys (fibheap_t heap, struct cgraph_node *node,
bitmap updated_nodes)
{
struct cgraph_edge *edge;
const char *failed_reason;
if (!node->local.inlinable || node->local.disregard_inline_limits
|| node->global.inlined_to)
return;
if (bitmap_bit_p (updated_nodes, node->uid))
return;
bitmap_set_bit (updated_nodes, node->uid);
node->global.estimated_growth = INT_MIN;
if (!node->local.inlinable)
return;
/* Prune out edges we won't inline into anymore. */
if (!cgraph_default_inline_p (node, &failed_reason))
{
for (edge = node->callers; edge; edge = edge->next_caller)
if (edge->aux)
{
fibheap_delete_node (heap, (fibnode_t) edge->aux);
edge->aux = NULL;
if (edge->inline_failed)
edge->inline_failed = failed_reason;
}
return;
}
for (edge = node->callers; edge; edge = edge->next_caller)
if (edge->inline_failed)
{
int badness = cgraph_edge_badness (edge);
if (edge->aux)
{
fibnode_t n = (fibnode_t) edge->aux;
gcc_assert (n->data == edge);
if (n->key == badness)
continue;
/* fibheap_replace_key only increase the keys. */
if (fibheap_replace_key (heap, n, badness))
continue;
fibheap_delete_node (heap, (fibnode_t) edge->aux);
}
edge->aux = fibheap_insert (heap, badness, edge);
}
}
/* Recompute heap nodes for each of caller edges of each of callees. */
static void
update_callee_keys (fibheap_t heap, struct cgraph_node *node,
bitmap updated_nodes)
{
struct cgraph_edge *e;
node->global.estimated_growth = INT_MIN;
for (e = node->callees; e; e = e->next_callee)
if (e->inline_failed)
update_caller_keys (heap, e->callee, updated_nodes);
else if (!e->inline_failed)
update_callee_keys (heap, e->callee, updated_nodes);
}
/* Enqueue all recursive calls from NODE into priority queue depending on
how likely we want to recursively inline the call. */
static void
lookup_recursive_calls (struct cgraph_node *node, struct cgraph_node *where,
fibheap_t heap)
{
static int priority;
struct cgraph_edge *e;
for (e = where->callees; e; e = e->next_callee)
if (e->callee == node)
{
/* When profile feedback is available, prioritize by expected number
of calls. Without profile feedback we maintain simple queue
to order candidates via recursive depths. */
fibheap_insert (heap,
!max_count ? priority++
: -(e->count / ((max_count + (1<<24) - 1) / (1<<24))),
e);
}
for (e = where->callees; e; e = e->next_callee)
if (!e->inline_failed)
lookup_recursive_calls (node, e->callee, heap);
}
/* Decide on recursive inlining: in the case function has recursive calls,
inline until body size reaches given argument. */
static bool
cgraph_decide_recursive_inlining (struct cgraph_node *node)
{
int limit = PARAM_VALUE (PARAM_MAX_INLINE_INSNS_RECURSIVE_AUTO);
int max_depth = PARAM_VALUE (PARAM_MAX_INLINE_RECURSIVE_DEPTH_AUTO);
int probability = PARAM_VALUE (PARAM_MIN_INLINE_RECURSIVE_PROBABILITY);
fibheap_t heap;
struct cgraph_edge *e;
struct cgraph_node *master_clone, *next;
int depth = 0;
int n = 0;
if (optimize_size
|| (!flag_inline_functions && !DECL_DECLARED_INLINE_P (node->decl)))
return false;
if (DECL_DECLARED_INLINE_P (node->decl))
{
limit = PARAM_VALUE (PARAM_MAX_INLINE_INSNS_RECURSIVE);
max_depth = PARAM_VALUE (PARAM_MAX_INLINE_RECURSIVE_DEPTH);
}
/* Make sure that function is small enough to be considered for inlining. */
if (!max_depth
|| cgraph_estimate_size_after_inlining (1, node, node) >= limit)
return false;
heap = fibheap_new ();
lookup_recursive_calls (node, node, heap);
if (fibheap_empty (heap))
{
fibheap_delete (heap);
return false;
}
if (dump_file)
fprintf (dump_file,
" Performing recursive inlining on %s\n",
cgraph_node_name (node));
/* We need original clone to copy around. */
master_clone = cgraph_clone_node (node, node->count, CGRAPH_FREQ_BASE, 1, false);
master_clone->needed = true;
for (e = master_clone->callees; e; e = e->next_callee)
if (!e->inline_failed)
cgraph_clone_inlined_nodes (e, true, false);
/* Do the inlining and update list of recursive call during process. */
while (!fibheap_empty (heap)
&& (cgraph_estimate_size_after_inlining (1, node, master_clone)
<= limit))
{
struct cgraph_edge *curr
= (struct cgraph_edge *) fibheap_extract_min (heap);
struct cgraph_node *cnode;
depth = 1;
for (cnode = curr->caller;
cnode->global.inlined_to; cnode = cnode->callers->caller)
if (node->decl == curr->callee->decl)
depth++;
if (depth > max_depth)
{
if (dump_file)
fprintf (dump_file,
" maximal depth reached\n");
continue;
}
if (max_count)
{
if (!cgraph_maybe_hot_edge_p (curr))
{
if (dump_file)
fprintf (dump_file, " Not inlining cold call\n");
continue;
}
if (curr->count * 100 / node->count < probability)
{
if (dump_file)
fprintf (dump_file,
" Probability of edge is too small\n");
continue;
}
}
if (dump_file)
{
fprintf (dump_file,
" Inlining call of depth %i", depth);
if (node->count)
{
fprintf (dump_file, " called approx. %.2f times per call",
(double)curr->count / node->count);
}
fprintf (dump_file, "\n");
}
cgraph_redirect_edge_callee (curr, master_clone);
cgraph_mark_inline_edge (curr, false);
lookup_recursive_calls (node, curr->callee, heap);
n++;
}
if (!fibheap_empty (heap) && dump_file)
fprintf (dump_file, " Recursive inlining growth limit met.\n");
fibheap_delete (heap);
if (dump_file)
fprintf (dump_file,
"\n Inlined %i times, body grown from %i to %i insns\n", n,
master_clone->global.insns, node->global.insns);
/* Remove master clone we used for inlining. We rely that clones inlined
into master clone gets queued just before master clone so we don't
need recursion. */
for (node = cgraph_nodes; node != master_clone;
node = next)
{
next = node->next;
if (node->global.inlined_to == master_clone)
cgraph_remove_node (node);
}
cgraph_remove_node (master_clone);
/* FIXME: Recursive inlining actually reduces number of calls of the
function. At this place we should probably walk the function and
inline clones and compensate the counts accordingly. This probably
doesn't matter much in practice. */
return n > 0;
}
/* Set inline_failed for all callers of given function to REASON. */
static void
cgraph_set_inline_failed (struct cgraph_node *node, const char *reason)
{
struct cgraph_edge *e;
if (dump_file)
fprintf (dump_file, "Inlining failed: %s\n", reason);
for (e = node->callers; e; e = e->next_caller)
if (e->inline_failed)
e->inline_failed = reason;
}
/* Given whole compilation unit estimate of INSNS, compute how large we can
allow the unit to grow. */
static int
compute_max_insns (int insns)
{
int max_insns = insns;
if (max_insns < PARAM_VALUE (PARAM_LARGE_UNIT_INSNS))
max_insns = PARAM_VALUE (PARAM_LARGE_UNIT_INSNS);
return ((HOST_WIDEST_INT) max_insns
* (100 + PARAM_VALUE (PARAM_INLINE_UNIT_GROWTH)) / 100);
}
/* We use greedy algorithm for inlining of small functions:
All inline candidates are put into prioritized heap based on estimated
growth of the overall number of instructions and then update the estimates.
INLINED and INLINED_CALEES are just pointers to arrays large enough
to be passed to cgraph_inlined_into and cgraph_inlined_callees. */
static void
cgraph_decide_inlining_of_small_functions (void)
{
struct cgraph_node *node;
struct cgraph_edge *edge;
const char *failed_reason;
fibheap_t heap = fibheap_new ();
bitmap updated_nodes = BITMAP_ALLOC (NULL);
int min_insns, max_insns;
if (dump_file)
fprintf (dump_file, "\nDeciding on smaller functions:\n");
/* Put all inline candidates into the heap. */
for (node = cgraph_nodes; node; node = node->next)
{
if (!node->local.inlinable || !node->callers
|| node->local.disregard_inline_limits)
continue;
if (dump_file)
fprintf (dump_file, "Considering inline candidate %s.\n", cgraph_node_name (node));
node->global.estimated_growth = INT_MIN;
if (!cgraph_default_inline_p (node, &failed_reason))
{
cgraph_set_inline_failed (node, failed_reason);
continue;
}
for (edge = node->callers; edge; edge = edge->next_caller)
if (edge->inline_failed)
{
gcc_assert (!edge->aux);
edge->aux = fibheap_insert (heap, cgraph_edge_badness (edge), edge);
}
}
max_insns = compute_max_insns (overall_insns);
min_insns = overall_insns;
while (overall_insns <= max_insns
&& (edge = (struct cgraph_edge *) fibheap_extract_min (heap)))
{
int old_insns = overall_insns;
struct cgraph_node *where;
int growth =
cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
const char *not_good = NULL;
growth -= edge->caller->global.insns;
if (dump_file)
{
fprintf (dump_file,
"\nConsidering %s with %i insns\n",
cgraph_node_name (edge->callee),
edge->callee->global.insns);
fprintf (dump_file,
" to be inlined into %s\n"
" Estimated growth after inlined into all callees is %+i insns.\n"
" Estimated badness is %i, frequency %.2f.\n",
cgraph_node_name (edge->caller),
cgraph_estimate_growth (edge->callee),
cgraph_edge_badness (edge),
edge->frequency / (double)CGRAPH_FREQ_BASE);
if (edge->count)
fprintf (dump_file," Called "HOST_WIDEST_INT_PRINT_DEC"x\n", edge->count);
}
gcc_assert (edge->aux);
edge->aux = NULL;
if (!edge->inline_failed)
continue;
/* When not having profile info ready we don't weight by any way the
position of call in procedure itself. This means if call of
function A from function B seems profitable to inline, the recursive
call of function A in inline copy of A in B will look profitable too
and we end up inlining until reaching maximal function growth. This
is not good idea so prohibit the recursive inlining.
??? When the frequencies are taken into account we might not need this
restriction. */
if (!max_count)
{
where = edge->caller;
while (where->global.inlined_to)
{
if (where->decl == edge->callee->decl)
break;
where = where->callers->caller;
}
if (where->global.inlined_to)
{
edge->inline_failed
= (edge->callee->local.disregard_inline_limits ? N_("recursive inlining") : "");
if (dump_file)
fprintf (dump_file, " inline_failed:Recursive inlining performed only for function itself.\n");
continue;
}
}
if (!cgraph_maybe_hot_edge_p (edge))
not_good = N_("call is unlikely and code size would grow");
if (!flag_inline_functions
&& !DECL_DECLARED_INLINE_P (edge->callee->decl))
not_good = N_("function not declared inline and code size would grow");
if (optimize_size)
not_good = N_("optimizing for size and code size would grow");
if (not_good && growth > 0)
{
if (!cgraph_recursive_inlining_p (edge->caller, edge->callee,
&edge->inline_failed))
{
edge->inline_failed = not_good;
if (dump_file)
fprintf (dump_file, " inline_failed:%s.\n", edge->inline_failed);
}
continue;
}
if (!cgraph_default_inline_p (edge->callee, &edge->inline_failed))
{
if (!cgraph_recursive_inlining_p (edge->caller, edge->callee,
&edge->inline_failed))
{
if (dump_file)
fprintf (dump_file, " inline_failed:%s.\n", edge->inline_failed);
}
continue;
}
if (cgraph_recursive_inlining_p (edge->caller, edge->callee,
&edge->inline_failed))
{
where = edge->caller;
if (where->global.inlined_to)
where = where->global.inlined_to;
if (!cgraph_decide_recursive_inlining (where))
continue;
update_callee_keys (heap, where, updated_nodes);
}
else
{
struct cgraph_node *callee;
if (CALL_CANNOT_INLINE_P (edge->call_stmt)
|| !cgraph_check_inline_limits (edge->caller, edge->callee,
&edge->inline_failed, true))
{
if (dump_file)
fprintf (dump_file, " Not inlining into %s:%s.\n",
cgraph_node_name (edge->caller), edge->inline_failed);
continue;
}
callee = edge->callee;
cgraph_mark_inline_edge (edge, true);
update_callee_keys (heap, callee, updated_nodes);
}
where = edge->caller;
if (where->global.inlined_to)
where = where->global.inlined_to;
/* Our profitability metric can depend on local properties
such as number of inlinable calls and size of the function body.
After inlining these properties might change for the function we
inlined into (since it's body size changed) and for the functions
called by function we inlined (since number of it inlinable callers
might change). */
update_caller_keys (heap, where, updated_nodes);
bitmap_clear (updated_nodes);
if (dump_file)
{
fprintf (dump_file,
" Inlined into %s which now has %i insns,"
"net change of %+i insns.\n",
cgraph_node_name (edge->caller),
edge->caller->global.insns,
overall_insns - old_insns);
}
if (min_insns > overall_insns)
{
min_insns = overall_insns;
max_insns = compute_max_insns (min_insns);
if (dump_file)
fprintf (dump_file, "New minimal insns reached: %i\n", min_insns);
}
}
while ((edge = (struct cgraph_edge *) fibheap_extract_min (heap)) != NULL)
{
gcc_assert (edge->aux);
edge->aux = NULL;
if (!edge->callee->local.disregard_inline_limits && edge->inline_failed
&& !cgraph_recursive_inlining_p (edge->caller, edge->callee,
&edge->inline_failed))
edge->inline_failed = N_("--param inline-unit-growth limit reached");
}
fibheap_delete (heap);
BITMAP_FREE (updated_nodes);
}
/* Decide on the inlining. We do so in the topological order to avoid
expenses on updating data structures. */
static unsigned int
cgraph_decide_inlining (void)
{
struct cgraph_node *node;
int nnodes;
struct cgraph_node **order =
XCNEWVEC (struct cgraph_node *, cgraph_n_nodes);
int old_insns = 0;
int i;
int initial_insns = 0;
max_count = 0;
for (node = cgraph_nodes; node; node = node->next)
if (node->analyzed && (node->needed || node->reachable))
{
struct cgraph_edge *e;
initial_insns += node->local.self_insns;
gcc_assert (node->local.self_insns == node->global.insns);
for (e = node->callees; e; e = e->next_callee)
if (max_count < e->count)
max_count = e->count;
}
overall_insns = initial_insns;
gcc_assert (!max_count || (profile_info && flag_branch_probabilities));
nnodes = cgraph_postorder (order);
if (dump_file)
fprintf (dump_file,
"\nDeciding on inlining. Starting with %i insns.\n",
initial_insns);
for (node = cgraph_nodes; node; node = node->next)
node->aux = 0;
if (dump_file)
fprintf (dump_file, "\nInlining always_inline functions:\n");
/* In the first pass mark all always_inline edges. Do this with a priority
so none of our later choices will make this impossible. */
for (i = nnodes - 1; i >= 0; i--)
{
struct cgraph_edge *e, *next;
node = order[i];
/* Handle nodes to be flattened, but don't update overall unit size. */
if (lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
{
if (dump_file)
fprintf (dump_file,
"Flattening %s\n", cgraph_node_name (node));
cgraph_decide_inlining_incrementally (node, INLINE_ALL, 0);
}
if (!node->local.disregard_inline_limits)
continue;
if (dump_file)
fprintf (dump_file,
"\nConsidering %s %i insns (always inline)\n",
cgraph_node_name (node), node->global.insns);
old_insns = overall_insns;
for (e = node->callers; e; e = next)
{
next = e->next_caller;
if (!e->inline_failed || CALL_CANNOT_INLINE_P (e->call_stmt))
continue;
if (cgraph_recursive_inlining_p (e->caller, e->callee,
&e->inline_failed))
continue;
cgraph_mark_inline_edge (e, true);
if (dump_file)
fprintf (dump_file,
" Inlined into %s which now has %i insns.\n",
cgraph_node_name (e->caller),
e->caller->global.insns);
}
/* Inlining self recursive function might introduce new calls to
themselves we didn't see in the loop above. Fill in the proper
reason why inline failed. */
for (e = node->callers; e; e = e->next_caller)
if (e->inline_failed)
e->inline_failed = N_("recursive inlining");
if (dump_file)
fprintf (dump_file,
" Inlined for a net change of %+i insns.\n",
overall_insns - old_insns);
}
if (!flag_really_no_inline)
cgraph_decide_inlining_of_small_functions ();
if (!flag_really_no_inline
&& flag_inline_functions_called_once)
{
if (dump_file)
fprintf (dump_file, "\nDeciding on functions called once:\n");
/* And finally decide what functions are called once. */
for (i = nnodes - 1; i >= 0; i--)
{
node = order[i];
if (node->callers && !node->callers->next_caller && !node->needed
&& node->local.inlinable && node->callers->inline_failed
&& !CALL_CANNOT_INLINE_P (node->callers->call_stmt)
&& !DECL_EXTERNAL (node->decl) && !DECL_COMDAT (node->decl))
{
if (dump_file)
{
fprintf (dump_file,
"\nConsidering %s %i insns.\n",
cgraph_node_name (node), node->global.insns);
fprintf (dump_file,
" Called once from %s %i insns.\n",
cgraph_node_name (node->callers->caller),
node->callers->caller->global.insns);
}
old_insns = overall_insns;
if (cgraph_check_inline_limits (node->callers->caller, node,
NULL, false))
{
cgraph_mark_inline (node->callers);
if (dump_file)
fprintf (dump_file,
" Inlined into %s which now has %i insns"
" for a net change of %+i insns.\n",
cgraph_node_name (node->callers->caller),
node->callers->caller->global.insns,
overall_insns - old_insns);
}
else
{
if (dump_file)
fprintf (dump_file,
" Inline limit reached, not inlined.\n");
}
}
}
}
if (dump_file)
fprintf (dump_file,
"\nInlined %i calls, eliminated %i functions, "
"%i insns turned to %i insns.\n\n",
ncalls_inlined, nfunctions_inlined, initial_insns,
overall_insns);
free (order);
return 0;
}
/* Try to inline edge E from incremental inliner. MODE specifies mode
of inliner.
We are detecting cycles by storing mode of inliner into cgraph_node last
time we visited it in the recursion. In general when mode is set, we have
recursive inlining, but as an special case, we want to try harder inline
ALWAYS_INLINE functions: consider callgraph a->b->c->b, with a being
flatten, b being always inline. Flattening 'a' will collapse
a->b->c before hitting cycle. To accommodate always inline, we however
need to inline a->b->c->b.
So after hitting cycle first time, we switch into ALWAYS_INLINE mode and
stop inlining only after hitting ALWAYS_INLINE in ALWAY_INLINE mode. */
static bool
try_inline (struct cgraph_edge *e, enum inlining_mode mode, int depth)
{
struct cgraph_node *callee = e->callee;
enum inlining_mode callee_mode = (enum inlining_mode) (size_t) callee->aux;
bool always_inline = e->callee->local.disregard_inline_limits;
/* We've hit cycle? */
if (callee_mode)
{
/* It is first time we see it and we are not in ALWAY_INLINE only
mode yet. and the function in question is always_inline. */
if (always_inline && mode != INLINE_ALWAYS_INLINE)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Hit cycle in %s, switching to always inline only.\n",
cgraph_node_name (callee));
}
mode = INLINE_ALWAYS_INLINE;
}
/* Otherwise it is time to give up. */
else
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Not inlining %s into %s to avoid cycle.\n",
cgraph_node_name (callee),
cgraph_node_name (e->caller));
}
e->inline_failed = (e->callee->local.disregard_inline_limits
? N_("recursive inlining") : "");
return false;
}
}
callee->aux = (void *)(size_t) mode;
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, " Inlining %s into %s.\n",
cgraph_node_name (e->callee),
cgraph_node_name (e->caller));
}
if (e->inline_failed)
cgraph_mark_inline (e);
/* In order to fully inline always_inline functions at -O0, we need to
recurse here, since the inlined functions might not be processed by
incremental inlining at all yet.
Also flattening needs to be done recursively. */
if (!flag_unit_at_a_time || mode == INLINE_ALL || always_inline)
cgraph_decide_inlining_incrementally (e->callee, mode, depth + 1);
callee->aux = (void *)(size_t) callee_mode;
return true;
}
/* Decide on the inlining. We do so in the topological order to avoid
expenses on updating data structures.
DEPTH is depth of recursion, used only for debug output. */
static bool
cgraph_decide_inlining_incrementally (struct cgraph_node *node,
enum inlining_mode mode,
int depth)
{
struct cgraph_edge *e;
bool inlined = false;
const char *failed_reason;
enum inlining_mode old_mode;
#ifdef ENABLE_CHECKING
verify_cgraph_node (node);
#endif
old_mode = (enum inlining_mode) (size_t)node->aux;
if (mode != INLINE_ALWAYS_INLINE
&& lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Flattening %s\n", cgraph_node_name (node));
}
mode = INLINE_ALL;
}
node->aux = (void *)(size_t) mode;
/* First of all look for always inline functions. */
for (e = node->callees; e; e = e->next_callee)
{
if (!e->callee->local.disregard_inline_limits
&& (mode != INLINE_ALL || !e->callee->local.inlinable))
continue;
if (CALL_CANNOT_INLINE_P (e->call_stmt))
continue;
/* When the edge is already inlined, we just need to recurse into
it in order to fully flatten the leaves. */
if (!e->inline_failed && mode == INLINE_ALL)
{
inlined |= try_inline (e, mode, depth);
continue;
}
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Considering to always inline inline candidate %s.\n",
cgraph_node_name (e->callee));
}
if (cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed))
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Not inlining: recursive call.\n");
}
continue;
}
if (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
!= gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Not inlining: SSA form does not match.\n");
}
continue;
}
if (!DECL_SAVED_TREE (e->callee->decl) && !e->callee->inline_decl)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Not inlining: Function body no longer available.\n");
}
continue;
}
inlined |= try_inline (e, mode, depth);
}
/* Now do the automatic inlining. */
if (!flag_really_no_inline && mode != INLINE_ALL
&& mode != INLINE_ALWAYS_INLINE)
for (e = node->callees; e; e = e->next_callee)
{
if (!e->callee->local.inlinable
|| !e->inline_failed
|| e->callee->local.disregard_inline_limits)
continue;
if (dump_file)
fprintf (dump_file, "Considering inline candidate %s.\n",
cgraph_node_name (e->callee));
if (cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed))
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Not inlining: recursive call.\n");
}
continue;
}
if (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
!= gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Not inlining: SSA form does not match.\n");
}
continue;
}
/* When the function body would grow and inlining the function won't
eliminate the need for offline copy of the function, don't inline.
*/
if ((mode == INLINE_SIZE
|| (!flag_inline_functions
&& !DECL_DECLARED_INLINE_P (e->callee->decl)))
&& (cgraph_estimate_size_after_inlining (1, e->caller, e->callee)
> e->caller->global.insns)
&& cgraph_estimate_growth (e->callee) > 0)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Not inlining: code size would grow by %i insns.\n",
cgraph_estimate_size_after_inlining (1, e->caller,
e->callee)
- e->caller->global.insns);
}
continue;
}
if (!cgraph_check_inline_limits (node, e->callee, &e->inline_failed,
false)
|| CALL_CANNOT_INLINE_P (e->call_stmt))
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file, "Not inlining: %s.\n", e->inline_failed);
}
continue;
}
if (!DECL_SAVED_TREE (e->callee->decl) && !e->callee->inline_decl)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
"Not inlining: Function body no longer available.\n");
}
continue;
}
if (cgraph_default_inline_p (e->callee, &failed_reason))
inlined |= try_inline (e, mode, depth);
else if (!flag_unit_at_a_time)
e->inline_failed = failed_reason;
}
node->aux = (void *)(size_t) old_mode;
return inlined;
}
/* When inlining shall be performed. */
static bool
cgraph_gate_inlining (void)
{
return flag_inline_trees;
}
struct tree_opt_pass pass_ipa_inline =
{
"inline", /* name */
cgraph_gate_inlining, /* gate */
cgraph_decide_inlining, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
TODO_remove_functions, /* todo_flags_finish */
TODO_dump_cgraph | TODO_dump_func
| TODO_remove_functions, /* todo_flags_finish */
0 /* letter */
};
/* Because inlining might remove no-longer reachable nodes, we need to
keep the array visible to garbage collector to avoid reading collected
out nodes. */
static int nnodes;
static GTY ((length ("nnodes"))) struct cgraph_node **order;
/* Do inlining of small functions. Doing so early helps profiling and other
passes to be somewhat more effective and avoids some code duplication in
later real inlining pass for testcases with very many function calls. */
static unsigned int
cgraph_early_inlining (void)
{
struct cgraph_node *node = cgraph_node (current_function_decl);
unsigned int todo = 0;
if (sorrycount || errorcount)
return 0;
if (cgraph_decide_inlining_incrementally (node,
flag_unit_at_a_time || optimize_size
? INLINE_SIZE : INLINE_SPEED, 0))
{
timevar_push (TV_INTEGRATION);
todo = optimize_inline_calls (current_function_decl);
timevar_pop (TV_INTEGRATION);
}
return todo;
}
/* When inlining shall be performed. */
static bool
cgraph_gate_early_inlining (void)
{
return flag_inline_trees && flag_early_inlining;
}
struct tree_opt_pass pass_early_inline =
{
"einline", /* name */
cgraph_gate_early_inlining, /* gate */
cgraph_early_inlining, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_dump_func, /* todo_flags_finish */
0 /* letter */
};
/* When inlining shall be performed. */
static bool
cgraph_gate_ipa_early_inlining (void)
{
return (flag_inline_trees && flag_early_inlining
&& (flag_branch_probabilities || flag_test_coverage
|| profile_arc_flag));
}
/* IPA pass wrapper for early inlining pass. We need to run early inlining
before tree profiling so we have stand alone IPA pass for doing so. */
struct tree_opt_pass pass_ipa_early_inline =
{
"einline_ipa", /* name */
cgraph_gate_ipa_early_inlining, /* gate */
NULL, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_dump_cgraph, /* todo_flags_finish */
0 /* letter */
};
/* Compute parameters of functions used by inliner. */
static unsigned int
compute_inline_parameters (void)
{
struct cgraph_node *node = cgraph_node (current_function_decl);
gcc_assert (!node->global.inlined_to);
node->local.estimated_self_stack_size = estimated_stack_frame_size ();
node->global.estimated_stack_size = node->local.estimated_self_stack_size;
node->global.stack_frame_offset = 0;
node->local.inlinable = tree_inlinable_function_p (current_function_decl);
node->local.self_insns = estimate_num_insns (current_function_decl,
&eni_inlining_weights);
if (node->local.inlinable && !node->local.disregard_inline_limits)
node->local.disregard_inline_limits
= DECL_DISREGARD_INLINE_LIMITS (current_function_decl);
if (flag_really_no_inline && !node->local.disregard_inline_limits)
node->local.inlinable = 0;
/* Inlining characteristics are maintained by the cgraph_mark_inline. */
node->global.insns = node->local.self_insns;
return 0;
}
/* When inlining shall be performed. */
static bool
gate_inline_passes (void)
{
return flag_inline_trees;
}
struct tree_opt_pass pass_inline_parameters =
{
NULL, /* name */
gate_inline_passes, /* gate */
compute_inline_parameters, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
0, /* todo_flags_finish */
0 /* letter */
};
/* Apply inline plan to the function. */
static unsigned int
apply_inline (void)
{
unsigned int todo = 0;
struct cgraph_edge *e;
struct cgraph_node *node = cgraph_node (current_function_decl);
/* Even when not optimizing, ensure that always_inline functions get inlined.
*/
if (!optimize)
cgraph_decide_inlining_incrementally (node, INLINE_SPEED, 0);
/* We might need the body of this function so that we can expand
it inline somewhere else. */
if (cgraph_preserve_function_body_p (current_function_decl))
save_inline_function_body (node);
for (e = node->callees; e; e = e->next_callee)
if (!e->inline_failed || warn_inline)
break;
if (e)
{
timevar_push (TV_INTEGRATION);
todo = optimize_inline_calls (current_function_decl);
timevar_pop (TV_INTEGRATION);
}
/* In non-unit-at-a-time we must mark all referenced functions as needed. */
if (!flag_unit_at_a_time)
{
struct cgraph_edge *e;
for (e = node->callees; e; e = e->next_callee)
if (e->callee->analyzed)
cgraph_mark_needed_node (e->callee);
}
return todo | execute_fixup_cfg ();
}
struct tree_opt_pass pass_apply_inline =
{
"apply_inline", /* name */
NULL, /* gate */
apply_inline, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_dump_func | TODO_verify_flow
| TODO_verify_stmts, /* todo_flags_finish */
0 /* letter */
};
#include "gt-ipa-inline.h"
|