forked from illumos/gcc
-
Notifications
You must be signed in to change notification settings - Fork 1
/
tree-vect-loop.c
5488 lines (4681 loc) · 184 KB
/
tree-vect-loop.c
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
/* Loop Vectorization
Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012
Free Software Foundation, Inc.
Contributed by Dorit Naishlos <dorit@il.ibm.com> and
Ira Rosen <irar@il.ibm.com>
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/>. */
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "ggc.h"
#include "tree.h"
#include "basic-block.h"
#include "tree-pretty-print.h"
#include "gimple-pretty-print.h"
#include "tree-flow.h"
#include "tree-dump.h"
#include "cfgloop.h"
#include "cfglayout.h"
#include "expr.h"
#include "recog.h"
#include "optabs.h"
#include "params.h"
#include "diagnostic-core.h"
#include "tree-chrec.h"
#include "tree-scalar-evolution.h"
#include "tree-vectorizer.h"
#include "target.h"
/* Loop Vectorization Pass.
This pass tries to vectorize loops.
For example, the vectorizer transforms the following simple loop:
short a[N]; short b[N]; short c[N]; int i;
for (i=0; i<N; i++){
a[i] = b[i] + c[i];
}
as if it was manually vectorized by rewriting the source code into:
typedef int __attribute__((mode(V8HI))) v8hi;
short a[N]; short b[N]; short c[N]; int i;
v8hi *pa = (v8hi*)a, *pb = (v8hi*)b, *pc = (v8hi*)c;
v8hi va, vb, vc;
for (i=0; i<N/8; i++){
vb = pb[i];
vc = pc[i];
va = vb + vc;
pa[i] = va;
}
The main entry to this pass is vectorize_loops(), in which
the vectorizer applies a set of analyses on a given set of loops,
followed by the actual vectorization transformation for the loops that
had successfully passed the analysis phase.
Throughout this pass we make a distinction between two types of
data: scalars (which are represented by SSA_NAMES), and memory references
("data-refs"). These two types of data require different handling both
during analysis and transformation. The types of data-refs that the
vectorizer currently supports are ARRAY_REFS which base is an array DECL
(not a pointer), and INDIRECT_REFS through pointers; both array and pointer
accesses are required to have a simple (consecutive) access pattern.
Analysis phase:
===============
The driver for the analysis phase is vect_analyze_loop().
It applies a set of analyses, some of which rely on the scalar evolution
analyzer (scev) developed by Sebastian Pop.
During the analysis phase the vectorizer records some information
per stmt in a "stmt_vec_info" struct which is attached to each stmt in the
loop, as well as general information about the loop as a whole, which is
recorded in a "loop_vec_info" struct attached to each loop.
Transformation phase:
=====================
The loop transformation phase scans all the stmts in the loop, and
creates a vector stmt (or a sequence of stmts) for each scalar stmt S in
the loop that needs to be vectorized. It inserts the vector code sequence
just before the scalar stmt S, and records a pointer to the vector code
in STMT_VINFO_VEC_STMT (stmt_info) (stmt_info is the stmt_vec_info struct
attached to S). This pointer will be used for the vectorization of following
stmts which use the def of stmt S. Stmt S is removed if it writes to memory;
otherwise, we rely on dead code elimination for removing it.
For example, say stmt S1 was vectorized into stmt VS1:
VS1: vb = px[i];
S1: b = x[i]; STMT_VINFO_VEC_STMT (stmt_info (S1)) = VS1
S2: a = b;
To vectorize stmt S2, the vectorizer first finds the stmt that defines
the operand 'b' (S1), and gets the relevant vector def 'vb' from the
vector stmt VS1 pointed to by STMT_VINFO_VEC_STMT (stmt_info (S1)). The
resulting sequence would be:
VS1: vb = px[i];
S1: b = x[i]; STMT_VINFO_VEC_STMT (stmt_info (S1)) = VS1
VS2: va = vb;
S2: a = b; STMT_VINFO_VEC_STMT (stmt_info (S2)) = VS2
Operands that are not SSA_NAMEs, are data-refs that appear in
load/store operations (like 'x[i]' in S1), and are handled differently.
Target modeling:
=================
Currently the only target specific information that is used is the
size of the vector (in bytes) - "TARGET_VECTORIZE_UNITS_PER_SIMD_WORD".
Targets that can support different sizes of vectors, for now will need
to specify one value for "TARGET_VECTORIZE_UNITS_PER_SIMD_WORD". More
flexibility will be added in the future.
Since we only vectorize operations which vector form can be
expressed using existing tree codes, to verify that an operation is
supported, the vectorizer checks the relevant optab at the relevant
machine_mode (e.g, optab_handler (add_optab, V8HImode)). If
the value found is CODE_FOR_nothing, then there's no target support, and
we can't vectorize the stmt.
For additional information on this project see:
http://gcc.gnu.org/projects/tree-ssa/vectorization.html
*/
/* Function vect_determine_vectorization_factor
Determine the vectorization factor (VF). VF is the number of data elements
that are operated upon in parallel in a single iteration of the vectorized
loop. For example, when vectorizing a loop that operates on 4byte elements,
on a target with vector size (VS) 16byte, the VF is set to 4, since 4
elements can fit in a single vector register.
We currently support vectorization of loops in which all types operated upon
are of the same size. Therefore this function currently sets VF according to
the size of the types operated upon, and fails if there are multiple sizes
in the loop.
VF is also the factor by which the loop iterations are strip-mined, e.g.:
original loop:
for (i=0; i<N; i++){
a[i] = b[i] + c[i];
}
vectorized loop:
for (i=0; i<N; i+=VF){
a[i:VF] = b[i:VF] + c[i:VF];
}
*/
static bool
vect_determine_vectorization_factor (loop_vec_info loop_vinfo)
{
struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
basic_block *bbs = LOOP_VINFO_BBS (loop_vinfo);
int nbbs = loop->num_nodes;
gimple_stmt_iterator si;
unsigned int vectorization_factor = 0;
tree scalar_type;
gimple phi;
tree vectype;
unsigned int nunits;
stmt_vec_info stmt_info;
int i;
HOST_WIDE_INT dummy;
gimple stmt, pattern_stmt = NULL;
gimple_seq pattern_def_seq = NULL;
gimple_stmt_iterator pattern_def_si = gsi_start (NULL);
bool analyze_pattern_stmt = false;
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "=== vect_determine_vectorization_factor ===");
for (i = 0; i < nbbs; i++)
{
basic_block bb = bbs[i];
for (si = gsi_start_phis (bb); !gsi_end_p (si); gsi_next (&si))
{
phi = gsi_stmt (si);
stmt_info = vinfo_for_stmt (phi);
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "==> examining phi: ");
print_gimple_stmt (vect_dump, phi, 0, TDF_SLIM);
}
gcc_assert (stmt_info);
if (STMT_VINFO_RELEVANT_P (stmt_info))
{
gcc_assert (!STMT_VINFO_VECTYPE (stmt_info));
scalar_type = TREE_TYPE (PHI_RESULT (phi));
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "get vectype for scalar type: ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
vectype = get_vectype_for_scalar_type (scalar_type);
if (!vectype)
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump,
"not vectorized: unsupported data-type ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
return false;
}
STMT_VINFO_VECTYPE (stmt_info) = vectype;
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "vectype: ");
print_generic_expr (vect_dump, vectype, TDF_SLIM);
}
nunits = TYPE_VECTOR_SUBPARTS (vectype);
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "nunits = %d", nunits);
if (!vectorization_factor
|| (nunits > vectorization_factor))
vectorization_factor = nunits;
}
}
for (si = gsi_start_bb (bb); !gsi_end_p (si) || analyze_pattern_stmt;)
{
tree vf_vectype;
if (analyze_pattern_stmt)
stmt = pattern_stmt;
else
stmt = gsi_stmt (si);
stmt_info = vinfo_for_stmt (stmt);
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "==> examining statement: ");
print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
}
gcc_assert (stmt_info);
/* Skip stmts which do not need to be vectorized. */
if (!STMT_VINFO_RELEVANT_P (stmt_info)
&& !STMT_VINFO_LIVE_P (stmt_info))
{
if (STMT_VINFO_IN_PATTERN_P (stmt_info)
&& (pattern_stmt = STMT_VINFO_RELATED_STMT (stmt_info))
&& (STMT_VINFO_RELEVANT_P (vinfo_for_stmt (pattern_stmt))
|| STMT_VINFO_LIVE_P (vinfo_for_stmt (pattern_stmt))))
{
stmt = pattern_stmt;
stmt_info = vinfo_for_stmt (pattern_stmt);
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "==> examining pattern statement: ");
print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
}
}
else
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "skip.");
gsi_next (&si);
continue;
}
}
else if (STMT_VINFO_IN_PATTERN_P (stmt_info)
&& (pattern_stmt = STMT_VINFO_RELATED_STMT (stmt_info))
&& (STMT_VINFO_RELEVANT_P (vinfo_for_stmt (pattern_stmt))
|| STMT_VINFO_LIVE_P (vinfo_for_stmt (pattern_stmt))))
analyze_pattern_stmt = true;
/* If a pattern statement has def stmts, analyze them too. */
if (is_pattern_stmt_p (stmt_info))
{
if (pattern_def_seq == NULL)
{
pattern_def_seq = STMT_VINFO_PATTERN_DEF_SEQ (stmt_info);
pattern_def_si = gsi_start (pattern_def_seq);
}
else if (!gsi_end_p (pattern_def_si))
gsi_next (&pattern_def_si);
if (pattern_def_seq != NULL)
{
gimple pattern_def_stmt = NULL;
stmt_vec_info pattern_def_stmt_info = NULL;
while (!gsi_end_p (pattern_def_si))
{
pattern_def_stmt = gsi_stmt (pattern_def_si);
pattern_def_stmt_info
= vinfo_for_stmt (pattern_def_stmt);
if (STMT_VINFO_RELEVANT_P (pattern_def_stmt_info)
|| STMT_VINFO_LIVE_P (pattern_def_stmt_info))
break;
gsi_next (&pattern_def_si);
}
if (!gsi_end_p (pattern_def_si))
{
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump,
"==> examining pattern def stmt: ");
print_gimple_stmt (vect_dump, pattern_def_stmt, 0,
TDF_SLIM);
}
stmt = pattern_def_stmt;
stmt_info = pattern_def_stmt_info;
}
else
{
pattern_def_si = gsi_start (NULL);
analyze_pattern_stmt = false;
}
}
else
analyze_pattern_stmt = false;
}
if (gimple_get_lhs (stmt) == NULL_TREE)
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump, "not vectorized: irregular stmt.");
print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
}
return false;
}
if (VECTOR_MODE_P (TYPE_MODE (gimple_expr_type (stmt))))
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump, "not vectorized: vector stmt in loop:");
print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
}
return false;
}
if (STMT_VINFO_VECTYPE (stmt_info))
{
/* The only case when a vectype had been already set is for stmts
that contain a dataref, or for "pattern-stmts" (stmts
generated by the vectorizer to represent/replace a certain
idiom). */
gcc_assert (STMT_VINFO_DATA_REF (stmt_info)
|| is_pattern_stmt_p (stmt_info)
|| !gsi_end_p (pattern_def_si));
vectype = STMT_VINFO_VECTYPE (stmt_info);
}
else
{
gcc_assert (!STMT_VINFO_DATA_REF (stmt_info));
scalar_type = TREE_TYPE (gimple_get_lhs (stmt));
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "get vectype for scalar type: ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
vectype = get_vectype_for_scalar_type (scalar_type);
if (!vectype)
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump,
"not vectorized: unsupported data-type ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
return false;
}
STMT_VINFO_VECTYPE (stmt_info) = vectype;
}
/* The vectorization factor is according to the smallest
scalar type (or the largest vector size, but we only
support one vector size per loop). */
scalar_type = vect_get_smallest_scalar_type (stmt, &dummy,
&dummy);
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "get vectype for scalar type: ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
vf_vectype = get_vectype_for_scalar_type (scalar_type);
if (!vf_vectype)
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump,
"not vectorized: unsupported data-type ");
print_generic_expr (vect_dump, scalar_type, TDF_SLIM);
}
return false;
}
if ((GET_MODE_SIZE (TYPE_MODE (vectype))
!= GET_MODE_SIZE (TYPE_MODE (vf_vectype))))
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
{
fprintf (vect_dump,
"not vectorized: different sized vector "
"types in statement, ");
print_generic_expr (vect_dump, vectype, TDF_SLIM);
fprintf (vect_dump, " and ");
print_generic_expr (vect_dump, vf_vectype, TDF_SLIM);
}
return false;
}
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "vectype: ");
print_generic_expr (vect_dump, vf_vectype, TDF_SLIM);
}
nunits = TYPE_VECTOR_SUBPARTS (vf_vectype);
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "nunits = %d", nunits);
if (!vectorization_factor
|| (nunits > vectorization_factor))
vectorization_factor = nunits;
if (!analyze_pattern_stmt && gsi_end_p (pattern_def_si))
{
pattern_def_seq = NULL;
gsi_next (&si);
}
}
}
/* TODO: Analyze cost. Decide if worth while to vectorize. */
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "vectorization factor = %d", vectorization_factor);
if (vectorization_factor <= 1)
{
if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
fprintf (vect_dump, "not vectorized: unsupported data-type");
return false;
}
LOOP_VINFO_VECT_FACTOR (loop_vinfo) = vectorization_factor;
return true;
}
/* Function vect_is_simple_iv_evolution.
FORNOW: A simple evolution of an induction variables in the loop is
considered a polynomial evolution with constant step. */
static bool
vect_is_simple_iv_evolution (unsigned loop_nb, tree access_fn, tree * init,
tree * step)
{
tree init_expr;
tree step_expr;
tree evolution_part = evolution_part_in_loop_num (access_fn, loop_nb);
/* When there is no evolution in this loop, the evolution function
is not "simple". */
if (evolution_part == NULL_TREE)
return false;
/* When the evolution is a polynomial of degree >= 2
the evolution function is not "simple". */
if (tree_is_chrec (evolution_part))
return false;
step_expr = evolution_part;
init_expr = unshare_expr (initial_condition_in_loop_num (access_fn, loop_nb));
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "step: ");
print_generic_expr (vect_dump, step_expr, TDF_SLIM);
fprintf (vect_dump, ", init: ");
print_generic_expr (vect_dump, init_expr, TDF_SLIM);
}
*init = init_expr;
*step = step_expr;
if (TREE_CODE (step_expr) != INTEGER_CST)
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "step unknown.");
return false;
}
return true;
}
/* Function vect_analyze_scalar_cycles_1.
Examine the cross iteration def-use cycles of scalar variables
in LOOP. LOOP_VINFO represents the loop that is now being
considered for vectorization (can be LOOP, or an outer-loop
enclosing LOOP). */
static void
vect_analyze_scalar_cycles_1 (loop_vec_info loop_vinfo, struct loop *loop)
{
basic_block bb = loop->header;
tree dumy;
VEC(gimple,heap) *worklist = VEC_alloc (gimple, heap, 64);
gimple_stmt_iterator gsi;
bool double_reduc;
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "=== vect_analyze_scalar_cycles ===");
/* First - identify all inductions. Reduction detection assumes that all the
inductions have been identified, therefore, this order must not be
changed. */
for (gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
gimple phi = gsi_stmt (gsi);
tree access_fn = NULL;
tree def = PHI_RESULT (phi);
stmt_vec_info stmt_vinfo = vinfo_for_stmt (phi);
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "Analyze phi: ");
print_gimple_stmt (vect_dump, phi, 0, TDF_SLIM);
}
/* Skip virtual phi's. The data dependences that are associated with
virtual defs/uses (i.e., memory accesses) are analyzed elsewhere. */
if (!is_gimple_reg (SSA_NAME_VAR (def)))
continue;
STMT_VINFO_DEF_TYPE (stmt_vinfo) = vect_unknown_def_type;
/* Analyze the evolution function. */
access_fn = analyze_scalar_evolution (loop, def);
if (access_fn)
STRIP_NOPS (access_fn);
if (access_fn && vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "Access function of PHI: ");
print_generic_expr (vect_dump, access_fn, TDF_SLIM);
}
if (!access_fn
|| !vect_is_simple_iv_evolution (loop->num, access_fn, &dumy, &dumy))
{
VEC_safe_push (gimple, heap, worklist, phi);
continue;
}
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "Detected induction.");
STMT_VINFO_DEF_TYPE (stmt_vinfo) = vect_induction_def;
}
/* Second - identify all reductions and nested cycles. */
while (VEC_length (gimple, worklist) > 0)
{
gimple phi = VEC_pop (gimple, worklist);
tree def = PHI_RESULT (phi);
stmt_vec_info stmt_vinfo = vinfo_for_stmt (phi);
gimple reduc_stmt;
bool nested_cycle;
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "Analyze phi: ");
print_gimple_stmt (vect_dump, phi, 0, TDF_SLIM);
}
gcc_assert (is_gimple_reg (SSA_NAME_VAR (def)));
gcc_assert (STMT_VINFO_DEF_TYPE (stmt_vinfo) == vect_unknown_def_type);
nested_cycle = (loop != LOOP_VINFO_LOOP (loop_vinfo));
reduc_stmt = vect_force_simple_reduction (loop_vinfo, phi, !nested_cycle,
&double_reduc);
if (reduc_stmt)
{
if (double_reduc)
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "Detected double reduction.");
STMT_VINFO_DEF_TYPE (stmt_vinfo) = vect_double_reduction_def;
STMT_VINFO_DEF_TYPE (vinfo_for_stmt (reduc_stmt)) =
vect_double_reduction_def;
}
else
{
if (nested_cycle)
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "Detected vectorizable nested cycle.");
STMT_VINFO_DEF_TYPE (stmt_vinfo) = vect_nested_cycle;
STMT_VINFO_DEF_TYPE (vinfo_for_stmt (reduc_stmt)) =
vect_nested_cycle;
}
else
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "Detected reduction.");
STMT_VINFO_DEF_TYPE (stmt_vinfo) = vect_reduction_def;
STMT_VINFO_DEF_TYPE (vinfo_for_stmt (reduc_stmt)) =
vect_reduction_def;
/* Store the reduction cycles for possible vectorization in
loop-aware SLP. */
VEC_safe_push (gimple, heap,
LOOP_VINFO_REDUCTIONS (loop_vinfo),
reduc_stmt);
}
}
}
else
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "Unknown def-use cycle pattern.");
}
VEC_free (gimple, heap, worklist);
}
/* Function vect_analyze_scalar_cycles.
Examine the cross iteration def-use cycles of scalar variables, by
analyzing the loop-header PHIs of scalar variables. Classify each
cycle as one of the following: invariant, induction, reduction, unknown.
We do that for the loop represented by LOOP_VINFO, and also to its
inner-loop, if exists.
Examples for scalar cycles:
Example1: reduction:
loop1:
for (i=0; i<N; i++)
sum += a[i];
Example2: induction:
loop2:
for (i=0; i<N; i++)
a[i] = i; */
static void
vect_analyze_scalar_cycles (loop_vec_info loop_vinfo)
{
struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
vect_analyze_scalar_cycles_1 (loop_vinfo, loop);
/* When vectorizing an outer-loop, the inner-loop is executed sequentially.
Reductions in such inner-loop therefore have different properties than
the reductions in the nest that gets vectorized:
1. When vectorized, they are executed in the same order as in the original
scalar loop, so we can't change the order of computation when
vectorizing them.
2. FIXME: Inner-loop reductions can be used in the inner-loop, so the
current checks are too strict. */
if (loop->inner)
vect_analyze_scalar_cycles_1 (loop_vinfo, loop->inner);
}
/* Function vect_get_loop_niters.
Determine how many iterations the loop is executed.
If an expression that represents the number of iterations
can be constructed, place it in NUMBER_OF_ITERATIONS.
Return the loop exit condition. */
static gimple
vect_get_loop_niters (struct loop *loop, tree *number_of_iterations)
{
tree niters;
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "=== get_loop_niters ===");
niters = number_of_exit_cond_executions (loop);
if (niters != NULL_TREE
&& niters != chrec_dont_know)
{
*number_of_iterations = niters;
if (vect_print_dump_info (REPORT_DETAILS))
{
fprintf (vect_dump, "==> get_loop_niters:" );
print_generic_expr (vect_dump, *number_of_iterations, TDF_SLIM);
}
}
return get_loop_exit_condition (loop);
}
/* Function bb_in_loop_p
Used as predicate for dfs order traversal of the loop bbs. */
static bool
bb_in_loop_p (const_basic_block bb, const void *data)
{
const struct loop *const loop = (const struct loop *)data;
if (flow_bb_inside_loop_p (loop, bb))
return true;
return false;
}
/* Function new_loop_vec_info.
Create and initialize a new loop_vec_info struct for LOOP, as well as
stmt_vec_info structs for all the stmts in LOOP. */
static loop_vec_info
new_loop_vec_info (struct loop *loop)
{
loop_vec_info res;
basic_block *bbs;
gimple_stmt_iterator si;
unsigned int i, nbbs;
res = (loop_vec_info) xcalloc (1, sizeof (struct _loop_vec_info));
LOOP_VINFO_LOOP (res) = loop;
bbs = get_loop_body (loop);
/* Create/Update stmt_info for all stmts in the loop. */
for (i = 0; i < loop->num_nodes; i++)
{
basic_block bb = bbs[i];
/* BBs in a nested inner-loop will have been already processed (because
we will have called vect_analyze_loop_form for any nested inner-loop).
Therefore, for stmts in an inner-loop we just want to update the
STMT_VINFO_LOOP_VINFO field of their stmt_info to point to the new
loop_info of the outer-loop we are currently considering to vectorize
(instead of the loop_info of the inner-loop).
For stmts in other BBs we need to create a stmt_info from scratch. */
if (bb->loop_father != loop)
{
/* Inner-loop bb. */
gcc_assert (loop->inner && bb->loop_father == loop->inner);
for (si = gsi_start_phis (bb); !gsi_end_p (si); gsi_next (&si))
{
gimple phi = gsi_stmt (si);
stmt_vec_info stmt_info = vinfo_for_stmt (phi);
loop_vec_info inner_loop_vinfo =
STMT_VINFO_LOOP_VINFO (stmt_info);
gcc_assert (loop->inner == LOOP_VINFO_LOOP (inner_loop_vinfo));
STMT_VINFO_LOOP_VINFO (stmt_info) = res;
}
for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
{
gimple stmt = gsi_stmt (si);
stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
loop_vec_info inner_loop_vinfo =
STMT_VINFO_LOOP_VINFO (stmt_info);
gcc_assert (loop->inner == LOOP_VINFO_LOOP (inner_loop_vinfo));
STMT_VINFO_LOOP_VINFO (stmt_info) = res;
}
}
else
{
/* bb in current nest. */
for (si = gsi_start_phis (bb); !gsi_end_p (si); gsi_next (&si))
{
gimple phi = gsi_stmt (si);
gimple_set_uid (phi, 0);
set_vinfo_for_stmt (phi, new_stmt_vec_info (phi, res, NULL));
}
for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
{
gimple stmt = gsi_stmt (si);
gimple_set_uid (stmt, 0);
set_vinfo_for_stmt (stmt, new_stmt_vec_info (stmt, res, NULL));
}
}
}
/* CHECKME: We want to visit all BBs before their successors (except for
latch blocks, for which this assertion wouldn't hold). In the simple
case of the loop forms we allow, a dfs order of the BBs would the same
as reversed postorder traversal, so we are safe. */
free (bbs);
bbs = XCNEWVEC (basic_block, loop->num_nodes);
nbbs = dfs_enumerate_from (loop->header, 0, bb_in_loop_p,
bbs, loop->num_nodes, loop);
gcc_assert (nbbs == loop->num_nodes);
LOOP_VINFO_BBS (res) = bbs;
LOOP_VINFO_NITERS (res) = NULL;
LOOP_VINFO_NITERS_UNCHANGED (res) = NULL;
LOOP_VINFO_COST_MODEL_MIN_ITERS (res) = 0;
LOOP_VINFO_VECTORIZABLE_P (res) = 0;
LOOP_PEELING_FOR_ALIGNMENT (res) = 0;
LOOP_VINFO_VECT_FACTOR (res) = 0;
LOOP_VINFO_LOOP_NEST (res) = VEC_alloc (loop_p, heap, 3);
LOOP_VINFO_DATAREFS (res) = VEC_alloc (data_reference_p, heap, 10);
LOOP_VINFO_DDRS (res) = VEC_alloc (ddr_p, heap, 10 * 10);
LOOP_VINFO_UNALIGNED_DR (res) = NULL;
LOOP_VINFO_MAY_MISALIGN_STMTS (res) =
VEC_alloc (gimple, heap,
PARAM_VALUE (PARAM_VECT_MAX_VERSION_FOR_ALIGNMENT_CHECKS));
LOOP_VINFO_MAY_ALIAS_DDRS (res) =
VEC_alloc (ddr_p, heap,
PARAM_VALUE (PARAM_VECT_MAX_VERSION_FOR_ALIAS_CHECKS));
LOOP_VINFO_STRIDED_STORES (res) = VEC_alloc (gimple, heap, 10);
LOOP_VINFO_REDUCTIONS (res) = VEC_alloc (gimple, heap, 10);
LOOP_VINFO_REDUCTION_CHAINS (res) = VEC_alloc (gimple, heap, 10);
LOOP_VINFO_SLP_INSTANCES (res) = VEC_alloc (slp_instance, heap, 10);
LOOP_VINFO_SLP_UNROLLING_FACTOR (res) = 1;
LOOP_VINFO_PEELING_HTAB (res) = NULL;
LOOP_VINFO_PEELING_FOR_GAPS (res) = false;
return res;
}
/* Function destroy_loop_vec_info.
Free LOOP_VINFO struct, as well as all the stmt_vec_info structs of all the
stmts in the loop. */
void
destroy_loop_vec_info (loop_vec_info loop_vinfo, bool clean_stmts)
{
struct loop *loop;
basic_block *bbs;
int nbbs;
gimple_stmt_iterator si;
int j;
VEC (slp_instance, heap) *slp_instances;
slp_instance instance;
if (!loop_vinfo)
return;
loop = LOOP_VINFO_LOOP (loop_vinfo);
bbs = LOOP_VINFO_BBS (loop_vinfo);
nbbs = loop->num_nodes;
if (!clean_stmts)
{
free (LOOP_VINFO_BBS (loop_vinfo));
free_data_refs (LOOP_VINFO_DATAREFS (loop_vinfo));
free_dependence_relations (LOOP_VINFO_DDRS (loop_vinfo));
VEC_free (loop_p, heap, LOOP_VINFO_LOOP_NEST (loop_vinfo));
VEC_free (gimple, heap, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo));
VEC_free (ddr_p, heap, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo));
free (loop_vinfo);
loop->aux = NULL;
return;
}
for (j = 0; j < nbbs; j++)
{
basic_block bb = bbs[j];
for (si = gsi_start_phis (bb); !gsi_end_p (si); gsi_next (&si))
free_stmt_vec_info (gsi_stmt (si));
for (si = gsi_start_bb (bb); !gsi_end_p (si); )
{
gimple stmt = gsi_stmt (si);
/* Free stmt_vec_info. */
free_stmt_vec_info (stmt);
gsi_next (&si);
}
}
free (LOOP_VINFO_BBS (loop_vinfo));
free_data_refs (LOOP_VINFO_DATAREFS (loop_vinfo));
free_dependence_relations (LOOP_VINFO_DDRS (loop_vinfo));
VEC_free (loop_p, heap, LOOP_VINFO_LOOP_NEST (loop_vinfo));
VEC_free (gimple, heap, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo));
VEC_free (ddr_p, heap, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo));
slp_instances = LOOP_VINFO_SLP_INSTANCES (loop_vinfo);
FOR_EACH_VEC_ELT (slp_instance, slp_instances, j, instance)
vect_free_slp_instance (instance);
VEC_free (slp_instance, heap, LOOP_VINFO_SLP_INSTANCES (loop_vinfo));
VEC_free (gimple, heap, LOOP_VINFO_STRIDED_STORES (loop_vinfo));
VEC_free (gimple, heap, LOOP_VINFO_REDUCTIONS (loop_vinfo));
VEC_free (gimple, heap, LOOP_VINFO_REDUCTION_CHAINS (loop_vinfo));
if (LOOP_VINFO_PEELING_HTAB (loop_vinfo))
htab_delete (LOOP_VINFO_PEELING_HTAB (loop_vinfo));
free (loop_vinfo);
loop->aux = NULL;
}
/* Function vect_analyze_loop_1.
Apply a set of analyses on LOOP, and create a loop_vec_info struct
for it. The different analyses will record information in the
loop_vec_info struct. This is a subset of the analyses applied in
vect_analyze_loop, to be applied on an inner-loop nested in the loop
that is now considered for (outer-loop) vectorization. */
static loop_vec_info
vect_analyze_loop_1 (struct loop *loop)
{
loop_vec_info loop_vinfo;
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "===== analyze_loop_nest_1 =====");
/* Check the CFG characteristics of the loop (nesting, entry/exit, etc. */
loop_vinfo = vect_analyze_loop_form (loop);
if (!loop_vinfo)
{
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "bad inner-loop form.");
return NULL;
}
return loop_vinfo;
}
/* Function vect_analyze_loop_form.
Verify that certain CFG restrictions hold, including:
- the loop has a pre-header
- the loop has a single entry and exit
- the loop exit condition is simple enough, and the number of iterations
can be analyzed (a countable loop). */
loop_vec_info
vect_analyze_loop_form (struct loop *loop)
{
loop_vec_info loop_vinfo;
gimple loop_cond;
tree number_of_iterations = NULL;
loop_vec_info inner_loop_vinfo = NULL;
if (vect_print_dump_info (REPORT_DETAILS))
fprintf (vect_dump, "=== vect_analyze_loop_form ===");
/* Different restrictions apply when we are considering an inner-most loop,
vs. an outer (nested) loop.
(FORNOW. May want to relax some of these restrictions in the future). */
if (!loop->inner)
{
/* Inner-most loop. We currently require that the number of BBs is
exactly 2 (the header and latch). Vectorizable inner-most loops
look like this:
(pre-header)
|
header <--------+
| | |
| +--> latch --+
|
(exit-bb) */
if (loop->num_nodes != 2)
{