* pretty-print.h (struct pretty_print_info): Add
[official-gcc/alias-decl.git] / gcc / tree-scalar-evolution.c
blobb3990c6bfe15fb80ef39f0e7671dbaafe0f27939
1 /* Scalar evolution detector.
2 Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009
3 Free Software Foundation, Inc.
4 Contributed by Sebastian Pop <s.pop@laposte.net>
6 This file is part of GCC.
8 GCC is free software; you can redistribute it and/or modify it under
9 the terms of the GNU General Public License as published by the Free
10 Software Foundation; either version 3, or (at your option) any later
11 version.
13 GCC is distributed in the hope that it will be useful, but WITHOUT ANY
14 WARRANTY; without even the implied warranty of MERCHANTABILITY or
15 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
16 for more details.
18 You should have received a copy of the GNU General Public License
19 along with GCC; see the file COPYING3. If not see
20 <http://www.gnu.org/licenses/>. */
22 /*
23 Description:
25 This pass analyzes the evolution of scalar variables in loop
26 structures. The algorithm is based on the SSA representation,
27 and on the loop hierarchy tree. This algorithm is not based on
28 the notion of versions of a variable, as it was the case for the
29 previous implementations of the scalar evolution algorithm, but
30 it assumes that each defined name is unique.
32 The notation used in this file is called "chains of recurrences",
33 and has been proposed by Eugene Zima, Robert Van Engelen, and
34 others for describing induction variables in programs. For example
35 "b -> {0, +, 2}_1" means that the scalar variable "b" is equal to 0
36 when entering in the loop_1 and has a step 2 in this loop, in other
37 words "for (b = 0; b < N; b+=2);". Note that the coefficients of
38 this chain of recurrence (or chrec [shrek]) can contain the name of
39 other variables, in which case they are called parametric chrecs.
40 For example, "b -> {a, +, 2}_1" means that the initial value of "b"
41 is the value of "a". In most of the cases these parametric chrecs
42 are fully instantiated before their use because symbolic names can
43 hide some difficult cases such as self-references described later
44 (see the Fibonacci example).
46 A short sketch of the algorithm is:
48 Given a scalar variable to be analyzed, follow the SSA edge to
49 its definition:
51 - When the definition is a GIMPLE_ASSIGN: if the right hand side
52 (RHS) of the definition cannot be statically analyzed, the answer
53 of the analyzer is: "don't know".
54 Otherwise, for all the variables that are not yet analyzed in the
55 RHS, try to determine their evolution, and finally try to
56 evaluate the operation of the RHS that gives the evolution
57 function of the analyzed variable.
59 - When the definition is a condition-phi-node: determine the
60 evolution function for all the branches of the phi node, and
61 finally merge these evolutions (see chrec_merge).
63 - When the definition is a loop-phi-node: determine its initial
64 condition, that is the SSA edge defined in an outer loop, and
65 keep it symbolic. Then determine the SSA edges that are defined
66 in the body of the loop. Follow the inner edges until ending on
67 another loop-phi-node of the same analyzed loop. If the reached
68 loop-phi-node is not the starting loop-phi-node, then we keep
69 this definition under a symbolic form. If the reached
70 loop-phi-node is the same as the starting one, then we compute a
71 symbolic stride on the return path. The result is then the
72 symbolic chrec {initial_condition, +, symbolic_stride}_loop.
74 Examples:
76 Example 1: Illustration of the basic algorithm.
78 | a = 3
79 | loop_1
80 | b = phi (a, c)
81 | c = b + 1
82 | if (c > 10) exit_loop
83 | endloop
85 Suppose that we want to know the number of iterations of the
86 loop_1. The exit_loop is controlled by a COND_EXPR (c > 10). We
87 ask the scalar evolution analyzer two questions: what's the
88 scalar evolution (scev) of "c", and what's the scev of "10". For
89 "10" the answer is "10" since it is a scalar constant. For the
90 scalar variable "c", it follows the SSA edge to its definition,
91 "c = b + 1", and then asks again what's the scev of "b".
92 Following the SSA edge, we end on a loop-phi-node "b = phi (a,
93 c)", where the initial condition is "a", and the inner loop edge
94 is "c". The initial condition is kept under a symbolic form (it
95 may be the case that the copy constant propagation has done its
96 work and we end with the constant "3" as one of the edges of the
97 loop-phi-node). The update edge is followed to the end of the
98 loop, and until reaching again the starting loop-phi-node: b -> c
99 -> b. At this point we have drawn a path from "b" to "b" from
100 which we compute the stride in the loop: in this example it is
101 "+1". The resulting scev for "b" is "b -> {a, +, 1}_1". Now
102 that the scev for "b" is known, it is possible to compute the
103 scev for "c", that is "c -> {a + 1, +, 1}_1". In order to
104 determine the number of iterations in the loop_1, we have to
105 instantiate_parameters (loop_1, {a + 1, +, 1}_1), that gives after some
106 more analysis the scev {4, +, 1}_1, or in other words, this is
107 the function "f (x) = x + 4", where x is the iteration count of
108 the loop_1. Now we have to solve the inequality "x + 4 > 10",
109 and take the smallest iteration number for which the loop is
110 exited: x = 7. This loop runs from x = 0 to x = 7, and in total
111 there are 8 iterations. In terms of loop normalization, we have
112 created a variable that is implicitly defined, "x" or just "_1",
113 and all the other analyzed scalars of the loop are defined in
114 function of this variable:
116 a -> 3
117 b -> {3, +, 1}_1
118 c -> {4, +, 1}_1
120 or in terms of a C program:
122 | a = 3
123 | for (x = 0; x <= 7; x++)
125 | b = x + 3
126 | c = x + 4
129 Example 2a: Illustration of the algorithm on nested loops.
131 | loop_1
132 | a = phi (1, b)
133 | c = a + 2
134 | loop_2 10 times
135 | b = phi (c, d)
136 | d = b + 3
137 | endloop
138 | endloop
140 For analyzing the scalar evolution of "a", the algorithm follows
141 the SSA edge into the loop's body: "a -> b". "b" is an inner
142 loop-phi-node, and its analysis as in Example 1, gives:
144 b -> {c, +, 3}_2
145 d -> {c + 3, +, 3}_2
147 Following the SSA edge for the initial condition, we end on "c = a
148 + 2", and then on the starting loop-phi-node "a". From this point,
149 the loop stride is computed: back on "c = a + 2" we get a "+2" in
150 the loop_1, then on the loop-phi-node "b" we compute the overall
151 effect of the inner loop that is "b = c + 30", and we get a "+30"
152 in the loop_1. That means that the overall stride in loop_1 is
153 equal to "+32", and the result is:
155 a -> {1, +, 32}_1
156 c -> {3, +, 32}_1
158 Example 2b: Multivariate chains of recurrences.
160 | loop_1
161 | k = phi (0, k + 1)
162 | loop_2 4 times
163 | j = phi (0, j + 1)
164 | loop_3 4 times
165 | i = phi (0, i + 1)
166 | A[j + k] = ...
167 | endloop
168 | endloop
169 | endloop
171 Analyzing the access function of array A with
172 instantiate_parameters (loop_1, "j + k"), we obtain the
173 instantiation and the analysis of the scalar variables "j" and "k"
174 in loop_1. This leads to the scalar evolution {4, +, 1}_1: the end
175 value of loop_2 for "j" is 4, and the evolution of "k" in loop_1 is
176 {0, +, 1}_1. To obtain the evolution function in loop_3 and
177 instantiate the scalar variables up to loop_1, one has to use:
178 instantiate_scev (block_before_loop (loop_1), loop_3, "j + k").
179 The result of this call is {{0, +, 1}_1, +, 1}_2.
181 Example 3: Higher degree polynomials.
183 | loop_1
184 | a = phi (2, b)
185 | c = phi (5, d)
186 | b = a + 1
187 | d = c + a
188 | endloop
190 a -> {2, +, 1}_1
191 b -> {3, +, 1}_1
192 c -> {5, +, a}_1
193 d -> {5 + a, +, a}_1
195 instantiate_parameters (loop_1, {5, +, a}_1) -> {5, +, 2, +, 1}_1
196 instantiate_parameters (loop_1, {5 + a, +, a}_1) -> {7, +, 3, +, 1}_1
198 Example 4: Lucas, Fibonacci, or mixers in general.
200 | loop_1
201 | a = phi (1, b)
202 | c = phi (3, d)
203 | b = c
204 | d = c + a
205 | endloop
207 a -> (1, c)_1
208 c -> {3, +, a}_1
210 The syntax "(1, c)_1" stands for a PEELED_CHREC that has the
211 following semantics: during the first iteration of the loop_1, the
212 variable contains the value 1, and then it contains the value "c".
213 Note that this syntax is close to the syntax of the loop-phi-node:
214 "a -> (1, c)_1" vs. "a = phi (1, c)".
216 The symbolic chrec representation contains all the semantics of the
217 original code. What is more difficult is to use this information.
219 Example 5: Flip-flops, or exchangers.
221 | loop_1
222 | a = phi (1, b)
223 | c = phi (3, d)
224 | b = c
225 | d = a
226 | endloop
228 a -> (1, c)_1
229 c -> (3, a)_1
231 Based on these symbolic chrecs, it is possible to refine this
232 information into the more precise PERIODIC_CHRECs:
234 a -> |1, 3|_1
235 c -> |3, 1|_1
237 This transformation is not yet implemented.
239 Further readings:
241 You can find a more detailed description of the algorithm in:
242 http://icps.u-strasbg.fr/~pop/DEA_03_Pop.pdf
243 http://icps.u-strasbg.fr/~pop/DEA_03_Pop.ps.gz. But note that
244 this is a preliminary report and some of the details of the
245 algorithm have changed. I'm working on a research report that
246 updates the description of the algorithms to reflect the design
247 choices used in this implementation.
249 A set of slides show a high level overview of the algorithm and run
250 an example through the scalar evolution analyzer:
251 http://cri.ensmp.fr/~pop/gcc/mar04/slides.pdf
253 The slides that I have presented at the GCC Summit'04 are available
254 at: http://cri.ensmp.fr/~pop/gcc/20040604/gccsummit-lno-spop.pdf
257 #include "config.h"
258 #include "system.h"
259 #include "coretypes.h"
260 #include "tm.h"
261 #include "ggc.h"
262 #include "tree.h"
263 #include "real.h"
265 /* These RTL headers are needed for basic-block.h. */
266 #include "rtl.h"
267 #include "basic-block.h"
268 #include "diagnostic.h"
269 #include "tree-flow.h"
270 #include "tree-dump.h"
271 #include "timevar.h"
272 #include "cfgloop.h"
273 #include "tree-chrec.h"
274 #include "tree-scalar-evolution.h"
275 #include "tree-pass.h"
276 #include "flags.h"
277 #include "params.h"
279 static tree analyze_scalar_evolution_1 (struct loop *, tree, tree);
281 /* The cached information about an SSA name VAR, claiming that below
282 basic block INSTANTIATED_BELOW, the value of VAR can be expressed
283 as CHREC. */
285 struct GTY(()) scev_info_str {
286 basic_block instantiated_below;
287 tree var;
288 tree chrec;
291 /* Counters for the scev database. */
292 static unsigned nb_set_scev = 0;
293 static unsigned nb_get_scev = 0;
295 /* The following trees are unique elements. Thus the comparison of
296 another element to these elements should be done on the pointer to
297 these trees, and not on their value. */
299 /* The SSA_NAMEs that are not yet analyzed are qualified with NULL_TREE. */
300 tree chrec_not_analyzed_yet;
302 /* Reserved to the cases where the analyzer has detected an
303 undecidable property at compile time. */
304 tree chrec_dont_know;
306 /* When the analyzer has detected that a property will never
307 happen, then it qualifies it with chrec_known. */
308 tree chrec_known;
310 static GTY ((param_is (struct scev_info_str))) htab_t scalar_evolution_info;
313 /* Constructs a new SCEV_INFO_STR structure for VAR and INSTANTIATED_BELOW. */
315 static inline struct scev_info_str *
316 new_scev_info_str (basic_block instantiated_below, tree var)
318 struct scev_info_str *res;
320 res = GGC_NEW (struct scev_info_str);
321 res->var = var;
322 res->chrec = chrec_not_analyzed_yet;
323 res->instantiated_below = instantiated_below;
325 return res;
328 /* Computes a hash function for database element ELT. */
330 static hashval_t
331 hash_scev_info (const void *elt)
333 return SSA_NAME_VERSION (((const struct scev_info_str *) elt)->var);
336 /* Compares database elements E1 and E2. */
338 static int
339 eq_scev_info (const void *e1, const void *e2)
341 const struct scev_info_str *elt1 = (const struct scev_info_str *) e1;
342 const struct scev_info_str *elt2 = (const struct scev_info_str *) e2;
344 return (elt1->var == elt2->var
345 && elt1->instantiated_below == elt2->instantiated_below);
348 /* Deletes database element E. */
350 static void
351 del_scev_info (void *e)
353 ggc_free (e);
356 /* Get the scalar evolution of VAR for INSTANTIATED_BELOW basic block.
357 A first query on VAR returns chrec_not_analyzed_yet. */
359 static tree *
360 find_var_scev_info (basic_block instantiated_below, tree var)
362 struct scev_info_str *res;
363 struct scev_info_str tmp;
364 PTR *slot;
366 tmp.var = var;
367 tmp.instantiated_below = instantiated_below;
368 slot = htab_find_slot (scalar_evolution_info, &tmp, INSERT);
370 if (!*slot)
371 *slot = new_scev_info_str (instantiated_below, var);
372 res = (struct scev_info_str *) *slot;
374 return &res->chrec;
377 /* Return true when CHREC contains symbolic names defined in
378 LOOP_NB. */
380 bool
381 chrec_contains_symbols_defined_in_loop (const_tree chrec, unsigned loop_nb)
383 int i, n;
385 if (chrec == NULL_TREE)
386 return false;
388 if (is_gimple_min_invariant (chrec))
389 return false;
391 if (TREE_CODE (chrec) == VAR_DECL
392 || TREE_CODE (chrec) == PARM_DECL
393 || TREE_CODE (chrec) == FUNCTION_DECL
394 || TREE_CODE (chrec) == LABEL_DECL
395 || TREE_CODE (chrec) == RESULT_DECL
396 || TREE_CODE (chrec) == FIELD_DECL)
397 return true;
399 if (TREE_CODE (chrec) == SSA_NAME)
401 gimple def = SSA_NAME_DEF_STMT (chrec);
402 struct loop *def_loop = loop_containing_stmt (def);
403 struct loop *loop = get_loop (loop_nb);
405 if (def_loop == NULL)
406 return false;
408 if (loop == def_loop || flow_loop_nested_p (loop, def_loop))
409 return true;
411 return false;
414 n = TREE_OPERAND_LENGTH (chrec);
415 for (i = 0; i < n; i++)
416 if (chrec_contains_symbols_defined_in_loop (TREE_OPERAND (chrec, i),
417 loop_nb))
418 return true;
419 return false;
422 /* Return true when PHI is a loop-phi-node. */
424 static bool
425 loop_phi_node_p (gimple phi)
427 /* The implementation of this function is based on the following
428 property: "all the loop-phi-nodes of a loop are contained in the
429 loop's header basic block". */
431 return loop_containing_stmt (phi)->header == gimple_bb (phi);
434 /* Compute the scalar evolution for EVOLUTION_FN after crossing LOOP.
435 In general, in the case of multivariate evolutions we want to get
436 the evolution in different loops. LOOP specifies the level for
437 which to get the evolution.
439 Example:
441 | for (j = 0; j < 100; j++)
443 | for (k = 0; k < 100; k++)
445 | i = k + j; - Here the value of i is a function of j, k.
447 | ... = i - Here the value of i is a function of j.
449 | ... = i - Here the value of i is a scalar.
451 Example:
453 | i_0 = ...
454 | loop_1 10 times
455 | i_1 = phi (i_0, i_2)
456 | i_2 = i_1 + 2
457 | endloop
459 This loop has the same effect as:
460 LOOP_1 has the same effect as:
462 | i_1 = i_0 + 20
464 The overall effect of the loop, "i_0 + 20" in the previous example,
465 is obtained by passing in the parameters: LOOP = 1,
466 EVOLUTION_FN = {i_0, +, 2}_1.
469 static tree
470 compute_overall_effect_of_inner_loop (struct loop *loop, tree evolution_fn)
472 bool val = false;
474 if (evolution_fn == chrec_dont_know)
475 return chrec_dont_know;
477 else if (TREE_CODE (evolution_fn) == POLYNOMIAL_CHREC)
479 struct loop *inner_loop = get_chrec_loop (evolution_fn);
481 if (inner_loop == loop
482 || flow_loop_nested_p (loop, inner_loop))
484 tree nb_iter = number_of_latch_executions (inner_loop);
486 if (nb_iter == chrec_dont_know)
487 return chrec_dont_know;
488 else
490 tree res;
492 /* evolution_fn is the evolution function in LOOP. Get
493 its value in the nb_iter-th iteration. */
494 res = chrec_apply (inner_loop->num, evolution_fn, nb_iter);
496 /* Continue the computation until ending on a parent of LOOP. */
497 return compute_overall_effect_of_inner_loop (loop, res);
500 else
501 return evolution_fn;
504 /* If the evolution function is an invariant, there is nothing to do. */
505 else if (no_evolution_in_loop_p (evolution_fn, loop->num, &val) && val)
506 return evolution_fn;
508 else
509 return chrec_dont_know;
512 /* Determine whether the CHREC is always positive/negative. If the expression
513 cannot be statically analyzed, return false, otherwise set the answer into
514 VALUE. */
516 bool
517 chrec_is_positive (tree chrec, bool *value)
519 bool value0, value1, value2;
520 tree end_value, nb_iter;
522 switch (TREE_CODE (chrec))
524 case POLYNOMIAL_CHREC:
525 if (!chrec_is_positive (CHREC_LEFT (chrec), &value0)
526 || !chrec_is_positive (CHREC_RIGHT (chrec), &value1))
527 return false;
529 /* FIXME -- overflows. */
530 if (value0 == value1)
532 *value = value0;
533 return true;
536 /* Otherwise the chrec is under the form: "{-197, +, 2}_1",
537 and the proof consists in showing that the sign never
538 changes during the execution of the loop, from 0 to
539 loop->nb_iterations. */
540 if (!evolution_function_is_affine_p (chrec))
541 return false;
543 nb_iter = number_of_latch_executions (get_chrec_loop (chrec));
544 if (chrec_contains_undetermined (nb_iter))
545 return false;
547 #if 0
548 /* TODO -- If the test is after the exit, we may decrease the number of
549 iterations by one. */
550 if (after_exit)
551 nb_iter = chrec_fold_minus (type, nb_iter, build_int_cst (type, 1));
552 #endif
554 end_value = chrec_apply (CHREC_VARIABLE (chrec), chrec, nb_iter);
556 if (!chrec_is_positive (end_value, &value2))
557 return false;
559 *value = value0;
560 return value0 == value1;
562 case INTEGER_CST:
563 *value = (tree_int_cst_sgn (chrec) == 1);
564 return true;
566 default:
567 return false;
571 /* Associate CHREC to SCALAR. */
573 static void
574 set_scalar_evolution (basic_block instantiated_below, tree scalar, tree chrec)
576 tree *scalar_info;
578 if (TREE_CODE (scalar) != SSA_NAME)
579 return;
581 scalar_info = find_var_scev_info (instantiated_below, scalar);
583 if (dump_file)
585 if (dump_flags & TDF_DETAILS)
587 fprintf (dump_file, "(set_scalar_evolution \n");
588 fprintf (dump_file, " instantiated_below = %d \n",
589 instantiated_below->index);
590 fprintf (dump_file, " (scalar = ");
591 print_generic_expr (dump_file, scalar, 0);
592 fprintf (dump_file, ")\n (scalar_evolution = ");
593 print_generic_expr (dump_file, chrec, 0);
594 fprintf (dump_file, "))\n");
596 if (dump_flags & TDF_STATS)
597 nb_set_scev++;
600 *scalar_info = chrec;
603 /* Retrieve the chrec associated to SCALAR instantiated below
604 INSTANTIATED_BELOW block. */
606 static tree
607 get_scalar_evolution (basic_block instantiated_below, tree scalar)
609 tree res;
611 if (dump_file)
613 if (dump_flags & TDF_DETAILS)
615 fprintf (dump_file, "(get_scalar_evolution \n");
616 fprintf (dump_file, " (scalar = ");
617 print_generic_expr (dump_file, scalar, 0);
618 fprintf (dump_file, ")\n");
620 if (dump_flags & TDF_STATS)
621 nb_get_scev++;
624 switch (TREE_CODE (scalar))
626 case SSA_NAME:
627 res = *find_var_scev_info (instantiated_below, scalar);
628 break;
630 case REAL_CST:
631 case FIXED_CST:
632 case INTEGER_CST:
633 res = scalar;
634 break;
636 default:
637 res = chrec_not_analyzed_yet;
638 break;
641 if (dump_file && (dump_flags & TDF_DETAILS))
643 fprintf (dump_file, " (scalar_evolution = ");
644 print_generic_expr (dump_file, res, 0);
645 fprintf (dump_file, "))\n");
648 return res;
651 /* Helper function for add_to_evolution. Returns the evolution
652 function for an assignment of the form "a = b + c", where "a" and
653 "b" are on the strongly connected component. CHREC_BEFORE is the
654 information that we already have collected up to this point.
655 TO_ADD is the evolution of "c".
657 When CHREC_BEFORE has an evolution part in LOOP_NB, add to this
658 evolution the expression TO_ADD, otherwise construct an evolution
659 part for this loop. */
661 static tree
662 add_to_evolution_1 (unsigned loop_nb, tree chrec_before, tree to_add,
663 gimple at_stmt)
665 tree type, left, right;
666 struct loop *loop = get_loop (loop_nb), *chloop;
668 switch (TREE_CODE (chrec_before))
670 case POLYNOMIAL_CHREC:
671 chloop = get_chrec_loop (chrec_before);
672 if (chloop == loop
673 || flow_loop_nested_p (chloop, loop))
675 unsigned var;
677 type = chrec_type (chrec_before);
679 /* When there is no evolution part in this loop, build it. */
680 if (chloop != loop)
682 var = loop_nb;
683 left = chrec_before;
684 right = SCALAR_FLOAT_TYPE_P (type)
685 ? build_real (type, dconst0)
686 : build_int_cst (type, 0);
688 else
690 var = CHREC_VARIABLE (chrec_before);
691 left = CHREC_LEFT (chrec_before);
692 right = CHREC_RIGHT (chrec_before);
695 to_add = chrec_convert (type, to_add, at_stmt);
696 right = chrec_convert_rhs (type, right, at_stmt);
697 right = chrec_fold_plus (chrec_type (right), right, to_add);
698 return build_polynomial_chrec (var, left, right);
700 else
702 gcc_assert (flow_loop_nested_p (loop, chloop));
704 /* Search the evolution in LOOP_NB. */
705 left = add_to_evolution_1 (loop_nb, CHREC_LEFT (chrec_before),
706 to_add, at_stmt);
707 right = CHREC_RIGHT (chrec_before);
708 right = chrec_convert_rhs (chrec_type (left), right, at_stmt);
709 return build_polynomial_chrec (CHREC_VARIABLE (chrec_before),
710 left, right);
713 default:
714 /* These nodes do not depend on a loop. */
715 if (chrec_before == chrec_dont_know)
716 return chrec_dont_know;
718 left = chrec_before;
719 right = chrec_convert_rhs (chrec_type (left), to_add, at_stmt);
720 return build_polynomial_chrec (loop_nb, left, right);
724 /* Add TO_ADD to the evolution part of CHREC_BEFORE in the dimension
725 of LOOP_NB.
727 Description (provided for completeness, for those who read code in
728 a plane, and for my poor 62 bytes brain that would have forgotten
729 all this in the next two or three months):
731 The algorithm of translation of programs from the SSA representation
732 into the chrecs syntax is based on a pattern matching. After having
733 reconstructed the overall tree expression for a loop, there are only
734 two cases that can arise:
736 1. a = loop-phi (init, a + expr)
737 2. a = loop-phi (init, expr)
739 where EXPR is either a scalar constant with respect to the analyzed
740 loop (this is a degree 0 polynomial), or an expression containing
741 other loop-phi definitions (these are higher degree polynomials).
743 Examples:
746 | init = ...
747 | loop_1
748 | a = phi (init, a + 5)
749 | endloop
752 | inita = ...
753 | initb = ...
754 | loop_1
755 | a = phi (inita, 2 * b + 3)
756 | b = phi (initb, b + 1)
757 | endloop
759 For the first case, the semantics of the SSA representation is:
761 | a (x) = init + \sum_{j = 0}^{x - 1} expr (j)
763 that is, there is a loop index "x" that determines the scalar value
764 of the variable during the loop execution. During the first
765 iteration, the value is that of the initial condition INIT, while
766 during the subsequent iterations, it is the sum of the initial
767 condition with the sum of all the values of EXPR from the initial
768 iteration to the before last considered iteration.
770 For the second case, the semantics of the SSA program is:
772 | a (x) = init, if x = 0;
773 | expr (x - 1), otherwise.
775 The second case corresponds to the PEELED_CHREC, whose syntax is
776 close to the syntax of a loop-phi-node:
778 | phi (init, expr) vs. (init, expr)_x
780 The proof of the translation algorithm for the first case is a
781 proof by structural induction based on the degree of EXPR.
783 Degree 0:
784 When EXPR is a constant with respect to the analyzed loop, or in
785 other words when EXPR is a polynomial of degree 0, the evolution of
786 the variable A in the loop is an affine function with an initial
787 condition INIT, and a step EXPR. In order to show this, we start
788 from the semantics of the SSA representation:
790 f (x) = init + \sum_{j = 0}^{x - 1} expr (j)
792 and since "expr (j)" is a constant with respect to "j",
794 f (x) = init + x * expr
796 Finally, based on the semantics of the pure sum chrecs, by
797 identification we get the corresponding chrecs syntax:
799 f (x) = init * \binom{x}{0} + expr * \binom{x}{1}
800 f (x) -> {init, +, expr}_x
802 Higher degree:
803 Suppose that EXPR is a polynomial of degree N with respect to the
804 analyzed loop_x for which we have already determined that it is
805 written under the chrecs syntax:
807 | expr (x) -> {b_0, +, b_1, +, ..., +, b_{n-1}} (x)
809 We start from the semantics of the SSA program:
811 | f (x) = init + \sum_{j = 0}^{x - 1} expr (j)
813 | f (x) = init + \sum_{j = 0}^{x - 1}
814 | (b_0 * \binom{j}{0} + ... + b_{n-1} * \binom{j}{n-1})
816 | f (x) = init + \sum_{j = 0}^{x - 1}
817 | \sum_{k = 0}^{n - 1} (b_k * \binom{j}{k})
819 | f (x) = init + \sum_{k = 0}^{n - 1}
820 | (b_k * \sum_{j = 0}^{x - 1} \binom{j}{k})
822 | f (x) = init + \sum_{k = 0}^{n - 1}
823 | (b_k * \binom{x}{k + 1})
825 | f (x) = init + b_0 * \binom{x}{1} + ...
826 | + b_{n-1} * \binom{x}{n}
828 | f (x) = init * \binom{x}{0} + b_0 * \binom{x}{1} + ...
829 | + b_{n-1} * \binom{x}{n}
832 And finally from the definition of the chrecs syntax, we identify:
833 | f (x) -> {init, +, b_0, +, ..., +, b_{n-1}}_x
835 This shows the mechanism that stands behind the add_to_evolution
836 function. An important point is that the use of symbolic
837 parameters avoids the need of an analysis schedule.
839 Example:
841 | inita = ...
842 | initb = ...
843 | loop_1
844 | a = phi (inita, a + 2 + b)
845 | b = phi (initb, b + 1)
846 | endloop
848 When analyzing "a", the algorithm keeps "b" symbolically:
850 | a -> {inita, +, 2 + b}_1
852 Then, after instantiation, the analyzer ends on the evolution:
854 | a -> {inita, +, 2 + initb, +, 1}_1
858 static tree
859 add_to_evolution (unsigned loop_nb, tree chrec_before, enum tree_code code,
860 tree to_add, gimple at_stmt)
862 tree type = chrec_type (to_add);
863 tree res = NULL_TREE;
865 if (to_add == NULL_TREE)
866 return chrec_before;
868 /* TO_ADD is either a scalar, or a parameter. TO_ADD is not
869 instantiated at this point. */
870 if (TREE_CODE (to_add) == POLYNOMIAL_CHREC)
871 /* This should not happen. */
872 return chrec_dont_know;
874 if (dump_file && (dump_flags & TDF_DETAILS))
876 fprintf (dump_file, "(add_to_evolution \n");
877 fprintf (dump_file, " (loop_nb = %d)\n", loop_nb);
878 fprintf (dump_file, " (chrec_before = ");
879 print_generic_expr (dump_file, chrec_before, 0);
880 fprintf (dump_file, ")\n (to_add = ");
881 print_generic_expr (dump_file, to_add, 0);
882 fprintf (dump_file, ")\n");
885 if (code == MINUS_EXPR)
886 to_add = chrec_fold_multiply (type, to_add, SCALAR_FLOAT_TYPE_P (type)
887 ? build_real (type, dconstm1)
888 : build_int_cst_type (type, -1));
890 res = add_to_evolution_1 (loop_nb, chrec_before, to_add, at_stmt);
892 if (dump_file && (dump_flags & TDF_DETAILS))
894 fprintf (dump_file, " (res = ");
895 print_generic_expr (dump_file, res, 0);
896 fprintf (dump_file, "))\n");
899 return res;
902 /* Helper function. */
904 static inline tree
905 set_nb_iterations_in_loop (struct loop *loop,
906 tree res)
908 if (dump_file && (dump_flags & TDF_DETAILS))
910 fprintf (dump_file, " (set_nb_iterations_in_loop = ");
911 print_generic_expr (dump_file, res, 0);
912 fprintf (dump_file, "))\n");
915 loop->nb_iterations = res;
916 return res;
921 /* This section selects the loops that will be good candidates for the
922 scalar evolution analysis. For the moment, greedily select all the
923 loop nests we could analyze. */
925 /* For a loop with a single exit edge, return the COND_EXPR that
926 guards the exit edge. If the expression is too difficult to
927 analyze, then give up. */
929 gimple
930 get_loop_exit_condition (const struct loop *loop)
932 gimple res = NULL;
933 edge exit_edge = single_exit (loop);
935 if (dump_file && (dump_flags & TDF_DETAILS))
936 fprintf (dump_file, "(get_loop_exit_condition \n ");
938 if (exit_edge)
940 gimple stmt;
942 stmt = last_stmt (exit_edge->src);
943 if (gimple_code (stmt) == GIMPLE_COND)
944 res = stmt;
947 if (dump_file && (dump_flags & TDF_DETAILS))
949 print_gimple_stmt (dump_file, res, 0, 0);
950 fprintf (dump_file, ")\n");
953 return res;
956 /* Recursively determine and enqueue the exit conditions for a loop. */
958 static void
959 get_exit_conditions_rec (struct loop *loop,
960 VEC(gimple,heap) **exit_conditions)
962 if (!loop)
963 return;
965 /* Recurse on the inner loops, then on the next (sibling) loops. */
966 get_exit_conditions_rec (loop->inner, exit_conditions);
967 get_exit_conditions_rec (loop->next, exit_conditions);
969 if (single_exit (loop))
971 gimple loop_condition = get_loop_exit_condition (loop);
973 if (loop_condition)
974 VEC_safe_push (gimple, heap, *exit_conditions, loop_condition);
978 /* Select the candidate loop nests for the analysis. This function
979 initializes the EXIT_CONDITIONS array. */
981 static void
982 select_loops_exit_conditions (VEC(gimple,heap) **exit_conditions)
984 struct loop *function_body = current_loops->tree_root;
986 get_exit_conditions_rec (function_body->inner, exit_conditions);
990 /* Depth first search algorithm. */
992 typedef enum t_bool {
993 t_false,
994 t_true,
995 t_dont_know
996 } t_bool;
999 static t_bool follow_ssa_edge (struct loop *loop, gimple, gimple, tree *, int);
1001 /* Follow the ssa edge into the binary expression RHS0 CODE RHS1.
1002 Return true if the strongly connected component has been found. */
1004 static t_bool
1005 follow_ssa_edge_binary (struct loop *loop, gimple at_stmt,
1006 tree type, tree rhs0, enum tree_code code, tree rhs1,
1007 gimple halting_phi, tree *evolution_of_loop, int limit)
1009 t_bool res = t_false;
1010 tree evol;
1012 switch (code)
1014 case POINTER_PLUS_EXPR:
1015 case PLUS_EXPR:
1016 if (TREE_CODE (rhs0) == SSA_NAME)
1018 if (TREE_CODE (rhs1) == SSA_NAME)
1020 /* Match an assignment under the form:
1021 "a = b + c". */
1023 /* We want only assignments of form "name + name" contribute to
1024 LIMIT, as the other cases do not necessarily contribute to
1025 the complexity of the expression. */
1026 limit++;
1028 evol = *evolution_of_loop;
1029 res = follow_ssa_edge
1030 (loop, SSA_NAME_DEF_STMT (rhs0), halting_phi, &evol, limit);
1032 if (res == t_true)
1033 *evolution_of_loop = add_to_evolution
1034 (loop->num,
1035 chrec_convert (type, evol, at_stmt),
1036 code, rhs1, at_stmt);
1038 else if (res == t_false)
1040 res = follow_ssa_edge
1041 (loop, SSA_NAME_DEF_STMT (rhs1), halting_phi,
1042 evolution_of_loop, limit);
1044 if (res == t_true)
1045 *evolution_of_loop = add_to_evolution
1046 (loop->num,
1047 chrec_convert (type, *evolution_of_loop, at_stmt),
1048 code, rhs0, at_stmt);
1050 else if (res == t_dont_know)
1051 *evolution_of_loop = chrec_dont_know;
1054 else if (res == t_dont_know)
1055 *evolution_of_loop = chrec_dont_know;
1058 else
1060 /* Match an assignment under the form:
1061 "a = b + ...". */
1062 res = follow_ssa_edge
1063 (loop, SSA_NAME_DEF_STMT (rhs0), halting_phi,
1064 evolution_of_loop, limit);
1065 if (res == t_true)
1066 *evolution_of_loop = add_to_evolution
1067 (loop->num, chrec_convert (type, *evolution_of_loop,
1068 at_stmt),
1069 code, rhs1, at_stmt);
1071 else if (res == t_dont_know)
1072 *evolution_of_loop = chrec_dont_know;
1076 else if (TREE_CODE (rhs1) == SSA_NAME)
1078 /* Match an assignment under the form:
1079 "a = ... + c". */
1080 res = follow_ssa_edge
1081 (loop, SSA_NAME_DEF_STMT (rhs1), halting_phi,
1082 evolution_of_loop, limit);
1083 if (res == t_true)
1084 *evolution_of_loop = add_to_evolution
1085 (loop->num, chrec_convert (type, *evolution_of_loop,
1086 at_stmt),
1087 code, rhs0, at_stmt);
1089 else if (res == t_dont_know)
1090 *evolution_of_loop = chrec_dont_know;
1093 else
1094 /* Otherwise, match an assignment under the form:
1095 "a = ... + ...". */
1096 /* And there is nothing to do. */
1097 res = t_false;
1098 break;
1100 case MINUS_EXPR:
1101 /* This case is under the form "opnd0 = rhs0 - rhs1". */
1102 if (TREE_CODE (rhs0) == SSA_NAME)
1104 /* Match an assignment under the form:
1105 "a = b - ...". */
1107 /* We want only assignments of form "name - name" contribute to
1108 LIMIT, as the other cases do not necessarily contribute to
1109 the complexity of the expression. */
1110 if (TREE_CODE (rhs1) == SSA_NAME)
1111 limit++;
1113 res = follow_ssa_edge (loop, SSA_NAME_DEF_STMT (rhs0), halting_phi,
1114 evolution_of_loop, limit);
1115 if (res == t_true)
1116 *evolution_of_loop = add_to_evolution
1117 (loop->num, chrec_convert (type, *evolution_of_loop, at_stmt),
1118 MINUS_EXPR, rhs1, at_stmt);
1120 else if (res == t_dont_know)
1121 *evolution_of_loop = chrec_dont_know;
1123 else
1124 /* Otherwise, match an assignment under the form:
1125 "a = ... - ...". */
1126 /* And there is nothing to do. */
1127 res = t_false;
1128 break;
1130 default:
1131 res = t_false;
1134 return res;
1137 /* Follow the ssa edge into the expression EXPR.
1138 Return true if the strongly connected component has been found. */
1140 static t_bool
1141 follow_ssa_edge_expr (struct loop *loop, gimple at_stmt, tree expr,
1142 gimple halting_phi, tree *evolution_of_loop, int limit)
1144 t_bool res = t_false;
1145 tree rhs0, rhs1;
1146 tree type = TREE_TYPE (expr);
1147 enum tree_code code;
1149 /* The EXPR is one of the following cases:
1150 - an SSA_NAME,
1151 - an INTEGER_CST,
1152 - a PLUS_EXPR,
1153 - a POINTER_PLUS_EXPR,
1154 - a MINUS_EXPR,
1155 - an ASSERT_EXPR,
1156 - other cases are not yet handled. */
1157 code = TREE_CODE (expr);
1158 switch (code)
1160 case NOP_EXPR:
1161 /* This assignment is under the form "a_1 = (cast) rhs. */
1162 res = follow_ssa_edge_expr (loop, at_stmt, TREE_OPERAND (expr, 0),
1163 halting_phi, evolution_of_loop, limit);
1164 *evolution_of_loop = chrec_convert (type, *evolution_of_loop, at_stmt);
1165 break;
1167 case INTEGER_CST:
1168 /* This assignment is under the form "a_1 = 7". */
1169 res = t_false;
1170 break;
1172 case SSA_NAME:
1173 /* This assignment is under the form: "a_1 = b_2". */
1174 res = follow_ssa_edge
1175 (loop, SSA_NAME_DEF_STMT (expr), halting_phi, evolution_of_loop, limit);
1176 break;
1178 case POINTER_PLUS_EXPR:
1179 case PLUS_EXPR:
1180 case MINUS_EXPR:
1181 /* This case is under the form "rhs0 +- rhs1". */
1182 rhs0 = TREE_OPERAND (expr, 0);
1183 rhs1 = TREE_OPERAND (expr, 1);
1184 STRIP_TYPE_NOPS (rhs0);
1185 STRIP_TYPE_NOPS (rhs1);
1186 return follow_ssa_edge_binary (loop, at_stmt, type, rhs0, code, rhs1,
1187 halting_phi, evolution_of_loop, limit);
1189 case ASSERT_EXPR:
1191 /* This assignment is of the form: "a_1 = ASSERT_EXPR <a_2, ...>"
1192 It must be handled as a copy assignment of the form a_1 = a_2. */
1193 tree op0 = ASSERT_EXPR_VAR (expr);
1194 if (TREE_CODE (op0) == SSA_NAME)
1195 res = follow_ssa_edge (loop, SSA_NAME_DEF_STMT (op0),
1196 halting_phi, evolution_of_loop, limit);
1197 else
1198 res = t_false;
1199 break;
1203 default:
1204 res = t_false;
1205 break;
1208 return res;
1211 /* Follow the ssa edge into the right hand side of an assignment STMT.
1212 Return true if the strongly connected component has been found. */
1214 static t_bool
1215 follow_ssa_edge_in_rhs (struct loop *loop, gimple stmt,
1216 gimple halting_phi, tree *evolution_of_loop, int limit)
1218 tree type = TREE_TYPE (gimple_assign_lhs (stmt));
1219 enum tree_code code = gimple_assign_rhs_code (stmt);
1221 switch (get_gimple_rhs_class (code))
1223 case GIMPLE_BINARY_RHS:
1224 return follow_ssa_edge_binary (loop, stmt, type,
1225 gimple_assign_rhs1 (stmt), code,
1226 gimple_assign_rhs2 (stmt),
1227 halting_phi, evolution_of_loop, limit);
1228 case GIMPLE_SINGLE_RHS:
1229 return follow_ssa_edge_expr (loop, stmt, gimple_assign_rhs1 (stmt),
1230 halting_phi, evolution_of_loop, limit);
1231 case GIMPLE_UNARY_RHS:
1232 if (code == NOP_EXPR)
1234 /* This assignment is under the form "a_1 = (cast) rhs. */
1235 t_bool res
1236 = follow_ssa_edge_expr (loop, stmt, gimple_assign_rhs1 (stmt),
1237 halting_phi, evolution_of_loop, limit);
1238 *evolution_of_loop = chrec_convert (type, *evolution_of_loop, stmt);
1239 return res;
1241 /* FALLTHRU */
1243 default:
1244 return t_false;
1248 /* Checks whether the I-th argument of a PHI comes from a backedge. */
1250 static bool
1251 backedge_phi_arg_p (gimple phi, int i)
1253 const_edge e = gimple_phi_arg_edge (phi, i);
1255 /* We would in fact like to test EDGE_DFS_BACK here, but we do not care
1256 about updating it anywhere, and this should work as well most of the
1257 time. */
1258 if (e->flags & EDGE_IRREDUCIBLE_LOOP)
1259 return true;
1261 return false;
1264 /* Helper function for one branch of the condition-phi-node. Return
1265 true if the strongly connected component has been found following
1266 this path. */
1268 static inline t_bool
1269 follow_ssa_edge_in_condition_phi_branch (int i,
1270 struct loop *loop,
1271 gimple condition_phi,
1272 gimple halting_phi,
1273 tree *evolution_of_branch,
1274 tree init_cond, int limit)
1276 tree branch = PHI_ARG_DEF (condition_phi, i);
1277 *evolution_of_branch = chrec_dont_know;
1279 /* Do not follow back edges (they must belong to an irreducible loop, which
1280 we really do not want to worry about). */
1281 if (backedge_phi_arg_p (condition_phi, i))
1282 return t_false;
1284 if (TREE_CODE (branch) == SSA_NAME)
1286 *evolution_of_branch = init_cond;
1287 return follow_ssa_edge (loop, SSA_NAME_DEF_STMT (branch), halting_phi,
1288 evolution_of_branch, limit);
1291 /* This case occurs when one of the condition branches sets
1292 the variable to a constant: i.e. a phi-node like
1293 "a_2 = PHI <a_7(5), 2(6)>;".
1295 FIXME: This case have to be refined correctly:
1296 in some cases it is possible to say something better than
1297 chrec_dont_know, for example using a wrap-around notation. */
1298 return t_false;
1301 /* This function merges the branches of a condition-phi-node in a
1302 loop. */
1304 static t_bool
1305 follow_ssa_edge_in_condition_phi (struct loop *loop,
1306 gimple condition_phi,
1307 gimple halting_phi,
1308 tree *evolution_of_loop, int limit)
1310 int i, n;
1311 tree init = *evolution_of_loop;
1312 tree evolution_of_branch;
1313 t_bool res = follow_ssa_edge_in_condition_phi_branch (0, loop, condition_phi,
1314 halting_phi,
1315 &evolution_of_branch,
1316 init, limit);
1317 if (res == t_false || res == t_dont_know)
1318 return res;
1320 *evolution_of_loop = evolution_of_branch;
1322 n = gimple_phi_num_args (condition_phi);
1323 for (i = 1; i < n; i++)
1325 /* Quickly give up when the evolution of one of the branches is
1326 not known. */
1327 if (*evolution_of_loop == chrec_dont_know)
1328 return t_true;
1330 /* Increase the limit by the PHI argument number to avoid exponential
1331 time and memory complexity. */
1332 res = follow_ssa_edge_in_condition_phi_branch (i, loop, condition_phi,
1333 halting_phi,
1334 &evolution_of_branch,
1335 init, limit + i);
1336 if (res == t_false || res == t_dont_know)
1337 return res;
1339 *evolution_of_loop = chrec_merge (*evolution_of_loop,
1340 evolution_of_branch);
1343 return t_true;
1346 /* Follow an SSA edge in an inner loop. It computes the overall
1347 effect of the loop, and following the symbolic initial conditions,
1348 it follows the edges in the parent loop. The inner loop is
1349 considered as a single statement. */
1351 static t_bool
1352 follow_ssa_edge_inner_loop_phi (struct loop *outer_loop,
1353 gimple loop_phi_node,
1354 gimple halting_phi,
1355 tree *evolution_of_loop, int limit)
1357 struct loop *loop = loop_containing_stmt (loop_phi_node);
1358 tree ev = analyze_scalar_evolution (loop, PHI_RESULT (loop_phi_node));
1360 /* Sometimes, the inner loop is too difficult to analyze, and the
1361 result of the analysis is a symbolic parameter. */
1362 if (ev == PHI_RESULT (loop_phi_node))
1364 t_bool res = t_false;
1365 int i, n = gimple_phi_num_args (loop_phi_node);
1367 for (i = 0; i < n; i++)
1369 tree arg = PHI_ARG_DEF (loop_phi_node, i);
1370 basic_block bb;
1372 /* Follow the edges that exit the inner loop. */
1373 bb = gimple_phi_arg_edge (loop_phi_node, i)->src;
1374 if (!flow_bb_inside_loop_p (loop, bb))
1375 res = follow_ssa_edge_expr (outer_loop, loop_phi_node,
1376 arg, halting_phi,
1377 evolution_of_loop, limit);
1378 if (res == t_true)
1379 break;
1382 /* If the path crosses this loop-phi, give up. */
1383 if (res == t_true)
1384 *evolution_of_loop = chrec_dont_know;
1386 return res;
1389 /* Otherwise, compute the overall effect of the inner loop. */
1390 ev = compute_overall_effect_of_inner_loop (loop, ev);
1391 return follow_ssa_edge_expr (outer_loop, loop_phi_node, ev, halting_phi,
1392 evolution_of_loop, limit);
1395 /* Follow an SSA edge from a loop-phi-node to itself, constructing a
1396 path that is analyzed on the return walk. */
1398 static t_bool
1399 follow_ssa_edge (struct loop *loop, gimple def, gimple halting_phi,
1400 tree *evolution_of_loop, int limit)
1402 struct loop *def_loop;
1404 if (gimple_nop_p (def))
1405 return t_false;
1407 /* Give up if the path is longer than the MAX that we allow. */
1408 if (limit > PARAM_VALUE (PARAM_SCEV_MAX_EXPR_SIZE))
1409 return t_dont_know;
1411 def_loop = loop_containing_stmt (def);
1413 switch (gimple_code (def))
1415 case GIMPLE_PHI:
1416 if (!loop_phi_node_p (def))
1417 /* DEF is a condition-phi-node. Follow the branches, and
1418 record their evolutions. Finally, merge the collected
1419 information and set the approximation to the main
1420 variable. */
1421 return follow_ssa_edge_in_condition_phi
1422 (loop, def, halting_phi, evolution_of_loop, limit);
1424 /* When the analyzed phi is the halting_phi, the
1425 depth-first search is over: we have found a path from
1426 the halting_phi to itself in the loop. */
1427 if (def == halting_phi)
1428 return t_true;
1430 /* Otherwise, the evolution of the HALTING_PHI depends
1431 on the evolution of another loop-phi-node, i.e. the
1432 evolution function is a higher degree polynomial. */
1433 if (def_loop == loop)
1434 return t_false;
1436 /* Inner loop. */
1437 if (flow_loop_nested_p (loop, def_loop))
1438 return follow_ssa_edge_inner_loop_phi
1439 (loop, def, halting_phi, evolution_of_loop, limit + 1);
1441 /* Outer loop. */
1442 return t_false;
1444 case GIMPLE_ASSIGN:
1445 return follow_ssa_edge_in_rhs (loop, def, halting_phi,
1446 evolution_of_loop, limit);
1448 default:
1449 /* At this level of abstraction, the program is just a set
1450 of GIMPLE_ASSIGNs and PHI_NODEs. In principle there is no
1451 other node to be handled. */
1452 return t_false;
1458 /* Given a LOOP_PHI_NODE, this function determines the evolution
1459 function from LOOP_PHI_NODE to LOOP_PHI_NODE in the loop. */
1461 static tree
1462 analyze_evolution_in_loop (gimple loop_phi_node,
1463 tree init_cond)
1465 int i, n = gimple_phi_num_args (loop_phi_node);
1466 tree evolution_function = chrec_not_analyzed_yet;
1467 struct loop *loop = loop_containing_stmt (loop_phi_node);
1468 basic_block bb;
1470 if (dump_file && (dump_flags & TDF_DETAILS))
1472 fprintf (dump_file, "(analyze_evolution_in_loop \n");
1473 fprintf (dump_file, " (loop_phi_node = ");
1474 print_gimple_stmt (dump_file, loop_phi_node, 0, 0);
1475 fprintf (dump_file, ")\n");
1478 for (i = 0; i < n; i++)
1480 tree arg = PHI_ARG_DEF (loop_phi_node, i);
1481 gimple ssa_chain;
1482 tree ev_fn;
1483 t_bool res;
1485 /* Select the edges that enter the loop body. */
1486 bb = gimple_phi_arg_edge (loop_phi_node, i)->src;
1487 if (!flow_bb_inside_loop_p (loop, bb))
1488 continue;
1490 if (TREE_CODE (arg) == SSA_NAME)
1492 ssa_chain = SSA_NAME_DEF_STMT (arg);
1494 /* Pass in the initial condition to the follow edge function. */
1495 ev_fn = init_cond;
1496 res = follow_ssa_edge (loop, ssa_chain, loop_phi_node, &ev_fn, 0);
1498 else
1499 res = t_false;
1501 /* When it is impossible to go back on the same
1502 loop_phi_node by following the ssa edges, the
1503 evolution is represented by a peeled chrec, i.e. the
1504 first iteration, EV_FN has the value INIT_COND, then
1505 all the other iterations it has the value of ARG.
1506 For the moment, PEELED_CHREC nodes are not built. */
1507 if (res != t_true)
1508 ev_fn = chrec_dont_know;
1510 /* When there are multiple back edges of the loop (which in fact never
1511 happens currently, but nevertheless), merge their evolutions. */
1512 evolution_function = chrec_merge (evolution_function, ev_fn);
1515 if (dump_file && (dump_flags & TDF_DETAILS))
1517 fprintf (dump_file, " (evolution_function = ");
1518 print_generic_expr (dump_file, evolution_function, 0);
1519 fprintf (dump_file, "))\n");
1522 return evolution_function;
1525 /* Given a loop-phi-node, return the initial conditions of the
1526 variable on entry of the loop. When the CCP has propagated
1527 constants into the loop-phi-node, the initial condition is
1528 instantiated, otherwise the initial condition is kept symbolic.
1529 This analyzer does not analyze the evolution outside the current
1530 loop, and leaves this task to the on-demand tree reconstructor. */
1532 static tree
1533 analyze_initial_condition (gimple loop_phi_node)
1535 int i, n;
1536 tree init_cond = chrec_not_analyzed_yet;
1537 struct loop *loop = loop_containing_stmt (loop_phi_node);
1539 if (dump_file && (dump_flags & TDF_DETAILS))
1541 fprintf (dump_file, "(analyze_initial_condition \n");
1542 fprintf (dump_file, " (loop_phi_node = \n");
1543 print_gimple_stmt (dump_file, loop_phi_node, 0, 0);
1544 fprintf (dump_file, ")\n");
1547 n = gimple_phi_num_args (loop_phi_node);
1548 for (i = 0; i < n; i++)
1550 tree branch = PHI_ARG_DEF (loop_phi_node, i);
1551 basic_block bb = gimple_phi_arg_edge (loop_phi_node, i)->src;
1553 /* When the branch is oriented to the loop's body, it does
1554 not contribute to the initial condition. */
1555 if (flow_bb_inside_loop_p (loop, bb))
1556 continue;
1558 if (init_cond == chrec_not_analyzed_yet)
1560 init_cond = branch;
1561 continue;
1564 if (TREE_CODE (branch) == SSA_NAME)
1566 init_cond = chrec_dont_know;
1567 break;
1570 init_cond = chrec_merge (init_cond, branch);
1573 /* Ooops -- a loop without an entry??? */
1574 if (init_cond == chrec_not_analyzed_yet)
1575 init_cond = chrec_dont_know;
1577 /* During early loop unrolling we do not have fully constant propagated IL.
1578 Handle degenerate PHIs here to not miss important unrollings. */
1579 if (TREE_CODE (init_cond) == SSA_NAME)
1581 gimple def = SSA_NAME_DEF_STMT (init_cond);
1582 tree res;
1583 if (gimple_code (def) == GIMPLE_PHI
1584 && (res = degenerate_phi_result (def)) != NULL_TREE
1585 /* Only allow invariants here, otherwise we may break
1586 loop-closed SSA form. */
1587 && is_gimple_min_invariant (res))
1588 init_cond = res;
1591 if (dump_file && (dump_flags & TDF_DETAILS))
1593 fprintf (dump_file, " (init_cond = ");
1594 print_generic_expr (dump_file, init_cond, 0);
1595 fprintf (dump_file, "))\n");
1598 return init_cond;
1601 /* Analyze the scalar evolution for LOOP_PHI_NODE. */
1603 static tree
1604 interpret_loop_phi (struct loop *loop, gimple loop_phi_node)
1606 tree res;
1607 struct loop *phi_loop = loop_containing_stmt (loop_phi_node);
1608 tree init_cond;
1610 if (phi_loop != loop)
1612 struct loop *subloop;
1613 tree evolution_fn = analyze_scalar_evolution
1614 (phi_loop, PHI_RESULT (loop_phi_node));
1616 /* Dive one level deeper. */
1617 subloop = superloop_at_depth (phi_loop, loop_depth (loop) + 1);
1619 /* Interpret the subloop. */
1620 res = compute_overall_effect_of_inner_loop (subloop, evolution_fn);
1621 return res;
1624 /* Otherwise really interpret the loop phi. */
1625 init_cond = analyze_initial_condition (loop_phi_node);
1626 res = analyze_evolution_in_loop (loop_phi_node, init_cond);
1628 return res;
1631 /* This function merges the branches of a condition-phi-node,
1632 contained in the outermost loop, and whose arguments are already
1633 analyzed. */
1635 static tree
1636 interpret_condition_phi (struct loop *loop, gimple condition_phi)
1638 int i, n = gimple_phi_num_args (condition_phi);
1639 tree res = chrec_not_analyzed_yet;
1641 for (i = 0; i < n; i++)
1643 tree branch_chrec;
1645 if (backedge_phi_arg_p (condition_phi, i))
1647 res = chrec_dont_know;
1648 break;
1651 branch_chrec = analyze_scalar_evolution
1652 (loop, PHI_ARG_DEF (condition_phi, i));
1654 res = chrec_merge (res, branch_chrec);
1657 return res;
1660 /* Interpret the operation RHS1 OP RHS2. If we didn't
1661 analyze this node before, follow the definitions until ending
1662 either on an analyzed GIMPLE_ASSIGN, or on a loop-phi-node. On the
1663 return path, this function propagates evolutions (ala constant copy
1664 propagation). OPND1 is not a GIMPLE expression because we could
1665 analyze the effect of an inner loop: see interpret_loop_phi. */
1667 static tree
1668 interpret_rhs_expr (struct loop *loop, gimple at_stmt,
1669 tree type, tree rhs1, enum tree_code code, tree rhs2)
1671 tree res, chrec1, chrec2;
1673 if (get_gimple_rhs_class (code) == GIMPLE_SINGLE_RHS)
1675 if (is_gimple_min_invariant (rhs1))
1676 return chrec_convert (type, rhs1, at_stmt);
1678 if (code == SSA_NAME)
1679 return chrec_convert (type, analyze_scalar_evolution (loop, rhs1),
1680 at_stmt);
1682 if (code == ASSERT_EXPR)
1684 rhs1 = ASSERT_EXPR_VAR (rhs1);
1685 return chrec_convert (type, analyze_scalar_evolution (loop, rhs1),
1686 at_stmt);
1689 return chrec_dont_know;
1692 switch (code)
1694 case POINTER_PLUS_EXPR:
1695 chrec1 = analyze_scalar_evolution (loop, rhs1);
1696 chrec2 = analyze_scalar_evolution (loop, rhs2);
1697 chrec1 = chrec_convert (type, chrec1, at_stmt);
1698 chrec2 = chrec_convert (sizetype, chrec2, at_stmt);
1699 res = chrec_fold_plus (type, chrec1, chrec2);
1700 break;
1702 case PLUS_EXPR:
1703 chrec1 = analyze_scalar_evolution (loop, rhs1);
1704 chrec2 = analyze_scalar_evolution (loop, rhs2);
1705 chrec1 = chrec_convert (type, chrec1, at_stmt);
1706 chrec2 = chrec_convert (type, chrec2, at_stmt);
1707 res = chrec_fold_plus (type, chrec1, chrec2);
1708 break;
1710 case MINUS_EXPR:
1711 chrec1 = analyze_scalar_evolution (loop, rhs1);
1712 chrec2 = analyze_scalar_evolution (loop, rhs2);
1713 chrec1 = chrec_convert (type, chrec1, at_stmt);
1714 chrec2 = chrec_convert (type, chrec2, at_stmt);
1715 res = chrec_fold_minus (type, chrec1, chrec2);
1716 break;
1718 case NEGATE_EXPR:
1719 chrec1 = analyze_scalar_evolution (loop, rhs1);
1720 chrec1 = chrec_convert (type, chrec1, at_stmt);
1721 /* TYPE may be integer, real or complex, so use fold_convert. */
1722 res = chrec_fold_multiply (type, chrec1,
1723 fold_convert (type, integer_minus_one_node));
1724 break;
1726 case BIT_NOT_EXPR:
1727 /* Handle ~X as -1 - X. */
1728 chrec1 = analyze_scalar_evolution (loop, rhs1);
1729 chrec1 = chrec_convert (type, chrec1, at_stmt);
1730 res = chrec_fold_minus (type,
1731 fold_convert (type, integer_minus_one_node),
1732 chrec1);
1733 break;
1735 case MULT_EXPR:
1736 chrec1 = analyze_scalar_evolution (loop, rhs1);
1737 chrec2 = analyze_scalar_evolution (loop, rhs2);
1738 chrec1 = chrec_convert (type, chrec1, at_stmt);
1739 chrec2 = chrec_convert (type, chrec2, at_stmt);
1740 res = chrec_fold_multiply (type, chrec1, chrec2);
1741 break;
1743 CASE_CONVERT:
1744 chrec1 = analyze_scalar_evolution (loop, rhs1);
1745 res = chrec_convert (type, chrec1, at_stmt);
1746 break;
1748 default:
1749 res = chrec_dont_know;
1750 break;
1753 return res;
1756 /* Interpret the expression EXPR. */
1758 static tree
1759 interpret_expr (struct loop *loop, gimple at_stmt, tree expr)
1761 enum tree_code code;
1762 tree type = TREE_TYPE (expr), op0, op1;
1764 if (automatically_generated_chrec_p (expr))
1765 return expr;
1767 if (TREE_CODE (expr) == POLYNOMIAL_CHREC)
1768 return chrec_dont_know;
1770 extract_ops_from_tree (expr, &code, &op0, &op1);
1772 return interpret_rhs_expr (loop, at_stmt, type,
1773 op0, code, op1);
1776 /* Interpret the rhs of the assignment STMT. */
1778 static tree
1779 interpret_gimple_assign (struct loop *loop, gimple stmt)
1781 tree type = TREE_TYPE (gimple_assign_lhs (stmt));
1782 enum tree_code code = gimple_assign_rhs_code (stmt);
1784 return interpret_rhs_expr (loop, stmt, type,
1785 gimple_assign_rhs1 (stmt), code,
1786 gimple_assign_rhs2 (stmt));
1791 /* This section contains all the entry points:
1792 - number_of_iterations_in_loop,
1793 - analyze_scalar_evolution,
1794 - instantiate_parameters.
1797 /* Compute and return the evolution function in WRTO_LOOP, the nearest
1798 common ancestor of DEF_LOOP and USE_LOOP. */
1800 static tree
1801 compute_scalar_evolution_in_loop (struct loop *wrto_loop,
1802 struct loop *def_loop,
1803 tree ev)
1805 tree res;
1806 if (def_loop == wrto_loop)
1807 return ev;
1809 def_loop = superloop_at_depth (def_loop, loop_depth (wrto_loop) + 1);
1810 res = compute_overall_effect_of_inner_loop (def_loop, ev);
1812 return analyze_scalar_evolution_1 (wrto_loop, res, chrec_not_analyzed_yet);
1815 /* Helper recursive function. */
1817 static tree
1818 analyze_scalar_evolution_1 (struct loop *loop, tree var, tree res)
1820 tree type = TREE_TYPE (var);
1821 gimple def;
1822 basic_block bb;
1823 struct loop *def_loop;
1825 if (loop == NULL || TREE_CODE (type) == VECTOR_TYPE)
1826 return chrec_dont_know;
1828 if (TREE_CODE (var) != SSA_NAME)
1829 return interpret_expr (loop, NULL, var);
1831 def = SSA_NAME_DEF_STMT (var);
1832 bb = gimple_bb (def);
1833 def_loop = bb ? bb->loop_father : NULL;
1835 if (bb == NULL
1836 || !flow_bb_inside_loop_p (loop, bb))
1838 /* Keep the symbolic form. */
1839 res = var;
1840 goto set_and_end;
1843 if (res != chrec_not_analyzed_yet)
1845 if (loop != bb->loop_father)
1846 res = compute_scalar_evolution_in_loop
1847 (find_common_loop (loop, bb->loop_father), bb->loop_father, res);
1849 goto set_and_end;
1852 if (loop != def_loop)
1854 res = analyze_scalar_evolution_1 (def_loop, var, chrec_not_analyzed_yet);
1855 res = compute_scalar_evolution_in_loop (loop, def_loop, res);
1857 goto set_and_end;
1860 switch (gimple_code (def))
1862 case GIMPLE_ASSIGN:
1863 res = interpret_gimple_assign (loop, def);
1864 break;
1866 case GIMPLE_PHI:
1867 if (loop_phi_node_p (def))
1868 res = interpret_loop_phi (loop, def);
1869 else
1870 res = interpret_condition_phi (loop, def);
1871 break;
1873 default:
1874 res = chrec_dont_know;
1875 break;
1878 set_and_end:
1880 /* Keep the symbolic form. */
1881 if (res == chrec_dont_know)
1882 res = var;
1884 if (loop == def_loop)
1885 set_scalar_evolution (block_before_loop (loop), var, res);
1887 return res;
1890 /* Entry point for the scalar evolution analyzer.
1891 Analyzes and returns the scalar evolution of the ssa_name VAR.
1892 LOOP_NB is the identifier number of the loop in which the variable
1893 is used.
1895 Example of use: having a pointer VAR to a SSA_NAME node, STMT a
1896 pointer to the statement that uses this variable, in order to
1897 determine the evolution function of the variable, use the following
1898 calls:
1900 unsigned loop_nb = loop_containing_stmt (stmt)->num;
1901 tree chrec_with_symbols = analyze_scalar_evolution (loop_nb, var);
1902 tree chrec_instantiated = instantiate_parameters (loop, chrec_with_symbols);
1905 tree
1906 analyze_scalar_evolution (struct loop *loop, tree var)
1908 tree res;
1910 if (dump_file && (dump_flags & TDF_DETAILS))
1912 fprintf (dump_file, "(analyze_scalar_evolution \n");
1913 fprintf (dump_file, " (loop_nb = %d)\n", loop->num);
1914 fprintf (dump_file, " (scalar = ");
1915 print_generic_expr (dump_file, var, 0);
1916 fprintf (dump_file, ")\n");
1919 res = get_scalar_evolution (block_before_loop (loop), var);
1920 res = analyze_scalar_evolution_1 (loop, var, res);
1922 if (dump_file && (dump_flags & TDF_DETAILS))
1923 fprintf (dump_file, ")\n");
1925 return res;
1928 /* Analyze scalar evolution of use of VERSION in USE_LOOP with respect to
1929 WRTO_LOOP (which should be a superloop of USE_LOOP)
1931 FOLDED_CASTS is set to true if resolve_mixers used
1932 chrec_convert_aggressive (TODO -- not really, we are way too conservative
1933 at the moment in order to keep things simple).
1935 To illustrate the meaning of USE_LOOP and WRTO_LOOP, consider the following
1936 example:
1938 for (i = 0; i < 100; i++) -- loop 1
1940 for (j = 0; j < 100; j++) -- loop 2
1942 k1 = i;
1943 k2 = j;
1945 use2 (k1, k2);
1947 for (t = 0; t < 100; t++) -- loop 3
1948 use3 (k1, k2);
1951 use1 (k1, k2);
1954 Both k1 and k2 are invariants in loop3, thus
1955 analyze_scalar_evolution_in_loop (loop3, loop3, k1) = k1
1956 analyze_scalar_evolution_in_loop (loop3, loop3, k2) = k2
1958 As they are invariant, it does not matter whether we consider their
1959 usage in loop 3 or loop 2, hence
1960 analyze_scalar_evolution_in_loop (loop2, loop3, k1) =
1961 analyze_scalar_evolution_in_loop (loop2, loop2, k1) = i
1962 analyze_scalar_evolution_in_loop (loop2, loop3, k2) =
1963 analyze_scalar_evolution_in_loop (loop2, loop2, k2) = [0,+,1]_2
1965 Similarly for their evolutions with respect to loop 1. The values of K2
1966 in the use in loop 2 vary independently on loop 1, thus we cannot express
1967 the evolution with respect to loop 1:
1968 analyze_scalar_evolution_in_loop (loop1, loop3, k1) =
1969 analyze_scalar_evolution_in_loop (loop1, loop2, k1) = [0,+,1]_1
1970 analyze_scalar_evolution_in_loop (loop1, loop3, k2) =
1971 analyze_scalar_evolution_in_loop (loop1, loop2, k2) = dont_know
1973 The value of k2 in the use in loop 1 is known, though:
1974 analyze_scalar_evolution_in_loop (loop1, loop1, k1) = [0,+,1]_1
1975 analyze_scalar_evolution_in_loop (loop1, loop1, k2) = 100
1978 static tree
1979 analyze_scalar_evolution_in_loop (struct loop *wrto_loop, struct loop *use_loop,
1980 tree version, bool *folded_casts)
1982 bool val = false;
1983 tree ev = version, tmp;
1985 /* We cannot just do
1987 tmp = analyze_scalar_evolution (use_loop, version);
1988 ev = resolve_mixers (wrto_loop, tmp);
1990 as resolve_mixers would query the scalar evolution with respect to
1991 wrto_loop. For example, in the situation described in the function
1992 comment, suppose that wrto_loop = loop1, use_loop = loop3 and
1993 version = k2. Then
1995 analyze_scalar_evolution (use_loop, version) = k2
1997 and resolve_mixers (loop1, k2) finds that the value of k2 in loop 1
1998 is 100, which is a wrong result, since we are interested in the
1999 value in loop 3.
2001 Instead, we need to proceed from use_loop to wrto_loop loop by loop,
2002 each time checking that there is no evolution in the inner loop. */
2004 if (folded_casts)
2005 *folded_casts = false;
2006 while (1)
2008 tmp = analyze_scalar_evolution (use_loop, ev);
2009 ev = resolve_mixers (use_loop, tmp);
2011 if (folded_casts && tmp != ev)
2012 *folded_casts = true;
2014 if (use_loop == wrto_loop)
2015 return ev;
2017 /* If the value of the use changes in the inner loop, we cannot express
2018 its value in the outer loop (we might try to return interval chrec,
2019 but we do not have a user for it anyway) */
2020 if (!no_evolution_in_loop_p (ev, use_loop->num, &val)
2021 || !val)
2022 return chrec_dont_know;
2024 use_loop = loop_outer (use_loop);
2028 /* Returns from CACHE the value for VERSION instantiated below
2029 INSTANTIATED_BELOW block. */
2031 static tree
2032 get_instantiated_value (htab_t cache, basic_block instantiated_below,
2033 tree version)
2035 struct scev_info_str *info, pattern;
2037 pattern.var = version;
2038 pattern.instantiated_below = instantiated_below;
2039 info = (struct scev_info_str *) htab_find (cache, &pattern);
2041 if (info)
2042 return info->chrec;
2043 else
2044 return NULL_TREE;
2047 /* Sets in CACHE the value of VERSION instantiated below basic block
2048 INSTANTIATED_BELOW to VAL. */
2050 static void
2051 set_instantiated_value (htab_t cache, basic_block instantiated_below,
2052 tree version, tree val)
2054 struct scev_info_str *info, pattern;
2055 PTR *slot;
2057 pattern.var = version;
2058 pattern.instantiated_below = instantiated_below;
2059 slot = htab_find_slot (cache, &pattern, INSERT);
2061 if (!*slot)
2062 *slot = new_scev_info_str (instantiated_below, version);
2063 info = (struct scev_info_str *) *slot;
2064 info->chrec = val;
2067 /* Return the closed_loop_phi node for VAR. If there is none, return
2068 NULL_TREE. */
2070 static tree
2071 loop_closed_phi_def (tree var)
2073 struct loop *loop;
2074 edge exit;
2075 gimple phi;
2076 gimple_stmt_iterator psi;
2078 if (var == NULL_TREE
2079 || TREE_CODE (var) != SSA_NAME)
2080 return NULL_TREE;
2082 loop = loop_containing_stmt (SSA_NAME_DEF_STMT (var));
2083 exit = single_exit (loop);
2084 if (!exit)
2085 return NULL_TREE;
2087 for (psi = gsi_start_phis (exit->dest); !gsi_end_p (psi); gsi_next (&psi))
2089 phi = gsi_stmt (psi);
2090 if (PHI_ARG_DEF_FROM_EDGE (phi, exit) == var)
2091 return PHI_RESULT (phi);
2094 return NULL_TREE;
2097 /* Analyze all the parameters of the chrec, between INSTANTIATE_BELOW
2098 and EVOLUTION_LOOP, that were left under a symbolic form.
2100 CHREC is the scalar evolution to instantiate.
2102 CACHE is the cache of already instantiated values.
2104 FOLD_CONVERSIONS should be set to true when the conversions that
2105 may wrap in signed/pointer type are folded, as long as the value of
2106 the chrec is preserved.
2108 SIZE_EXPR is used for computing the size of the expression to be
2109 instantiated, and to stop if it exceeds some limit. */
2111 static tree
2112 instantiate_scev_1 (basic_block instantiate_below,
2113 struct loop *evolution_loop, tree chrec,
2114 bool fold_conversions, htab_t cache, int size_expr)
2116 tree res, op0, op1, op2;
2117 basic_block def_bb;
2118 struct loop *def_loop;
2119 tree type = chrec_type (chrec);
2121 /* Give up if the expression is larger than the MAX that we allow. */
2122 if (size_expr++ > PARAM_VALUE (PARAM_SCEV_MAX_EXPR_SIZE))
2123 return chrec_dont_know;
2125 if (automatically_generated_chrec_p (chrec)
2126 || is_gimple_min_invariant (chrec))
2127 return chrec;
2129 switch (TREE_CODE (chrec))
2131 case SSA_NAME:
2132 def_bb = gimple_bb (SSA_NAME_DEF_STMT (chrec));
2134 /* A parameter (or loop invariant and we do not want to include
2135 evolutions in outer loops), nothing to do. */
2136 if (!def_bb
2137 || loop_depth (def_bb->loop_father) == 0
2138 || dominated_by_p (CDI_DOMINATORS, instantiate_below, def_bb))
2139 return chrec;
2141 /* We cache the value of instantiated variable to avoid exponential
2142 time complexity due to reevaluations. We also store the convenient
2143 value in the cache in order to prevent infinite recursion -- we do
2144 not want to instantiate the SSA_NAME if it is in a mixer
2145 structure. This is used for avoiding the instantiation of
2146 recursively defined functions, such as:
2148 | a_2 -> {0, +, 1, +, a_2}_1 */
2150 res = get_instantiated_value (cache, instantiate_below, chrec);
2151 if (res)
2152 return res;
2154 res = chrec_dont_know;
2155 set_instantiated_value (cache, instantiate_below, chrec, res);
2157 def_loop = find_common_loop (evolution_loop, def_bb->loop_father);
2159 /* If the analysis yields a parametric chrec, instantiate the
2160 result again. */
2161 res = analyze_scalar_evolution (def_loop, chrec);
2163 /* Don't instantiate loop-closed-ssa phi nodes. */
2164 if (TREE_CODE (res) == SSA_NAME
2165 && (loop_containing_stmt (SSA_NAME_DEF_STMT (res)) == NULL
2166 || (loop_depth (loop_containing_stmt (SSA_NAME_DEF_STMT (res)))
2167 > loop_depth (def_loop))))
2169 if (res == chrec)
2170 res = loop_closed_phi_def (chrec);
2171 else
2172 res = chrec;
2174 if (res == NULL_TREE)
2175 res = chrec_dont_know;
2178 else if (res != chrec_dont_know)
2179 res = instantiate_scev_1 (instantiate_below, evolution_loop, res,
2180 fold_conversions, cache, size_expr);
2182 /* Store the correct value to the cache. */
2183 set_instantiated_value (cache, instantiate_below, chrec, res);
2184 return res;
2186 case POLYNOMIAL_CHREC:
2187 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2188 CHREC_LEFT (chrec), fold_conversions, cache,
2189 size_expr);
2190 if (op0 == chrec_dont_know)
2191 return chrec_dont_know;
2193 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2194 CHREC_RIGHT (chrec), fold_conversions, cache,
2195 size_expr);
2196 if (op1 == chrec_dont_know)
2197 return chrec_dont_know;
2199 if (CHREC_LEFT (chrec) != op0
2200 || CHREC_RIGHT (chrec) != op1)
2202 op1 = chrec_convert_rhs (chrec_type (op0), op1, NULL);
2203 chrec = build_polynomial_chrec (CHREC_VARIABLE (chrec), op0, op1);
2205 return chrec;
2207 case POINTER_PLUS_EXPR:
2208 case PLUS_EXPR:
2209 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2210 TREE_OPERAND (chrec, 0), fold_conversions, cache,
2211 size_expr);
2212 if (op0 == chrec_dont_know)
2213 return chrec_dont_know;
2215 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2216 TREE_OPERAND (chrec, 1), fold_conversions, cache,
2217 size_expr);
2218 if (op1 == chrec_dont_know)
2219 return chrec_dont_know;
2221 if (TREE_OPERAND (chrec, 0) != op0
2222 || TREE_OPERAND (chrec, 1) != op1)
2224 op0 = chrec_convert (type, op0, NULL);
2225 op1 = chrec_convert_rhs (type, op1, NULL);
2226 chrec = chrec_fold_plus (type, op0, op1);
2228 return chrec;
2230 case MINUS_EXPR:
2231 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2232 TREE_OPERAND (chrec, 0), fold_conversions, cache,
2233 size_expr);
2234 if (op0 == chrec_dont_know)
2235 return chrec_dont_know;
2237 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2238 TREE_OPERAND (chrec, 1),
2239 fold_conversions, cache, size_expr);
2240 if (op1 == chrec_dont_know)
2241 return chrec_dont_know;
2243 if (TREE_OPERAND (chrec, 0) != op0
2244 || TREE_OPERAND (chrec, 1) != op1)
2246 op0 = chrec_convert (type, op0, NULL);
2247 op1 = chrec_convert (type, op1, NULL);
2248 chrec = chrec_fold_minus (type, op0, op1);
2250 return chrec;
2252 case MULT_EXPR:
2253 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2254 TREE_OPERAND (chrec, 0),
2255 fold_conversions, cache, size_expr);
2256 if (op0 == chrec_dont_know)
2257 return chrec_dont_know;
2259 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2260 TREE_OPERAND (chrec, 1),
2261 fold_conversions, cache, size_expr);
2262 if (op1 == chrec_dont_know)
2263 return chrec_dont_know;
2265 if (TREE_OPERAND (chrec, 0) != op0
2266 || TREE_OPERAND (chrec, 1) != op1)
2268 op0 = chrec_convert (type, op0, NULL);
2269 op1 = chrec_convert (type, op1, NULL);
2270 chrec = chrec_fold_multiply (type, op0, op1);
2272 return chrec;
2274 CASE_CONVERT:
2275 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2276 TREE_OPERAND (chrec, 0),
2277 fold_conversions, cache, size_expr);
2278 if (op0 == chrec_dont_know)
2279 return chrec_dont_know;
2281 if (fold_conversions)
2283 tree tmp = chrec_convert_aggressive (TREE_TYPE (chrec), op0);
2284 if (tmp)
2285 return tmp;
2288 if (op0 == TREE_OPERAND (chrec, 0))
2289 return chrec;
2291 /* If we used chrec_convert_aggressive, we can no longer assume that
2292 signed chrecs do not overflow, as chrec_convert does, so avoid
2293 calling it in that case. */
2294 if (fold_conversions)
2295 return fold_convert (TREE_TYPE (chrec), op0);
2297 return chrec_convert (TREE_TYPE (chrec), op0, NULL);
2299 case BIT_NOT_EXPR:
2300 /* Handle ~X as -1 - X. */
2301 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2302 TREE_OPERAND (chrec, 0),
2303 fold_conversions, cache, size_expr);
2304 if (op0 == chrec_dont_know)
2305 return chrec_dont_know;
2307 if (TREE_OPERAND (chrec, 0) != op0)
2309 op0 = chrec_convert (type, op0, NULL);
2310 chrec = chrec_fold_minus (type,
2311 fold_convert (type,
2312 integer_minus_one_node),
2313 op0);
2315 return chrec;
2317 case SCEV_NOT_KNOWN:
2318 return chrec_dont_know;
2320 case SCEV_KNOWN:
2321 return chrec_known;
2323 default:
2324 break;
2327 if (VL_EXP_CLASS_P (chrec))
2328 return chrec_dont_know;
2330 switch (TREE_CODE_LENGTH (TREE_CODE (chrec)))
2332 case 3:
2333 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2334 TREE_OPERAND (chrec, 0),
2335 fold_conversions, cache, size_expr);
2336 if (op0 == chrec_dont_know)
2337 return chrec_dont_know;
2339 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2340 TREE_OPERAND (chrec, 1),
2341 fold_conversions, cache, size_expr);
2342 if (op1 == chrec_dont_know)
2343 return chrec_dont_know;
2345 op2 = instantiate_scev_1 (instantiate_below, evolution_loop,
2346 TREE_OPERAND (chrec, 2),
2347 fold_conversions, cache, size_expr);
2348 if (op2 == chrec_dont_know)
2349 return chrec_dont_know;
2351 if (op0 == TREE_OPERAND (chrec, 0)
2352 && op1 == TREE_OPERAND (chrec, 1)
2353 && op2 == TREE_OPERAND (chrec, 2))
2354 return chrec;
2356 return fold_build3 (TREE_CODE (chrec),
2357 TREE_TYPE (chrec), op0, op1, op2);
2359 case 2:
2360 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2361 TREE_OPERAND (chrec, 0),
2362 fold_conversions, cache, size_expr);
2363 if (op0 == chrec_dont_know)
2364 return chrec_dont_know;
2366 op1 = instantiate_scev_1 (instantiate_below, evolution_loop,
2367 TREE_OPERAND (chrec, 1),
2368 fold_conversions, cache, size_expr);
2369 if (op1 == chrec_dont_know)
2370 return chrec_dont_know;
2372 if (op0 == TREE_OPERAND (chrec, 0)
2373 && op1 == TREE_OPERAND (chrec, 1))
2374 return chrec;
2375 return fold_build2 (TREE_CODE (chrec), TREE_TYPE (chrec), op0, op1);
2377 case 1:
2378 op0 = instantiate_scev_1 (instantiate_below, evolution_loop,
2379 TREE_OPERAND (chrec, 0),
2380 fold_conversions, cache, size_expr);
2381 if (op0 == chrec_dont_know)
2382 return chrec_dont_know;
2383 if (op0 == TREE_OPERAND (chrec, 0))
2384 return chrec;
2385 return fold_build1 (TREE_CODE (chrec), TREE_TYPE (chrec), op0);
2387 case 0:
2388 return chrec;
2390 default:
2391 break;
2394 /* Too complicated to handle. */
2395 return chrec_dont_know;
2398 /* Analyze all the parameters of the chrec that were left under a
2399 symbolic form. INSTANTIATE_BELOW is the basic block that stops the
2400 recursive instantiation of parameters: a parameter is a variable
2401 that is defined in a basic block that dominates INSTANTIATE_BELOW or
2402 a function parameter. */
2404 tree
2405 instantiate_scev (basic_block instantiate_below, struct loop *evolution_loop,
2406 tree chrec)
2408 tree res;
2409 htab_t cache = htab_create (10, hash_scev_info, eq_scev_info, del_scev_info);
2411 if (dump_file && (dump_flags & TDF_DETAILS))
2413 fprintf (dump_file, "(instantiate_scev \n");
2414 fprintf (dump_file, " (instantiate_below = %d)\n", instantiate_below->index);
2415 fprintf (dump_file, " (evolution_loop = %d)\n", evolution_loop->num);
2416 fprintf (dump_file, " (chrec = ");
2417 print_generic_expr (dump_file, chrec, 0);
2418 fprintf (dump_file, ")\n");
2421 res = instantiate_scev_1 (instantiate_below, evolution_loop, chrec, false,
2422 cache, 0);
2424 if (dump_file && (dump_flags & TDF_DETAILS))
2426 fprintf (dump_file, " (res = ");
2427 print_generic_expr (dump_file, res, 0);
2428 fprintf (dump_file, "))\n");
2431 htab_delete (cache);
2433 return res;
2436 /* Similar to instantiate_parameters, but does not introduce the
2437 evolutions in outer loops for LOOP invariants in CHREC, and does not
2438 care about causing overflows, as long as they do not affect value
2439 of an expression. */
2441 tree
2442 resolve_mixers (struct loop *loop, tree chrec)
2444 htab_t cache = htab_create (10, hash_scev_info, eq_scev_info, del_scev_info);
2445 tree ret = instantiate_scev_1 (block_before_loop (loop), loop, chrec, true,
2446 cache, 0);
2447 htab_delete (cache);
2448 return ret;
2451 /* Entry point for the analysis of the number of iterations pass.
2452 This function tries to safely approximate the number of iterations
2453 the loop will run. When this property is not decidable at compile
2454 time, the result is chrec_dont_know. Otherwise the result is
2455 a scalar or a symbolic parameter.
2457 Example of analysis: suppose that the loop has an exit condition:
2459 "if (b > 49) goto end_loop;"
2461 and that in a previous analysis we have determined that the
2462 variable 'b' has an evolution function:
2464 "EF = {23, +, 5}_2".
2466 When we evaluate the function at the point 5, i.e. the value of the
2467 variable 'b' after 5 iterations in the loop, we have EF (5) = 48,
2468 and EF (6) = 53. In this case the value of 'b' on exit is '53' and
2469 the loop body has been executed 6 times. */
2471 tree
2472 number_of_latch_executions (struct loop *loop)
2474 tree res, type;
2475 edge exit;
2476 struct tree_niter_desc niter_desc;
2478 /* Determine whether the number_of_iterations_in_loop has already
2479 been computed. */
2480 res = loop->nb_iterations;
2481 if (res)
2482 return res;
2483 res = chrec_dont_know;
2485 if (dump_file && (dump_flags & TDF_DETAILS))
2486 fprintf (dump_file, "(number_of_iterations_in_loop\n");
2488 exit = single_exit (loop);
2489 if (!exit)
2490 goto end;
2492 if (!number_of_iterations_exit (loop, exit, &niter_desc, false))
2493 goto end;
2495 type = TREE_TYPE (niter_desc.niter);
2496 if (integer_nonzerop (niter_desc.may_be_zero))
2497 res = build_int_cst (type, 0);
2498 else if (integer_zerop (niter_desc.may_be_zero))
2499 res = niter_desc.niter;
2500 else
2501 res = chrec_dont_know;
2503 end:
2504 return set_nb_iterations_in_loop (loop, res);
2507 /* Returns the number of executions of the exit condition of LOOP,
2508 i.e., the number by one higher than number_of_latch_executions.
2509 Note that unlike number_of_latch_executions, this number does
2510 not necessarily fit in the unsigned variant of the type of
2511 the control variable -- if the number of iterations is a constant,
2512 we return chrec_dont_know if adding one to number_of_latch_executions
2513 overflows; however, in case the number of iterations is symbolic
2514 expression, the caller is responsible for dealing with this
2515 the possible overflow. */
2517 tree
2518 number_of_exit_cond_executions (struct loop *loop)
2520 tree ret = number_of_latch_executions (loop);
2521 tree type = chrec_type (ret);
2523 if (chrec_contains_undetermined (ret))
2524 return ret;
2526 ret = chrec_fold_plus (type, ret, build_int_cst (type, 1));
2527 if (TREE_CODE (ret) == INTEGER_CST
2528 && TREE_OVERFLOW (ret))
2529 return chrec_dont_know;
2531 return ret;
2534 /* One of the drivers for testing the scalar evolutions analysis.
2535 This function computes the number of iterations for all the loops
2536 from the EXIT_CONDITIONS array. */
2538 static void
2539 number_of_iterations_for_all_loops (VEC(gimple,heap) **exit_conditions)
2541 unsigned int i;
2542 unsigned nb_chrec_dont_know_loops = 0;
2543 unsigned nb_static_loops = 0;
2544 gimple cond;
2546 for (i = 0; VEC_iterate (gimple, *exit_conditions, i, cond); i++)
2548 tree res = number_of_latch_executions (loop_containing_stmt (cond));
2549 if (chrec_contains_undetermined (res))
2550 nb_chrec_dont_know_loops++;
2551 else
2552 nb_static_loops++;
2555 if (dump_file)
2557 fprintf (dump_file, "\n(\n");
2558 fprintf (dump_file, "-----------------------------------------\n");
2559 fprintf (dump_file, "%d\tnb_chrec_dont_know_loops\n", nb_chrec_dont_know_loops);
2560 fprintf (dump_file, "%d\tnb_static_loops\n", nb_static_loops);
2561 fprintf (dump_file, "%d\tnb_total_loops\n", number_of_loops ());
2562 fprintf (dump_file, "-----------------------------------------\n");
2563 fprintf (dump_file, ")\n\n");
2565 print_loops (dump_file, 3);
2571 /* Counters for the stats. */
2573 struct chrec_stats
2575 unsigned nb_chrecs;
2576 unsigned nb_affine;
2577 unsigned nb_affine_multivar;
2578 unsigned nb_higher_poly;
2579 unsigned nb_chrec_dont_know;
2580 unsigned nb_undetermined;
2583 /* Reset the counters. */
2585 static inline void
2586 reset_chrecs_counters (struct chrec_stats *stats)
2588 stats->nb_chrecs = 0;
2589 stats->nb_affine = 0;
2590 stats->nb_affine_multivar = 0;
2591 stats->nb_higher_poly = 0;
2592 stats->nb_chrec_dont_know = 0;
2593 stats->nb_undetermined = 0;
2596 /* Dump the contents of a CHREC_STATS structure. */
2598 static void
2599 dump_chrecs_stats (FILE *file, struct chrec_stats *stats)
2601 fprintf (file, "\n(\n");
2602 fprintf (file, "-----------------------------------------\n");
2603 fprintf (file, "%d\taffine univariate chrecs\n", stats->nb_affine);
2604 fprintf (file, "%d\taffine multivariate chrecs\n", stats->nb_affine_multivar);
2605 fprintf (file, "%d\tdegree greater than 2 polynomials\n",
2606 stats->nb_higher_poly);
2607 fprintf (file, "%d\tchrec_dont_know chrecs\n", stats->nb_chrec_dont_know);
2608 fprintf (file, "-----------------------------------------\n");
2609 fprintf (file, "%d\ttotal chrecs\n", stats->nb_chrecs);
2610 fprintf (file, "%d\twith undetermined coefficients\n",
2611 stats->nb_undetermined);
2612 fprintf (file, "-----------------------------------------\n");
2613 fprintf (file, "%d\tchrecs in the scev database\n",
2614 (int) htab_elements (scalar_evolution_info));
2615 fprintf (file, "%d\tsets in the scev database\n", nb_set_scev);
2616 fprintf (file, "%d\tgets in the scev database\n", nb_get_scev);
2617 fprintf (file, "-----------------------------------------\n");
2618 fprintf (file, ")\n\n");
2621 /* Gather statistics about CHREC. */
2623 static void
2624 gather_chrec_stats (tree chrec, struct chrec_stats *stats)
2626 if (dump_file && (dump_flags & TDF_STATS))
2628 fprintf (dump_file, "(classify_chrec ");
2629 print_generic_expr (dump_file, chrec, 0);
2630 fprintf (dump_file, "\n");
2633 stats->nb_chrecs++;
2635 if (chrec == NULL_TREE)
2637 stats->nb_undetermined++;
2638 return;
2641 switch (TREE_CODE (chrec))
2643 case POLYNOMIAL_CHREC:
2644 if (evolution_function_is_affine_p (chrec))
2646 if (dump_file && (dump_flags & TDF_STATS))
2647 fprintf (dump_file, " affine_univariate\n");
2648 stats->nb_affine++;
2650 else if (evolution_function_is_affine_multivariate_p (chrec, 0))
2652 if (dump_file && (dump_flags & TDF_STATS))
2653 fprintf (dump_file, " affine_multivariate\n");
2654 stats->nb_affine_multivar++;
2656 else
2658 if (dump_file && (dump_flags & TDF_STATS))
2659 fprintf (dump_file, " higher_degree_polynomial\n");
2660 stats->nb_higher_poly++;
2663 break;
2665 default:
2666 break;
2669 if (chrec_contains_undetermined (chrec))
2671 if (dump_file && (dump_flags & TDF_STATS))
2672 fprintf (dump_file, " undetermined\n");
2673 stats->nb_undetermined++;
2676 if (dump_file && (dump_flags & TDF_STATS))
2677 fprintf (dump_file, ")\n");
2680 /* One of the drivers for testing the scalar evolutions analysis.
2681 This function analyzes the scalar evolution of all the scalars
2682 defined as loop phi nodes in one of the loops from the
2683 EXIT_CONDITIONS array.
2685 TODO Optimization: A loop is in canonical form if it contains only
2686 a single scalar loop phi node. All the other scalars that have an
2687 evolution in the loop are rewritten in function of this single
2688 index. This allows the parallelization of the loop. */
2690 static void
2691 analyze_scalar_evolution_for_all_loop_phi_nodes (VEC(gimple,heap) **exit_conditions)
2693 unsigned int i;
2694 struct chrec_stats stats;
2695 gimple cond, phi;
2696 gimple_stmt_iterator psi;
2698 reset_chrecs_counters (&stats);
2700 for (i = 0; VEC_iterate (gimple, *exit_conditions, i, cond); i++)
2702 struct loop *loop;
2703 basic_block bb;
2704 tree chrec;
2706 loop = loop_containing_stmt (cond);
2707 bb = loop->header;
2709 for (psi = gsi_start_phis (bb); !gsi_end_p (psi); gsi_next (&psi))
2711 phi = gsi_stmt (psi);
2712 if (is_gimple_reg (PHI_RESULT (phi)))
2714 chrec = instantiate_parameters
2715 (loop,
2716 analyze_scalar_evolution (loop, PHI_RESULT (phi)));
2718 if (dump_file && (dump_flags & TDF_STATS))
2719 gather_chrec_stats (chrec, &stats);
2724 if (dump_file && (dump_flags & TDF_STATS))
2725 dump_chrecs_stats (dump_file, &stats);
2728 /* Callback for htab_traverse, gathers information on chrecs in the
2729 hashtable. */
2731 static int
2732 gather_stats_on_scev_database_1 (void **slot, void *stats)
2734 struct scev_info_str *entry = (struct scev_info_str *) *slot;
2736 gather_chrec_stats (entry->chrec, (struct chrec_stats *) stats);
2738 return 1;
2741 /* Classify the chrecs of the whole database. */
2743 void
2744 gather_stats_on_scev_database (void)
2746 struct chrec_stats stats;
2748 if (!dump_file)
2749 return;
2751 reset_chrecs_counters (&stats);
2753 htab_traverse (scalar_evolution_info, gather_stats_on_scev_database_1,
2754 &stats);
2756 dump_chrecs_stats (dump_file, &stats);
2761 /* Initializer. */
2763 static void
2764 initialize_scalar_evolutions_analyzer (void)
2766 /* The elements below are unique. */
2767 if (chrec_dont_know == NULL_TREE)
2769 chrec_not_analyzed_yet = NULL_TREE;
2770 chrec_dont_know = make_node (SCEV_NOT_KNOWN);
2771 chrec_known = make_node (SCEV_KNOWN);
2772 TREE_TYPE (chrec_dont_know) = void_type_node;
2773 TREE_TYPE (chrec_known) = void_type_node;
2777 /* Initialize the analysis of scalar evolutions for LOOPS. */
2779 void
2780 scev_initialize (void)
2782 loop_iterator li;
2783 struct loop *loop;
2785 scalar_evolution_info = htab_create_alloc (100,
2786 hash_scev_info,
2787 eq_scev_info,
2788 del_scev_info,
2789 ggc_calloc,
2790 ggc_free);
2792 initialize_scalar_evolutions_analyzer ();
2794 FOR_EACH_LOOP (li, loop, 0)
2796 loop->nb_iterations = NULL_TREE;
2800 /* Cleans up the information cached by the scalar evolutions analysis. */
2802 void
2803 scev_reset (void)
2805 loop_iterator li;
2806 struct loop *loop;
2808 if (!scalar_evolution_info || !current_loops)
2809 return;
2811 htab_empty (scalar_evolution_info);
2812 FOR_EACH_LOOP (li, loop, 0)
2814 loop->nb_iterations = NULL_TREE;
2818 /* Checks whether use of OP in USE_LOOP behaves as a simple affine iv with
2819 respect to WRTO_LOOP and returns its base and step in IV if possible
2820 (see analyze_scalar_evolution_in_loop for more details on USE_LOOP
2821 and WRTO_LOOP). If ALLOW_NONCONSTANT_STEP is true, we want step to be
2822 invariant in LOOP. Otherwise we require it to be an integer constant.
2824 IV->no_overflow is set to true if we are sure the iv cannot overflow (e.g.
2825 because it is computed in signed arithmetics). Consequently, adding an
2826 induction variable
2828 for (i = IV->base; ; i += IV->step)
2830 is only safe if IV->no_overflow is false, or TYPE_OVERFLOW_UNDEFINED is
2831 false for the type of the induction variable, or you can prove that i does
2832 not wrap by some other argument. Otherwise, this might introduce undefined
2833 behavior, and
2835 for (i = iv->base; ; i = (type) ((unsigned type) i + (unsigned type) iv->step))
2837 must be used instead. */
2839 bool
2840 simple_iv (struct loop *wrto_loop, struct loop *use_loop, tree op,
2841 affine_iv *iv, bool allow_nonconstant_step)
2843 tree type, ev;
2844 bool folded_casts;
2846 iv->base = NULL_TREE;
2847 iv->step = NULL_TREE;
2848 iv->no_overflow = false;
2850 type = TREE_TYPE (op);
2851 if (TREE_CODE (type) != INTEGER_TYPE
2852 && TREE_CODE (type) != POINTER_TYPE)
2853 return false;
2855 ev = analyze_scalar_evolution_in_loop (wrto_loop, use_loop, op,
2856 &folded_casts);
2857 if (chrec_contains_undetermined (ev)
2858 || chrec_contains_symbols_defined_in_loop (ev, wrto_loop->num))
2859 return false;
2861 if (tree_does_not_contain_chrecs (ev))
2863 iv->base = ev;
2864 iv->step = build_int_cst (TREE_TYPE (ev), 0);
2865 iv->no_overflow = true;
2866 return true;
2869 if (TREE_CODE (ev) != POLYNOMIAL_CHREC
2870 || CHREC_VARIABLE (ev) != (unsigned) wrto_loop->num)
2871 return false;
2873 iv->step = CHREC_RIGHT (ev);
2874 if ((!allow_nonconstant_step && TREE_CODE (iv->step) != INTEGER_CST)
2875 || tree_contains_chrecs (iv->step, NULL))
2876 return false;
2878 iv->base = CHREC_LEFT (ev);
2879 if (tree_contains_chrecs (iv->base, NULL))
2880 return false;
2882 iv->no_overflow = !folded_casts && TYPE_OVERFLOW_UNDEFINED (type);
2884 return true;
2887 /* Runs the analysis of scalar evolutions. */
2889 void
2890 scev_analysis (void)
2892 VEC(gimple,heap) *exit_conditions;
2894 exit_conditions = VEC_alloc (gimple, heap, 37);
2895 select_loops_exit_conditions (&exit_conditions);
2897 if (dump_file && (dump_flags & TDF_STATS))
2898 analyze_scalar_evolution_for_all_loop_phi_nodes (&exit_conditions);
2900 number_of_iterations_for_all_loops (&exit_conditions);
2901 VEC_free (gimple, heap, exit_conditions);
2904 /* Finalize the scalar evolution analysis. */
2906 void
2907 scev_finalize (void)
2909 if (!scalar_evolution_info)
2910 return;
2911 htab_delete (scalar_evolution_info);
2912 scalar_evolution_info = NULL;
2915 /* Returns true if the expression EXPR is considered to be too expensive
2916 for scev_const_prop. */
2918 bool
2919 expression_expensive_p (tree expr)
2921 enum tree_code code;
2923 if (is_gimple_val (expr))
2924 return false;
2926 code = TREE_CODE (expr);
2927 if (code == TRUNC_DIV_EXPR
2928 || code == CEIL_DIV_EXPR
2929 || code == FLOOR_DIV_EXPR
2930 || code == ROUND_DIV_EXPR
2931 || code == TRUNC_MOD_EXPR
2932 || code == CEIL_MOD_EXPR
2933 || code == FLOOR_MOD_EXPR
2934 || code == ROUND_MOD_EXPR
2935 || code == EXACT_DIV_EXPR)
2937 /* Division by power of two is usually cheap, so we allow it.
2938 Forbid anything else. */
2939 if (!integer_pow2p (TREE_OPERAND (expr, 1)))
2940 return true;
2943 switch (TREE_CODE_CLASS (code))
2945 case tcc_binary:
2946 case tcc_comparison:
2947 if (expression_expensive_p (TREE_OPERAND (expr, 1)))
2948 return true;
2950 /* Fallthru. */
2951 case tcc_unary:
2952 return expression_expensive_p (TREE_OPERAND (expr, 0));
2954 default:
2955 return true;
2959 /* Replace ssa names for that scev can prove they are constant by the
2960 appropriate constants. Also perform final value replacement in loops,
2961 in case the replacement expressions are cheap.
2963 We only consider SSA names defined by phi nodes; rest is left to the
2964 ordinary constant propagation pass. */
2966 unsigned int
2967 scev_const_prop (void)
2969 basic_block bb;
2970 tree name, type, ev;
2971 gimple phi, ass;
2972 struct loop *loop, *ex_loop;
2973 bitmap ssa_names_to_remove = NULL;
2974 unsigned i;
2975 loop_iterator li;
2976 gimple_stmt_iterator psi;
2978 if (number_of_loops () <= 1)
2979 return 0;
2981 FOR_EACH_BB (bb)
2983 loop = bb->loop_father;
2985 for (psi = gsi_start_phis (bb); !gsi_end_p (psi); gsi_next (&psi))
2987 phi = gsi_stmt (psi);
2988 name = PHI_RESULT (phi);
2990 if (!is_gimple_reg (name))
2991 continue;
2993 type = TREE_TYPE (name);
2995 if (!POINTER_TYPE_P (type)
2996 && !INTEGRAL_TYPE_P (type))
2997 continue;
2999 ev = resolve_mixers (loop, analyze_scalar_evolution (loop, name));
3000 if (!is_gimple_min_invariant (ev)
3001 || !may_propagate_copy (name, ev))
3002 continue;
3004 /* Replace the uses of the name. */
3005 if (name != ev)
3006 replace_uses_by (name, ev);
3008 if (!ssa_names_to_remove)
3009 ssa_names_to_remove = BITMAP_ALLOC (NULL);
3010 bitmap_set_bit (ssa_names_to_remove, SSA_NAME_VERSION (name));
3014 /* Remove the ssa names that were replaced by constants. We do not
3015 remove them directly in the previous cycle, since this
3016 invalidates scev cache. */
3017 if (ssa_names_to_remove)
3019 bitmap_iterator bi;
3021 EXECUTE_IF_SET_IN_BITMAP (ssa_names_to_remove, 0, i, bi)
3023 gimple_stmt_iterator psi;
3024 name = ssa_name (i);
3025 phi = SSA_NAME_DEF_STMT (name);
3027 gcc_assert (gimple_code (phi) == GIMPLE_PHI);
3028 psi = gsi_for_stmt (phi);
3029 remove_phi_node (&psi, true);
3032 BITMAP_FREE (ssa_names_to_remove);
3033 scev_reset ();
3036 /* Now the regular final value replacement. */
3037 FOR_EACH_LOOP (li, loop, LI_FROM_INNERMOST)
3039 edge exit;
3040 tree def, rslt, niter;
3041 gimple_stmt_iterator bsi;
3043 /* If we do not know exact number of iterations of the loop, we cannot
3044 replace the final value. */
3045 exit = single_exit (loop);
3046 if (!exit)
3047 continue;
3049 niter = number_of_latch_executions (loop);
3050 if (niter == chrec_dont_know)
3051 continue;
3053 /* Ensure that it is possible to insert new statements somewhere. */
3054 if (!single_pred_p (exit->dest))
3055 split_loop_exit_edge (exit);
3056 bsi = gsi_after_labels (exit->dest);
3058 ex_loop = superloop_at_depth (loop,
3059 loop_depth (exit->dest->loop_father) + 1);
3061 for (psi = gsi_start_phis (exit->dest); !gsi_end_p (psi); )
3063 phi = gsi_stmt (psi);
3064 rslt = PHI_RESULT (phi);
3065 def = PHI_ARG_DEF_FROM_EDGE (phi, exit);
3066 if (!is_gimple_reg (def))
3068 gsi_next (&psi);
3069 continue;
3072 if (!POINTER_TYPE_P (TREE_TYPE (def))
3073 && !INTEGRAL_TYPE_P (TREE_TYPE (def)))
3075 gsi_next (&psi);
3076 continue;
3079 def = analyze_scalar_evolution_in_loop (ex_loop, loop, def, NULL);
3080 def = compute_overall_effect_of_inner_loop (ex_loop, def);
3081 if (!tree_does_not_contain_chrecs (def)
3082 || chrec_contains_symbols_defined_in_loop (def, ex_loop->num)
3083 /* Moving the computation from the loop may prolong life range
3084 of some ssa names, which may cause problems if they appear
3085 on abnormal edges. */
3086 || contains_abnormal_ssa_name_p (def)
3087 /* Do not emit expensive expressions. The rationale is that
3088 when someone writes a code like
3090 while (n > 45) n -= 45;
3092 he probably knows that n is not large, and does not want it
3093 to be turned into n %= 45. */
3094 || expression_expensive_p (def))
3096 gsi_next (&psi);
3097 continue;
3100 /* Eliminate the PHI node and replace it by a computation outside
3101 the loop. */
3102 def = unshare_expr (def);
3103 remove_phi_node (&psi, false);
3105 def = force_gimple_operand_gsi (&bsi, def, false, NULL_TREE,
3106 true, GSI_SAME_STMT);
3107 ass = gimple_build_assign (rslt, def);
3108 gsi_insert_before (&bsi, ass, GSI_SAME_STMT);
3111 return 0;
3114 #include "gt-tree-scalar-evolution.h"