/* Inlining decision heuristics.
- Copyright (C) 2003, 2004 Free Software Foundation, Inc.
+ Copyright (C) 2003, 2004, 2007 Free Software Foundation, Inc.
Contributed by Jan Hubicka
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
-Software Foundation; either version 2, or (at your option) any later
+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
for more details.
You should have received a copy of the GNU General Public License
-along with GCC; see the file COPYING. If not, write to the Free
-Software Foundation, 59 Temple Place - Suite 330, Boston, MA
-02111-1307, USA. */
+along with GCC; see the file COPYING3. If not see
+<http://www.gnu.org/licenses/>. */
/* Inlining decision heuristics
cgraph_decide_inlining implements heuristics taking whole callgraph
into account, while cgraph_decide_inlining_incrementally considers
- only one function at a time and is used in non-unit-at-a-time mode. */
+ only one function at a time and is used in non-unit-at-a-time mode.
+
+ The inliner itself is split into several passes:
+
+ pass_inline_parameters
+
+ This pass computes local properties of functions that are used by inliner:
+ estimated function body size, whether function is inlinable at all and
+ stack frame consumption.
+
+ Before executing any of inliner passes, this local pass has to be applied
+ to each function in the callgraph (ie run as subpass of some earlier
+ IPA pass). The results are made out of date by any optimization applied
+ on the function body.
+
+ pass_early_inlining
+
+ Simple local inlining pass inlining callees into current function. This
+ pass makes no global whole compilation unit analysis and this when allowed
+ to do inlining expanding code size it might result in unbounded growth of
+ whole unit.
+
+ This is the main inlining pass in non-unit-at-a-time.
+
+ With unit-at-a-time the pass is run during conversion into SSA form.
+ Only functions already converted into SSA form are inlined, so the
+ conversion must happen in topological order on the callgraph (that is
+ maintained by pass manager). The functions after inlining are early
+ optimized so the early inliner sees unoptimized function itself, but
+ all considered callees are already optimized allowing it to unfold
+ abstraction penalty on C++ effectively and cheaply.
+
+ pass_ipa_early_inlining
+
+ With profiling, the early inlining is also necessary to reduce
+ instrumentation costs on program with high abstraction penalty (doing
+ many redundant calls). This can't happen in parallel with early
+ optimization and profile instrumentation, because we would end up
+ re-instrumenting already instrumented function bodies we brought in via
+ inlining.
+
+ To avoid this, this pass is executed as IPA pass before profiling. It is
+ simple wrapper to pass_early_inlining and ensures first inlining.
+
+ pass_ipa_inline
+
+ This is the main pass implementing simple greedy algorithm to do inlining
+ of small functions that results in overall growth of compilation unit and
+ inlining of functions called once. The pass compute just so called inline
+ plan (representation of inlining to be done in callgraph) and unlike early
+ inlining it is not performing the inlining itself.
+
+ pass_apply_inline
+
+ This pass performs actual inlining according to pass_ipa_inline on given
+ function. Possible the function body before inlining is saved when it is
+ needed for further inlining later.
+ */
#include "config.h"
#include "system.h"
#include "fibheap.h"
#include "intl.h"
#include "tree-pass.h"
+#include "hashtab.h"
+#include "coverage.h"
+#include "ggc.h"
+#include "tree-flow.h"
+#include "rtl.h"
+
+/* Mode incremental inliner operate on:
+
+ In ALWAYS_INLINE only functions marked
+ always_inline are inlined. This mode is used after detecting cycle during
+ flattening.
+
+ In SIZE mode, only functions that reduce function body size after inlining
+ are inlined, this is used during early inlining.
+
+ In SPEED mode, all small functions are inlined. This might result in
+ unbounded growth of compilation unit and is used only in non-unit-at-a-time
+ mode.
+
+ in ALL mode, everything is inlined. This is used during flattening. */
+enum inlining_mode {
+ INLINE_NONE = 0,
+ INLINE_ALWAYS_INLINE,
+ INLINE_SIZE,
+ INLINE_SPEED,
+ INLINE_ALL
+};
+static bool
+cgraph_decide_inlining_incrementally (struct cgraph_node *, enum inlining_mode,
+ int);
+
/* Statistics we collect about inlining algorithm. */
static int ncalls_inlined;
static int nfunctions_inlined;
-static int initial_insns;
static int overall_insns;
+static gcov_type max_count;
/* Estimate size of the function after inlining WHAT into TO. */
cgraph_estimate_size_after_inlining (int times, struct cgraph_node *to,
struct cgraph_node *what)
{
- tree fndecl = what->decl;
- tree arg;
+ int size;
+ tree fndecl = what->decl, arg;
int call_insns = PARAM_VALUE (PARAM_INLINE_CALL_COST);
+
for (arg = DECL_ARGUMENTS (fndecl); arg; arg = TREE_CHAIN (arg))
call_insns += estimate_move_cost (TREE_TYPE (arg));
- return (what->global.insns - call_insns) * times + to->global.insns;
+ size = (what->global.insns - call_insns) * times + to->global.insns;
+ gcc_assert (size >= 0);
+ return size;
}
/* E is expected to be an edge being inlined. Clone destination node of
clones or re-using node originally representing out-of-line function call.
*/
void
-cgraph_clone_inlined_nodes (struct cgraph_edge *e, bool duplicate)
+cgraph_clone_inlined_nodes (struct cgraph_edge *e, bool duplicate, bool update_original)
{
- struct cgraph_node *n;
-
- /* We may eliminate the need for out-of-line copy to be output. In that
- case just go ahead and re-use it. */
- if (!e->callee->callers->next_caller
- && (!e->callee->needed || DECL_EXTERNAL (e->callee->decl))
- && duplicate
- && flag_unit_at_a_time)
+ HOST_WIDE_INT peak;
+ if (duplicate)
{
- gcc_assert (!e->callee->global.inlined_to);
- if (!DECL_EXTERNAL (e->callee->decl))
- overall_insns -= e->callee->global.insns, nfunctions_inlined++;
- duplicate = 0;
- }
- else if (duplicate)
- {
- n = cgraph_clone_node (e->callee, e->count, e->loop_nest);
- cgraph_redirect_edge_callee (e, n);
+ /* We may eliminate the need for out-of-line copy to be output.
+ In that case just go ahead and re-use it. */
+ if (!e->callee->callers->next_caller
+ && !e->callee->needed
+ && !cgraph_new_nodes
+ && flag_unit_at_a_time)
+ {
+ gcc_assert (!e->callee->global.inlined_to);
+ if (DECL_SAVED_TREE (e->callee->decl))
+ overall_insns -= e->callee->global.insns, nfunctions_inlined++;
+ duplicate = false;
+ }
+ else
+ {
+ struct cgraph_node *n;
+ n = cgraph_clone_node (e->callee, e->count, e->frequency, e->loop_nest,
+ update_original);
+ cgraph_redirect_edge_callee (e, n);
+ }
}
if (e->caller->global.inlined_to)
e->callee->global.inlined_to = e->caller->global.inlined_to;
else
e->callee->global.inlined_to = e->caller;
+ e->callee->global.stack_frame_offset
+ = e->caller->global.stack_frame_offset + e->caller->local.estimated_self_stack_size;
+ peak = e->callee->global.stack_frame_offset + e->callee->local.estimated_self_stack_size;
+ if (e->callee->global.inlined_to->global.estimated_stack_size < peak)
+ e->callee->global.inlined_to->global.estimated_stack_size = peak;
/* Recursively clone all bodies. */
for (e = e->callee->callees; e; e = e->next_callee)
if (!e->inline_failed)
- cgraph_clone_inlined_nodes (e, duplicate);
+ cgraph_clone_inlined_nodes (e, duplicate, update_original);
}
-/* Mark edge E as inlined and update callgraph accordingly. */
+/* Mark edge E as inlined and update callgraph accordingly.
+ UPDATE_ORIGINAL specify whether profile of original function should be
+ updated. */
void
-cgraph_mark_inline_edge (struct cgraph_edge *e)
+cgraph_mark_inline_edge (struct cgraph_edge *e, bool update_original)
{
int old_insns = 0, new_insns = 0;
struct cgraph_node *to = NULL, *what;
+ if (e->callee->inline_decl)
+ cgraph_redirect_edge_callee (e, cgraph_node (e->callee->inline_decl));
+
gcc_assert (e->inline_failed);
e->inline_failed = NULL;
DECL_POSSIBLY_INLINED (e->callee->decl) = true;
e->callee->global.inlined = true;
- cgraph_clone_inlined_nodes (e, true);
+ cgraph_clone_inlined_nodes (e, true, update_original);
what = e->callee;
struct cgraph_node *to = edge->caller;
struct cgraph_node *what = edge->callee;
struct cgraph_edge *e, *next;
- int times = 0;
+ gcc_assert (!CALL_CANNOT_INLINE_P (edge->call_stmt));
/* Look for all calls, mark them inline and clone recursively
all inlined functions. */
for (e = what->callers; e; e = next)
next = e->next_caller;
if (e->caller == to && e->inline_failed)
{
- cgraph_mark_inline_edge (e);
+ cgraph_mark_inline_edge (e, true);
if (e == edge)
edge = next;
- times++;
}
}
- gcc_assert (times);
+
return edge;
}
{
int growth = 0;
struct cgraph_edge *e;
+ if (node->global.estimated_growth != INT_MIN)
+ return node->global.estimated_growth;
for (e = node->callers; e; e = e->next_caller)
if (e->inline_failed)
if (!node->needed && !DECL_EXTERNAL (node->decl))
growth -= node->global.insns;
+ node->global.estimated_growth = growth;
return growth;
}
/* Return false when inlining WHAT into TO is not good idea
- as it would cause too large growth of function bodies. */
+ as it would cause too large growth of function bodies.
+ When ONE_ONLY is true, assume that only one call site is going
+ to be inlined, otherwise figure out how many call sites in
+ TO calls WHAT and verify that all can be inlined.
+ */
static bool
cgraph_check_inline_limits (struct cgraph_node *to, struct cgraph_node *what,
- const char **reason)
+ const char **reason, bool one_only)
{
int times = 0;
struct cgraph_edge *e;
int newsize;
int limit;
+ HOST_WIDE_INT stack_size_limit, inlined_stack;
+
+ if (one_only)
+ times = 1;
+ else
+ for (e = to->callees; e; e = e->next_callee)
+ if (e->callee == what)
+ times++;
if (to->global.inlined_to)
to = to->global.inlined_to;
- for (e = to->callees; e; e = e->next_callee)
- if (e->callee == what)
- times++;
-
/* When inlining large function body called once into small function,
take the inlined function as base for limiting the growth. */
if (to->local.self_insns > what->local.self_insns)
limit += limit * PARAM_VALUE (PARAM_LARGE_FUNCTION_GROWTH) / 100;
+ /* Check the size after inlining against the function limits. But allow
+ the function to shrink if it went over the limits by forced inlining. */
newsize = cgraph_estimate_size_after_inlining (times, to, what);
- if (newsize > PARAM_VALUE (PARAM_LARGE_FUNCTION_INSNS)
+ if (newsize >= to->global.insns
+ && newsize > PARAM_VALUE (PARAM_LARGE_FUNCTION_INSNS)
&& newsize > limit)
{
if (reason)
*reason = N_("--param large-function-growth limit reached");
return false;
}
+
+ stack_size_limit = to->local.estimated_self_stack_size;
+
+ stack_size_limit += stack_size_limit * PARAM_VALUE (PARAM_STACK_FRAME_GROWTH) / 100;
+
+ inlined_stack = (to->global.stack_frame_offset
+ + to->local.estimated_self_stack_size
+ + what->global.estimated_stack_size);
+ if (inlined_stack > stack_size_limit
+ && inlined_stack > PARAM_VALUE (PARAM_LARGE_STACK_FRAME))
+ {
+ if (reason)
+ *reason = N_("--param large-stack-frame-growth limit reached");
+ return false;
+ }
return true;
}
/* Return true when function N is small enough to be inlined. */
bool
-cgraph_default_inline_p (struct cgraph_node *n)
+cgraph_default_inline_p (struct cgraph_node *n, const char **reason)
{
- if (!DECL_INLINE (n->decl) || !DECL_SAVED_TREE (n->decl))
- return false;
- if (DECL_DECLARED_INLINE_P (n->decl))
- return n->global.insns < MAX_INLINE_INSNS_SINGLE;
+ tree decl = n->decl;
+
+ if (n->inline_decl)
+ decl = n->inline_decl;
+ if (!flag_inline_small_functions && !DECL_DECLARED_INLINE_P (decl))
+ {
+ if (reason)
+ *reason = N_("function not inline candidate");
+ return false;
+ }
+
+ if (!DECL_STRUCT_FUNCTION (decl)->cfg)
+ {
+ if (reason)
+ *reason = N_("function body not available");
+ return false;
+ }
+
+ if (DECL_DECLARED_INLINE_P (decl))
+ {
+ if (n->global.insns >= MAX_INLINE_INSNS_SINGLE)
+ {
+ if (reason)
+ *reason = N_("--param max-inline-insns-single limit reached");
+ return false;
+ }
+ }
else
- return n->global.insns < MAX_INLINE_INSNS_AUTO;
+ {
+ if (n->global.insns >= MAX_INLINE_INSNS_AUTO)
+ {
+ if (reason)
+ *reason = N_("--param max-inline-insns-auto limit reached");
+ return false;
+ }
+ }
+
+ return true;
}
/* Return true when inlining WHAT would create recursive inlining.
return recursive;
}
-/* Recompute heap nodes for each of callees. */
+/* Return true if the call can be hot. */
+static bool
+cgraph_maybe_hot_edge_p (struct cgraph_edge *edge)
+{
+ if (profile_info && flag_branch_probabilities
+ && (edge->count
+ <= profile_info->sum_max / PARAM_VALUE (HOT_BB_COUNT_FRACTION)))
+ return false;
+ if (lookup_attribute ("cold", DECL_ATTRIBUTES (edge->callee->decl))
+ || lookup_attribute ("cold", DECL_ATTRIBUTES (edge->caller->decl)))
+ return false;
+ if (lookup_attribute ("hot", DECL_ATTRIBUTES (edge->caller->decl)))
+ return true;
+ if (flag_guess_branch_prob
+ && edge->frequency < (CGRAPH_FREQ_MAX
+ / PARAM_VALUE (HOT_BB_FREQUENCY_FRACTION)))
+ return false;
+ return true;
+}
+
+/* A cost model driving the inlining heuristics in a way so the edges with
+ smallest badness are inlined first. After each inlining is performed
+ the costs of all caller edges of nodes affected are recomputed so the
+ metrics may accurately depend on values such as number of inlinable callers
+ of the function or function body size. */
+
+static int
+cgraph_edge_badness (struct cgraph_edge *edge)
+{
+ int badness;
+ int growth =
+ cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
+
+ growth -= edge->caller->global.insns;
+
+ /* Always prefer inlining saving code size. */
+ if (growth <= 0)
+ badness = INT_MIN - growth;
+
+ /* When profiling is available, base priorities -(#calls / growth).
+ So we optimize for overall number of "executed" inlined calls. */
+ else if (max_count)
+ badness = ((int)((double)edge->count * INT_MIN / max_count)) / growth;
+
+ /* When function local profile is available, base priorities on
+ growth / frequency, so we optimize for overall frequency of inlined
+ calls. This is not too accurate since while the call might be frequent
+ within function, the function itself is infrequent.
+
+ Other objective to optimize for is number of different calls inlined.
+ We add the estimated growth after inlining all functions to biass the
+ priorities slightly in this direction (so fewer times called functions
+ of the same size gets priority). */
+ else if (flag_guess_branch_prob)
+ {
+ int div = edge->frequency * 100 / CGRAPH_FREQ_BASE;
+ int growth =
+ cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
+ growth -= edge->caller->global.insns;
+ badness = growth * 256;
+
+ /* Decrease badness if call is nested. */
+ /* Compress the range so we don't overflow. */
+ if (div > 256)
+ div = 256 + ceil_log2 (div) - 8;
+ if (div < 1)
+ div = 1;
+ if (badness > 0)
+ badness /= div;
+ badness += cgraph_estimate_growth (edge->callee);
+ }
+ /* When function local profile is not available or it does not give
+ useful information (ie frequency is zero), base the cost on
+ loop nest and overall size growth, so we optimize for overall number
+ of functions fully inlined in program. */
+ else
+ {
+ int nest = MIN (edge->loop_nest, 8);
+ badness = cgraph_estimate_growth (edge->callee) * 256;
+
+ /* Decrease badness if call is nested. */
+ if (badness > 0)
+ badness >>= nest;
+ else
+ {
+ badness <<= nest;
+ }
+ }
+ /* Make recursive inlining happen always after other inlining is done. */
+ if (cgraph_recursive_inlining_p (edge->caller, edge->callee, NULL))
+ return badness + 1;
+ else
+ return badness;
+}
+
+/* Recompute heap nodes for each of caller edge. */
+
+static void
+update_caller_keys (fibheap_t heap, struct cgraph_node *node,
+ bitmap updated_nodes)
+{
+ struct cgraph_edge *edge;
+ const char *failed_reason;
+
+ if (!node->local.inlinable || node->local.disregard_inline_limits
+ || node->global.inlined_to)
+ return;
+ if (bitmap_bit_p (updated_nodes, node->uid))
+ return;
+ bitmap_set_bit (updated_nodes, node->uid);
+ node->global.estimated_growth = INT_MIN;
+
+ if (!node->local.inlinable)
+ return;
+ /* Prune out edges we won't inline into anymore. */
+ if (!cgraph_default_inline_p (node, &failed_reason))
+ {
+ for (edge = node->callers; edge; edge = edge->next_caller)
+ if (edge->aux)
+ {
+ fibheap_delete_node (heap, (fibnode_t) edge->aux);
+ edge->aux = NULL;
+ if (edge->inline_failed)
+ edge->inline_failed = failed_reason;
+ }
+ return;
+ }
+
+ for (edge = node->callers; edge; edge = edge->next_caller)
+ if (edge->inline_failed)
+ {
+ int badness = cgraph_edge_badness (edge);
+ if (edge->aux)
+ {
+ fibnode_t n = (fibnode_t) edge->aux;
+ gcc_assert (n->data == edge);
+ if (n->key == badness)
+ continue;
+
+ /* fibheap_replace_key only increase the keys. */
+ if (fibheap_replace_key (heap, n, badness))
+ continue;
+ fibheap_delete_node (heap, (fibnode_t) edge->aux);
+ }
+ edge->aux = fibheap_insert (heap, badness, edge);
+ }
+}
+
+/* Recompute heap nodes for each of caller edges of each of callees. */
+
static void
-update_callee_keys (fibheap_t heap, struct fibnode **heap_node,
- struct cgraph_node *node)
+update_callee_keys (fibheap_t heap, struct cgraph_node *node,
+ bitmap updated_nodes)
{
struct cgraph_edge *e;
+ node->global.estimated_growth = INT_MIN;
for (e = node->callees; e; e = e->next_callee)
- if (e->inline_failed && heap_node[e->callee->uid])
- fibheap_replace_key (heap, heap_node[e->callee->uid],
- cgraph_estimate_growth (e->callee));
+ if (e->inline_failed)
+ update_caller_keys (heap, e->callee, updated_nodes);
else if (!e->inline_failed)
- update_callee_keys (heap, heap_node, e->callee);
+ update_callee_keys (heap, e->callee, updated_nodes);
}
-/* Enqueue all recursive calls from NODE into queue linked via aux pointers
- in between FIRST and LAST. WHERE is used for bookkeeping while looking
- int calls inlined within NODE. */
+/* Enqueue all recursive calls from NODE into priority queue depending on
+ how likely we want to recursively inline the call. */
+
static void
lookup_recursive_calls (struct cgraph_node *node, struct cgraph_node *where,
- struct cgraph_edge **first, struct cgraph_edge **last)
+ fibheap_t heap)
{
+ static int priority;
struct cgraph_edge *e;
for (e = where->callees; e; e = e->next_callee)
if (e->callee == node)
{
- if (!*first)
- *first = e;
- else
- (*last)->aux = e;
- *last = e;
+ /* When profile feedback is available, prioritize by expected number
+ of calls. Without profile feedback we maintain simple queue
+ to order candidates via recursive depths. */
+ fibheap_insert (heap,
+ !max_count ? priority++
+ : -(e->count / ((max_count + (1<<24) - 1) / (1<<24))),
+ e);
}
for (e = where->callees; e; e = e->next_callee)
if (!e->inline_failed)
- lookup_recursive_calls (node, e->callee, first, last);
+ lookup_recursive_calls (node, e->callee, heap);
}
/* Decide on recursive inlining: in the case function has recursive calls,
inline until body size reaches given argument. */
-static void
+
+static bool
cgraph_decide_recursive_inlining (struct cgraph_node *node)
{
int limit = PARAM_VALUE (PARAM_MAX_INLINE_INSNS_RECURSIVE_AUTO);
int max_depth = PARAM_VALUE (PARAM_MAX_INLINE_RECURSIVE_DEPTH_AUTO);
- struct cgraph_edge *first_call = NULL, *last_call = NULL;
- struct cgraph_edge *last_in_current_depth;
+ int probability = PARAM_VALUE (PARAM_MIN_INLINE_RECURSIVE_PROBABILITY);
+ fibheap_t heap;
struct cgraph_edge *e;
- struct cgraph_node *master_clone;
+ struct cgraph_node *master_clone, *next;
int depth = 0;
int n = 0;
+ if (optimize_size
+ || (!flag_inline_functions && !DECL_DECLARED_INLINE_P (node->decl)))
+ return false;
+
if (DECL_DECLARED_INLINE_P (node->decl))
{
limit = PARAM_VALUE (PARAM_MAX_INLINE_INSNS_RECURSIVE);
/* Make sure that function is small enough to be considered for inlining. */
if (!max_depth
|| cgraph_estimate_size_after_inlining (1, node, node) >= limit)
- return;
- lookup_recursive_calls (node, node, &first_call, &last_call);
- if (!first_call)
- return;
+ return false;
+ heap = fibheap_new ();
+ lookup_recursive_calls (node, node, heap);
+ if (fibheap_empty (heap))
+ {
+ fibheap_delete (heap);
+ return false;
+ }
if (dump_file)
fprintf (dump_file,
- "\nPerforming recursive inlining on %s\n",
+ " Performing recursive inlining on %s\n",
cgraph_node_name (node));
/* We need original clone to copy around. */
- master_clone = cgraph_clone_node (node, 0, 1);
+ master_clone = cgraph_clone_node (node, node->count, CGRAPH_FREQ_BASE, 1, false);
master_clone->needed = true;
for (e = master_clone->callees; e; e = e->next_callee)
if (!e->inline_failed)
- cgraph_clone_inlined_nodes (e, true);
+ cgraph_clone_inlined_nodes (e, true, false);
/* Do the inlining and update list of recursive call during process. */
- last_in_current_depth = last_call;
- while (first_call
- && cgraph_estimate_size_after_inlining (1, node, master_clone) <= limit)
+ while (!fibheap_empty (heap)
+ && (cgraph_estimate_size_after_inlining (1, node, master_clone)
+ <= limit))
{
- struct cgraph_edge *curr = first_call;
+ struct cgraph_edge *curr
+ = (struct cgraph_edge *) fibheap_extract_min (heap);
+ struct cgraph_node *cnode;
+
+ depth = 1;
+ for (cnode = curr->caller;
+ cnode->global.inlined_to; cnode = cnode->callers->caller)
+ if (node->decl == curr->callee->decl)
+ depth++;
+ if (depth > max_depth)
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ " maximal depth reached\n");
+ continue;
+ }
- first_call = first_call->aux;
- curr->aux = NULL;
+ if (max_count)
+ {
+ if (!cgraph_maybe_hot_edge_p (curr))
+ {
+ if (dump_file)
+ fprintf (dump_file, " Not inlining cold call\n");
+ continue;
+ }
+ if (curr->count * 100 / node->count < probability)
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ " Probability of edge is too small\n");
+ continue;
+ }
+ }
+ if (dump_file)
+ {
+ fprintf (dump_file,
+ " Inlining call of depth %i", depth);
+ if (node->count)
+ {
+ fprintf (dump_file, " called approx. %.2f times per call",
+ (double)curr->count / node->count);
+ }
+ fprintf (dump_file, "\n");
+ }
cgraph_redirect_edge_callee (curr, master_clone);
- cgraph_mark_inline_edge (curr);
- lookup_recursive_calls (node, curr->callee, &first_call, &last_call);
-
- if (last_in_current_depth
- && ++depth >= max_depth)
- break;
+ cgraph_mark_inline_edge (curr, false);
+ lookup_recursive_calls (node, curr->callee, heap);
n++;
}
+ if (!fibheap_empty (heap) && dump_file)
+ fprintf (dump_file, " Recursive inlining growth limit met.\n");
- /* Cleanup queue pointers. */
- while (first_call)
- {
- struct cgraph_edge *next = first_call->aux;
- first_call->aux = NULL;
- first_call = next;
- }
+ fibheap_delete (heap);
if (dump_file)
fprintf (dump_file,
"\n Inlined %i times, body grown from %i to %i insns\n", n,
into master clone gets queued just before master clone so we don't
need recursion. */
for (node = cgraph_nodes; node != master_clone;
- node = node->next)
- if (node->global.inlined_to == master_clone)
- cgraph_remove_node (node);
+ node = next)
+ {
+ next = node->next;
+ if (node->global.inlined_to == master_clone)
+ cgraph_remove_node (node);
+ }
cgraph_remove_node (master_clone);
+ /* FIXME: Recursive inlining actually reduces number of calls of the
+ function. At this place we should probably walk the function and
+ inline clones and compensate the counts accordingly. This probably
+ doesn't matter much in practice. */
+ return n > 0;
}
/* Set inline_failed for all callers of given function to REASON. */
e->inline_failed = reason;
}
+/* Given whole compilation unit estimate of INSNS, compute how large we can
+ allow the unit to grow. */
+static int
+compute_max_insns (int insns)
+{
+ int max_insns = insns;
+ if (max_insns < PARAM_VALUE (PARAM_LARGE_UNIT_INSNS))
+ max_insns = PARAM_VALUE (PARAM_LARGE_UNIT_INSNS);
+
+ return ((HOST_WIDEST_INT) max_insns
+ * (100 + PARAM_VALUE (PARAM_INLINE_UNIT_GROWTH)) / 100);
+}
+
/* We use greedy algorithm for inlining of small functions:
All inline candidates are put into prioritized heap based on estimated
growth of the overall number of instructions and then update the estimates.
cgraph_decide_inlining_of_small_functions (void)
{
struct cgraph_node *node;
+ struct cgraph_edge *edge;
+ const char *failed_reason;
fibheap_t heap = fibheap_new ();
- struct fibnode **heap_node =
- xcalloc (cgraph_max_uid, sizeof (struct fibnode *));
- int max_insns = ((HOST_WIDEST_INT) initial_insns
- * (100 + PARAM_VALUE (PARAM_INLINE_UNIT_GROWTH)) / 100);
+ bitmap updated_nodes = BITMAP_ALLOC (NULL);
+ int min_insns, max_insns;
+
+ if (dump_file)
+ fprintf (dump_file, "\nDeciding on smaller functions:\n");
/* Put all inline candidates into the heap. */
if (!node->local.inlinable || !node->callers
|| node->local.disregard_inline_limits)
continue;
+ if (dump_file)
+ fprintf (dump_file, "Considering inline candidate %s.\n", cgraph_node_name (node));
- if (!cgraph_default_inline_p (node))
+ node->global.estimated_growth = INT_MIN;
+ if (!cgraph_default_inline_p (node, &failed_reason))
{
- cgraph_set_inline_failed (node,
- N_("--param max-inline-insns-single limit reached"));
+ cgraph_set_inline_failed (node, failed_reason);
continue;
}
- heap_node[node->uid] =
- fibheap_insert (heap, cgraph_estimate_growth (node), node);
+
+ for (edge = node->callers; edge; edge = edge->next_caller)
+ if (edge->inline_failed)
+ {
+ gcc_assert (!edge->aux);
+ edge->aux = fibheap_insert (heap, cgraph_edge_badness (edge), edge);
+ }
}
- if (dump_file)
- fprintf (dump_file, "\nDeciding on smaller functions:\n");
- while (overall_insns <= max_insns && (node = fibheap_extract_min (heap)))
+ max_insns = compute_max_insns (overall_insns);
+ min_insns = overall_insns;
+
+ while (overall_insns <= max_insns
+ && (edge = (struct cgraph_edge *) fibheap_extract_min (heap)))
{
- struct cgraph_edge *e, *next;
int old_insns = overall_insns;
+ struct cgraph_node *where;
+ int growth =
+ cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
+ const char *not_good = NULL;
+
+ growth -= edge->caller->global.insns;
- heap_node[node->uid] = NULL;
if (dump_file)
- fprintf (dump_file,
- "\nConsidering %s with %i insns\n"
- " Estimated growth is %+i insns.\n",
- cgraph_node_name (node), node->global.insns,
- cgraph_estimate_growth (node));
- if (!cgraph_default_inline_p (node))
{
- cgraph_set_inline_failed (node,
- N_("--param max-inline-insns-single limit reached after inlining into the callee"));
- continue;
+ fprintf (dump_file,
+ "\nConsidering %s with %i insns\n",
+ cgraph_node_name (edge->callee),
+ edge->callee->global.insns);
+ fprintf (dump_file,
+ " to be inlined into %s\n"
+ " Estimated growth after inlined into all callees is %+i insns.\n"
+ " Estimated badness is %i, frequency %.2f.\n",
+ cgraph_node_name (edge->caller),
+ cgraph_estimate_growth (edge->callee),
+ cgraph_edge_badness (edge),
+ edge->frequency / (double)CGRAPH_FREQ_BASE);
+ if (edge->count)
+ fprintf (dump_file," Called "HOST_WIDEST_INT_PRINT_DEC"x\n", edge->count);
}
- for (e = node->callers; e; e = next)
- {
- next = e->next_caller;
- if (e->inline_failed)
- {
- struct cgraph_node *where;
-
- if (cgraph_recursive_inlining_p (e->caller, e->callee,
- &e->inline_failed)
- || !cgraph_check_inline_limits (e->caller, e->callee,
- &e->inline_failed))
- {
- if (dump_file)
- fprintf (dump_file, " Not inlining into %s:%s.\n",
- cgraph_node_name (e->caller), e->inline_failed);
- continue;
- }
- next = cgraph_mark_inline (e);
- where = e->caller;
- if (where->global.inlined_to)
- where = where->global.inlined_to;
+ gcc_assert (edge->aux);
+ edge->aux = NULL;
+ if (!edge->inline_failed)
+ continue;
- if (heap_node[where->uid])
- fibheap_replace_key (heap, heap_node[where->uid],
- cgraph_estimate_growth (where));
+ /* When not having profile info ready we don't weight by any way the
+ position of call in procedure itself. This means if call of
+ function A from function B seems profitable to inline, the recursive
+ call of function A in inline copy of A in B will look profitable too
+ and we end up inlining until reaching maximal function growth. This
+ is not good idea so prohibit the recursive inlining.
+ ??? When the frequencies are taken into account we might not need this
+ restriction. */
+ if (!max_count)
+ {
+ where = edge->caller;
+ while (where->global.inlined_to)
+ {
+ if (where->decl == edge->callee->decl)
+ break;
+ where = where->callers->caller;
+ }
+ if (where->global.inlined_to)
+ {
+ edge->inline_failed
+ = (edge->callee->local.disregard_inline_limits ? N_("recursive inlining") : "");
if (dump_file)
- fprintf (dump_file,
- " Inlined into %s which now has %i insns.\n",
- cgraph_node_name (e->caller),
- e->caller->global.insns);
+ fprintf (dump_file, " inline_failed:Recursive inlining performed only for function itself.\n");
+ continue;
}
}
- cgraph_decide_recursive_inlining (node);
-
- /* Similarly all functions called by the function we just inlined
- are now called more times; update keys. */
- update_callee_keys (heap, heap_node, node);
+ if (!cgraph_maybe_hot_edge_p (edge))
+ not_good = N_("call is unlikely and code size would grow");
+ if (!flag_inline_functions
+ && !DECL_DECLARED_INLINE_P (edge->callee->decl))
+ not_good = N_("function not declared inline and code size would grow");
+ if (optimize_size)
+ not_good = N_("optimizing for size and code size would grow");
+ if (not_good && growth > 0 && cgraph_estimate_growth (edge->callee) > 0)
+ {
+ if (!cgraph_recursive_inlining_p (edge->caller, edge->callee,
+ &edge->inline_failed))
+ {
+ edge->inline_failed = not_good;
+ if (dump_file)
+ fprintf (dump_file, " inline_failed:%s.\n", edge->inline_failed);
+ }
+ continue;
+ }
+ if (!cgraph_default_inline_p (edge->callee, &edge->inline_failed))
+ {
+ if (!cgraph_recursive_inlining_p (edge->caller, edge->callee,
+ &edge->inline_failed))
+ {
+ if (dump_file)
+ fprintf (dump_file, " inline_failed:%s.\n", edge->inline_failed);
+ }
+ continue;
+ }
+ if (cgraph_recursive_inlining_p (edge->caller, edge->callee,
+ &edge->inline_failed))
+ {
+ where = edge->caller;
+ if (where->global.inlined_to)
+ where = where->global.inlined_to;
+ if (!cgraph_decide_recursive_inlining (where))
+ continue;
+ update_callee_keys (heap, where, updated_nodes);
+ }
+ else
+ {
+ struct cgraph_node *callee;
+ if (CALL_CANNOT_INLINE_P (edge->call_stmt)
+ || !cgraph_check_inline_limits (edge->caller, edge->callee,
+ &edge->inline_failed, true))
+ {
+ if (dump_file)
+ fprintf (dump_file, " Not inlining into %s:%s.\n",
+ cgraph_node_name (edge->caller), edge->inline_failed);
+ continue;
+ }
+ callee = edge->callee;
+ cgraph_mark_inline_edge (edge, true);
+ update_callee_keys (heap, callee, updated_nodes);
+ }
+ where = edge->caller;
+ if (where->global.inlined_to)
+ where = where->global.inlined_to;
+
+ /* Our profitability metric can depend on local properties
+ such as number of inlinable calls and size of the function body.
+ After inlining these properties might change for the function we
+ inlined into (since it's body size changed) and for the functions
+ called by function we inlined (since number of it inlinable callers
+ might change). */
+ update_caller_keys (heap, where, updated_nodes);
+ bitmap_clear (updated_nodes);
if (dump_file)
- fprintf (dump_file,
- " Inlined for a net change of %+i insns.\n",
- overall_insns - old_insns);
+ {
+ fprintf (dump_file,
+ " Inlined into %s which now has %i insns,"
+ "net change of %+i insns.\n",
+ cgraph_node_name (edge->caller),
+ edge->caller->global.insns,
+ overall_insns - old_insns);
+ }
+ if (min_insns > overall_insns)
+ {
+ min_insns = overall_insns;
+ max_insns = compute_max_insns (min_insns);
+
+ if (dump_file)
+ fprintf (dump_file, "New minimal insns reached: %i\n", min_insns);
+ }
+ }
+ while ((edge = (struct cgraph_edge *) fibheap_extract_min (heap)) != NULL)
+ {
+ gcc_assert (edge->aux);
+ edge->aux = NULL;
+ if (!edge->callee->local.disregard_inline_limits && edge->inline_failed
+ && !cgraph_recursive_inlining_p (edge->caller, edge->callee,
+ &edge->inline_failed))
+ edge->inline_failed = N_("--param inline-unit-growth limit reached");
}
- while ((node = fibheap_extract_min (heap)) != NULL)
- if (!node->local.disregard_inline_limits)
- cgraph_set_inline_failed (node, N_("--param inline-unit-growth limit reached"));
fibheap_delete (heap);
- free (heap_node);
+ BITMAP_FREE (updated_nodes);
}
/* Decide on the inlining. We do so in the topological order to avoid
expenses on updating data structures. */
-static void
+static unsigned int
cgraph_decide_inlining (void)
{
struct cgraph_node *node;
int nnodes;
struct cgraph_node **order =
- xcalloc (cgraph_n_nodes, sizeof (struct cgraph_node *));
+ XCNEWVEC (struct cgraph_node *, cgraph_n_nodes);
int old_insns = 0;
int i;
+ int initial_insns = 0;
+ max_count = 0;
for (node = cgraph_nodes; node; node = node->next)
- initial_insns += node->local.self_insns;
+ if (node->analyzed && (node->needed || node->reachable))
+ {
+ struct cgraph_edge *e;
+
+ initial_insns += node->local.self_insns;
+ gcc_assert (node->local.self_insns == node->global.insns);
+ for (e = node->callees; e; e = e->next_callee)
+ if (max_count < e->count)
+ max_count = e->count;
+ }
overall_insns = initial_insns;
+ gcc_assert (!max_count || (profile_info && flag_branch_probabilities));
nnodes = cgraph_postorder (order);
node = order[i];
+ /* Handle nodes to be flattened, but don't update overall unit size. */
+ if (lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ "Flattening %s\n", cgraph_node_name (node));
+ cgraph_decide_inlining_incrementally (node, INLINE_ALL, 0);
+ }
+
if (!node->local.disregard_inline_limits)
continue;
if (dump_file)
for (e = node->callers; e; e = next)
{
next = e->next_caller;
- if (!e->inline_failed)
+ if (!e->inline_failed || CALL_CANNOT_INLINE_P (e->call_stmt))
continue;
if (cgraph_recursive_inlining_p (e->caller, e->callee,
&e->inline_failed))
continue;
- cgraph_mark_inline_edge (e);
+ cgraph_mark_inline_edge (e, true);
if (dump_file)
fprintf (dump_file,
" Inlined into %s which now has %i insns.\n",
cgraph_node_name (e->caller),
e->caller->global.insns);
}
+ /* Inlining self recursive function might introduce new calls to
+ themselves we didn't see in the loop above. Fill in the proper
+ reason why inline failed. */
+ for (e = node->callers; e; e = e->next_caller)
+ if (e->inline_failed)
+ e->inline_failed = N_("recursive inlining");
if (dump_file)
fprintf (dump_file,
" Inlined for a net change of %+i insns.\n",
}
if (!flag_really_no_inline)
- {
- cgraph_decide_inlining_of_small_functions ();
+ cgraph_decide_inlining_of_small_functions ();
+ if (!flag_really_no_inline
+ && flag_inline_functions_called_once)
+ {
if (dump_file)
fprintf (dump_file, "\nDeciding on functions called once:\n");
if (node->callers && !node->callers->next_caller && !node->needed
&& node->local.inlinable && node->callers->inline_failed
+ && !CALL_CANNOT_INLINE_P (node->callers->call_stmt)
&& !DECL_EXTERNAL (node->decl) && !DECL_COMDAT (node->decl))
{
- bool ok = true;
- struct cgraph_node *node1;
-
- /* Verify that we won't duplicate the caller. */
- for (node1 = node->callers->caller;
- node1->callers && !node1->callers->inline_failed
- && ok; node1 = node1->callers->caller)
- if (node1->callers->next_caller || node1->needed)
- ok = false;
- if (ok)
+ if (dump_file)
{
+ fprintf (dump_file,
+ "\nConsidering %s %i insns.\n",
+ cgraph_node_name (node), node->global.insns);
+ fprintf (dump_file,
+ " Called once from %s %i insns.\n",
+ cgraph_node_name (node->callers->caller),
+ node->callers->caller->global.insns);
+ }
+
+ old_insns = overall_insns;
+
+ if (cgraph_check_inline_limits (node->callers->caller, node,
+ NULL, false))
+ {
+ cgraph_mark_inline (node->callers);
if (dump_file)
fprintf (dump_file,
- "\nConsidering %s %i insns.\n"
- " Called once from %s %i insns.\n",
- cgraph_node_name (node), node->global.insns,
+ " Inlined into %s which now has %i insns"
+ " for a net change of %+i insns.\n",
cgraph_node_name (node->callers->caller),
- node->callers->caller->global.insns);
-
- old_insns = overall_insns;
-
- if (cgraph_check_inline_limits (node->callers->caller, node,
- NULL))
- {
- cgraph_mark_inline (node->callers);
- if (dump_file)
- fprintf (dump_file,
- " Inlined into %s which now has %i insns"
- " for a net change of %+i insns.\n",
- cgraph_node_name (node->callers->caller),
- node->callers->caller->global.insns,
- overall_insns - old_insns);
- }
- else
- {
- if (dump_file)
- fprintf (dump_file,
- " Inline limit reached, not inlined.\n");
- }
+ node->callers->caller->global.insns,
+ overall_insns - old_insns);
+ }
+ else
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ " Inline limit reached, not inlined.\n");
}
}
}
}
- /* We will never output extern functions we didn't inline.
- ??? Perhaps we can prevent accounting of growth of external
- inline functions. */
- cgraph_remove_unreachable_nodes (false, dump_file);
-
if (dump_file)
fprintf (dump_file,
"\nInlined %i calls, eliminated %i functions, "
ncalls_inlined, nfunctions_inlined, initial_insns,
overall_insns);
free (order);
+ return 0;
+}
+
+/* Try to inline edge E from incremental inliner. MODE specifies mode
+ of inliner.
+
+ We are detecting cycles by storing mode of inliner into cgraph_node last
+ time we visited it in the recursion. In general when mode is set, we have
+ recursive inlining, but as an special case, we want to try harder inline
+ ALWAYS_INLINE functions: consider callgraph a->b->c->b, with a being
+ flatten, b being always inline. Flattening 'a' will collapse
+ a->b->c before hitting cycle. To accommodate always inline, we however
+ need to inline a->b->c->b.
+
+ So after hitting cycle first time, we switch into ALWAYS_INLINE mode and
+ stop inlining only after hitting ALWAYS_INLINE in ALWAY_INLINE mode. */
+static bool
+try_inline (struct cgraph_edge *e, enum inlining_mode mode, int depth)
+{
+ struct cgraph_node *callee = e->callee;
+ enum inlining_mode callee_mode = (enum inlining_mode) (size_t) callee->aux;
+ bool always_inline = e->callee->local.disregard_inline_limits;
+
+ /* We've hit cycle? */
+ if (callee_mode)
+ {
+ /* It is first time we see it and we are not in ALWAY_INLINE only
+ mode yet. and the function in question is always_inline. */
+ if (always_inline && mode != INLINE_ALWAYS_INLINE)
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Hit cycle in %s, switching to always inline only.\n",
+ cgraph_node_name (callee));
+ }
+ mode = INLINE_ALWAYS_INLINE;
+ }
+ /* Otherwise it is time to give up. */
+ else
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Not inlining %s into %s to avoid cycle.\n",
+ cgraph_node_name (callee),
+ cgraph_node_name (e->caller));
+ }
+ e->inline_failed = (e->callee->local.disregard_inline_limits
+ ? N_("recursive inlining") : "");
+ return false;
+ }
+ }
+
+ callee->aux = (void *)(size_t) mode;
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, " Inlining %s into %s.\n",
+ cgraph_node_name (e->callee),
+ cgraph_node_name (e->caller));
+ }
+ if (e->inline_failed)
+ cgraph_mark_inline (e);
+
+ /* In order to fully inline always_inline functions at -O0, we need to
+ recurse here, since the inlined functions might not be processed by
+ incremental inlining at all yet.
+
+ Also flattening needs to be done recursively. */
+
+ if (!flag_unit_at_a_time || mode == INLINE_ALL || always_inline)
+ cgraph_decide_inlining_incrementally (e->callee, mode, depth + 1);
+ callee->aux = (void *)(size_t) callee_mode;
+ return true;
}
/* Decide on the inlining. We do so in the topological order to avoid
- expenses on updating data structures. */
+ expenses on updating data structures.
+ DEPTH is depth of recursion, used only for debug output. */
-void
-cgraph_decide_inlining_incrementally (struct cgraph_node *node)
+static bool
+cgraph_decide_inlining_incrementally (struct cgraph_node *node,
+ enum inlining_mode mode,
+ int depth)
{
struct cgraph_edge *e;
+ bool inlined = false;
+ const char *failed_reason;
+ enum inlining_mode old_mode;
+
+#ifdef ENABLE_CHECKING
+ verify_cgraph_node (node);
+#endif
+
+ old_mode = (enum inlining_mode) (size_t)node->aux;
+
+ if (mode != INLINE_ALWAYS_INLINE
+ && lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Flattening %s\n", cgraph_node_name (node));
+ }
+ mode = INLINE_ALL;
+ }
+
+ node->aux = (void *)(size_t) mode;
/* First of all look for always inline functions. */
for (e = node->callees; e; e = e->next_callee)
- if (e->callee->local.disregard_inline_limits
- && e->inline_failed
- && !cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed)
- /* ??? It is possible that renaming variable removed the function body
- in duplicate_decls. See gcc.c-torture/compile/20011119-2.c */
- && DECL_SAVED_TREE (e->callee->decl))
- cgraph_mark_inline (e);
+ {
+ if (!e->callee->local.disregard_inline_limits
+ && (mode != INLINE_ALL || !e->callee->local.inlinable))
+ continue;
+ if (CALL_CANNOT_INLINE_P (e->call_stmt))
+ continue;
+ /* When the edge is already inlined, we just need to recurse into
+ it in order to fully flatten the leaves. */
+ if (!e->inline_failed && mode == INLINE_ALL)
+ {
+ inlined |= try_inline (e, mode, depth);
+ continue;
+ }
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Considering to always inline inline candidate %s.\n",
+ cgraph_node_name (e->callee));
+ }
+ if (cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: recursive call.\n");
+ }
+ continue;
+ }
+ if (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
+ != gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: SSA form does not match.\n");
+ }
+ continue;
+ }
+ if (!DECL_SAVED_TREE (e->callee->decl) && !e->callee->inline_decl)
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Not inlining: Function body no longer available.\n");
+ }
+ continue;
+ }
+ inlined |= try_inline (e, mode, depth);
+ }
/* Now do the automatic inlining. */
- if (!flag_really_no_inline)
+ if (!flag_really_no_inline && mode != INLINE_ALL
+ && mode != INLINE_ALWAYS_INLINE)
for (e = node->callees; e; e = e->next_callee)
- if (e->callee->local.inlinable
- && e->inline_failed
- && !e->callee->local.disregard_inline_limits
- && !cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed)
- && cgraph_check_inline_limits (node, e->callee, &e->inline_failed)
- && DECL_SAVED_TREE (e->callee->decl))
- {
- if (cgraph_default_inline_p (e->callee))
- cgraph_mark_inline (e);
- else
- e->inline_failed
- = N_("--param max-inline-insns-single limit reached");
- }
+ {
+ if (!e->callee->local.inlinable
+ || !e->inline_failed
+ || e->callee->local.disregard_inline_limits)
+ continue;
+ if (dump_file)
+ fprintf (dump_file, "Considering inline candidate %s.\n",
+ cgraph_node_name (e->callee));
+ if (cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: recursive call.\n");
+ }
+ continue;
+ }
+ if (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
+ != gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: SSA form does not match.\n");
+ }
+ continue;
+ }
+ /* When the function body would grow and inlining the function won't
+ eliminate the need for offline copy of the function, don't inline.
+ */
+ if ((mode == INLINE_SIZE
+ || (!flag_inline_functions
+ && !DECL_DECLARED_INLINE_P (e->callee->decl)))
+ && (cgraph_estimate_size_after_inlining (1, e->caller, e->callee)
+ > e->caller->global.insns)
+ && cgraph_estimate_growth (e->callee) > 0)
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Not inlining: code size would grow by %i insns.\n",
+ cgraph_estimate_size_after_inlining (1, e->caller,
+ e->callee)
+ - e->caller->global.insns);
+ }
+ continue;
+ }
+ if (!cgraph_check_inline_limits (node, e->callee, &e->inline_failed,
+ false)
+ || CALL_CANNOT_INLINE_P (e->call_stmt))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: %s.\n", e->inline_failed);
+ }
+ continue;
+ }
+ if (!DECL_SAVED_TREE (e->callee->decl) && !e->callee->inline_decl)
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Not inlining: Function body no longer available.\n");
+ }
+ continue;
+ }
+ if (cgraph_default_inline_p (e->callee, &failed_reason))
+ inlined |= try_inline (e, mode, depth);
+ else if (!flag_unit_at_a_time)
+ e->inline_failed = failed_reason;
+ }
+ node->aux = (void *)(size_t) old_mode;
+ return inlined;
}
/* When inlining shall be performed. */
return flag_inline_trees;
}
-struct tree_opt_pass pass_ipa_inline =
+struct simple_ipa_opt_pass pass_ipa_inline =
{
+ {
+ SIMPLE_IPA_PASS,
"inline", /* name */
cgraph_gate_inlining, /* gate */
cgraph_decide_inlining, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
- TV_INTEGRATION, /* tv_id */
+ TV_INLINE_HEURISTICS, /* tv_id */
+ 0, /* properties_required */
+ PROP_cfg, /* properties_provided */
+ 0, /* properties_destroyed */
+ TODO_remove_functions, /* todo_flags_finish */
+ TODO_dump_cgraph | TODO_dump_func
+ | TODO_remove_functions /* todo_flags_finish */
+ }
+};
+
+/* Because inlining might remove no-longer reachable nodes, we need to
+ keep the array visible to garbage collector to avoid reading collected
+ out nodes. */
+static int nnodes;
+static GTY ((length ("nnodes"))) struct cgraph_node **order;
+
+/* Do inlining of small functions. Doing so early helps profiling and other
+ passes to be somewhat more effective and avoids some code duplication in
+ later real inlining pass for testcases with very many function calls. */
+static unsigned int
+cgraph_early_inlining (void)
+{
+ struct cgraph_node *node = cgraph_node (current_function_decl);
+ unsigned int todo = 0;
+
+ if (sorrycount || errorcount)
+ return 0;
+ if (cgraph_decide_inlining_incrementally (node,
+ flag_unit_at_a_time || optimize_size
+ ? INLINE_SIZE : INLINE_SPEED, 0))
+ {
+ timevar_push (TV_INTEGRATION);
+ todo = optimize_inline_calls (current_function_decl);
+ timevar_pop (TV_INTEGRATION);
+ }
+ return todo;
+}
+
+/* When inlining shall be performed. */
+static bool
+cgraph_gate_early_inlining (void)
+{
+ return flag_inline_trees && flag_early_inlining;
+}
+
+struct gimple_opt_pass pass_early_inline =
+{
+ {
+ GIMPLE_PASS,
+ "einline", /* name */
+ cgraph_gate_early_inlining, /* gate */
+ cgraph_early_inlining, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
- PROP_trees, /* properties_provided */
+ PROP_cfg, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
- TODO_dump_cgraph | TODO_dump_func, /* todo_flags_finish */
- 0 /* letter */
+ TODO_dump_func /* todo_flags_finish */
+ }
};
+
+/* When inlining shall be performed. */
+static bool
+cgraph_gate_ipa_early_inlining (void)
+{
+ return (flag_inline_trees && flag_early_inlining
+ && (flag_branch_probabilities || flag_test_coverage
+ || profile_arc_flag));
+}
+
+/* IPA pass wrapper for early inlining pass. We need to run early inlining
+ before tree profiling so we have stand alone IPA pass for doing so. */
+struct simple_ipa_opt_pass pass_ipa_early_inline =
+{
+ {
+ SIMPLE_IPA_PASS,
+ "einline_ipa", /* name */
+ cgraph_gate_ipa_early_inlining, /* gate */
+ NULL, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_INLINE_HEURISTICS, /* tv_id */
+ 0, /* properties_required */
+ PROP_cfg, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ TODO_dump_cgraph /* todo_flags_finish */
+ }
+};
+
+/* Compute parameters of functions used by inliner. */
+static unsigned int
+compute_inline_parameters (void)
+{
+ struct cgraph_node *node = cgraph_node (current_function_decl);
+
+ gcc_assert (!node->global.inlined_to);
+ node->local.estimated_self_stack_size = estimated_stack_frame_size ();
+ node->global.estimated_stack_size = node->local.estimated_self_stack_size;
+ node->global.stack_frame_offset = 0;
+ node->local.inlinable = tree_inlinable_function_p (current_function_decl);
+ node->local.self_insns = estimate_num_insns (current_function_decl,
+ &eni_inlining_weights);
+ if (node->local.inlinable && !node->local.disregard_inline_limits)
+ node->local.disregard_inline_limits
+ = DECL_DISREGARD_INLINE_LIMITS (current_function_decl);
+ if (flag_really_no_inline && !node->local.disregard_inline_limits)
+ node->local.inlinable = 0;
+ /* Inlining characteristics are maintained by the cgraph_mark_inline. */
+ node->global.insns = node->local.self_insns;
+ return 0;
+}
+
+/* When inlining shall be performed. */
+static bool
+gate_inline_passes (void)
+{
+ return flag_inline_trees;
+}
+
+struct gimple_opt_pass pass_inline_parameters =
+{
+ {
+ GIMPLE_PASS,
+ NULL, /* name */
+ gate_inline_passes, /* gate */
+ compute_inline_parameters, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_INLINE_HEURISTICS, /* tv_id */
+ 0, /* properties_required */
+ PROP_cfg, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ 0 /* todo_flags_finish */
+ }
+};
+
+/* Apply inline plan to the function. */
+static unsigned int
+apply_inline (void)
+{
+ unsigned int todo = 0;
+ struct cgraph_edge *e;
+ struct cgraph_node *node = cgraph_node (current_function_decl);
+
+ /* Even when not optimizing, ensure that always_inline functions get inlined.
+ */
+ if (!optimize)
+ cgraph_decide_inlining_incrementally (node, INLINE_SPEED, 0);
+
+ /* We might need the body of this function so that we can expand
+ it inline somewhere else. */
+ if (cgraph_preserve_function_body_p (current_function_decl))
+ save_inline_function_body (node);
+
+ for (e = node->callees; e; e = e->next_callee)
+ if (!e->inline_failed || warn_inline)
+ break;
+ if (e)
+ {
+ timevar_push (TV_INTEGRATION);
+ todo = optimize_inline_calls (current_function_decl);
+ timevar_pop (TV_INTEGRATION);
+ }
+ /* In non-unit-at-a-time we must mark all referenced functions as needed. */
+ if (!flag_unit_at_a_time)
+ {
+ struct cgraph_edge *e;
+ for (e = node->callees; e; e = e->next_callee)
+ if (e->callee->analyzed)
+ cgraph_mark_needed_node (e->callee);
+ }
+ return todo | execute_fixup_cfg ();
+}
+
+struct gimple_opt_pass pass_apply_inline =
+{
+ {
+ GIMPLE_PASS,
+ "apply_inline", /* name */
+ NULL, /* gate */
+ apply_inline, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_INLINE_HEURISTICS, /* tv_id */
+ 0, /* properties_required */
+ PROP_cfg, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ TODO_dump_func | TODO_verify_flow
+ | TODO_verify_stmts /* todo_flags_finish */
+ }
+};
+
+#include "gt-ipa-inline.h"