/* 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, 51 Franklin Street, Fifth Floor, Boston, MA
-02110-1301, USA. */
+along with GCC; see the file COPYING3. If not see
+<http://www.gnu.org/licenses/>. */
/* Inlining decision heuristics
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++ effectivly and cheaply.
+ abstraction penalty on C++ effectively and cheaply.
pass_ipa_early_inlining
- With profiling, the early inlining is also neccesary to reduce
+ 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
#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 int max_insns;
static gcov_type max_count;
/* Estimate size of the function after inlining WHAT into TO. */
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);
else
{
struct cgraph_node *n;
- n = cgraph_clone_node (e->callee, e->count, e->loop_nest,
+ n = cgraph_clone_node (e->callee, e->count, e->frequency, e->loop_nest,
update_original);
cgraph_redirect_edge_callee (e, n);
}
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)
cgraph_mark_inline_edge (e, true);
if (e == edge)
edge = next;
- times++;
}
}
- gcc_assert (times);
+
return edge;
}
&& (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;
}
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.
-
- With profiling we use number of executions of each edge to drive the cost.
- We also should distinguish hot and cold calls where the cold calls are
- inlined into only when code size is overall improved.
- */
+ of the function or function body size. */
static int
cgraph_edge_badness (struct cgraph_edge *edge)
{
- if (max_count)
+ 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;
- /* Always prefer inlining saving code size. */
- if (growth <= 0)
- return INT_MIN - growth;
- return ((int)((double)edge->count * INT_MIN / max_count)) / growth;
+ /* 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
- {
- int nest = MIN (edge->loop_nest, 8);
- int 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;
- }
+ return badness;
}
/* Recompute heap nodes for each of caller edge. */
for (edge = node->callers; edge; edge = edge->next_caller)
if (edge->aux)
{
- fibheap_delete_node (heap, edge->aux);
+ fibheap_delete_node (heap, (fibnode_t) edge->aux);
edge->aux = NULL;
if (edge->inline_failed)
edge->inline_failed = failed_reason;
int badness = cgraph_edge_badness (edge);
if (edge->aux)
{
- fibnode_t n = 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, edge->aux);
+ fibheap_delete_node (heap, (fibnode_t) edge->aux);
}
edge->aux = fibheap_insert (heap, badness, edge);
}
lookup_recursive_calls (node, e->callee, heap);
}
-/* Find callgraph nodes closing a circle in the graph. The
- resulting hashtab can be used to avoid walking the circles.
- Uses the cgraph nodes ->aux field which needs to be zero
- before and will be zero after operation. */
-
-static void
-cgraph_find_cycles (struct cgraph_node *node, htab_t cycles)
-{
- struct cgraph_edge *e;
-
- if (node->aux)
- {
- void **slot;
- slot = htab_find_slot (cycles, node, INSERT);
- if (!*slot)
- {
- if (dump_file)
- fprintf (dump_file, "Cycle contains %s\n", cgraph_node_name (node));
- *slot = node;
- }
- return;
- }
-
- node->aux = node;
- for (e = node->callees; e; e = e->next_callee)
- cgraph_find_cycles (e->callee, cycles);
- node->aux = 0;
-}
-
-/* Flatten the cgraph node. We have to be careful in recursing
- as to not run endlessly in circles of the callgraph.
- We do so by using a hashtab of cycle entering nodes as generated
- by cgraph_find_cycles. */
-
-static void
-cgraph_flatten_node (struct cgraph_node *node, htab_t cycles)
-{
- struct cgraph_edge *e;
-
- for (e = node->callees; e; e = e->next_callee)
- {
- /* Inline call, if possible, and recurse. Be sure we are not
- entering callgraph circles here. */
- if (e->inline_failed
- && e->callee->local.inlinable
- && !cgraph_recursive_inlining_p (node, e->callee,
- &e->inline_failed)
- && !htab_find (cycles, e->callee))
- {
- if (dump_file)
- fprintf (dump_file, " inlining %s", cgraph_node_name (e->callee));
- cgraph_mark_inline_edge (e, true);
- cgraph_flatten_node (e->callee, cycles);
- }
- else if (dump_file)
- fprintf (dump_file, " !inlining %s", cgraph_node_name (e->callee));
- }
-}
-
/* Decide on recursive inlining: in the case function has recursive calls,
inline until body size reaches given argument. */
int depth = 0;
int n = 0;
+ if (optimize_size)
+ return false;
+
if (DECL_DECLARED_INLINE_P (node->decl))
{
limit = PARAM_VALUE (PARAM_MAX_INLINE_INSNS_RECURSIVE);
cgraph_node_name (node));
/* We need original clone to copy around. */
- master_clone = cgraph_clone_node (node, node->count, 1, false);
+ 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_estimate_size_after_inlining (1, node, master_clone)
<= limit))
{
- struct cgraph_edge *curr = fibheap_extract_min (heap);
+ struct cgraph_edge *curr
+ = (struct cgraph_edge *) fibheap_extract_min (heap);
struct cgraph_node *cnode;
depth = 1;
{
if (dump_file)
fprintf (dump_file,
- " maxmal depth reached\n");
+ " maximal depth reached\n");
continue;
}
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.
const char *failed_reason;
fibheap_t heap = fibheap_new ();
bitmap updated_nodes = BITMAP_ALLOC (NULL);
+ int min_insns, max_insns;
if (dump_file)
fprintf (dump_file, "\nDeciding on smaller functions:\n");
edge->aux = fibheap_insert (heap, cgraph_edge_badness (edge), edge);
}
}
- while (overall_insns <= max_insns && (edge = 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)))
{
int old_insns = overall_insns;
struct cgraph_node *where;
fprintf (dump_file,
" to be inlined into %s\n"
" Estimated growth after inlined into all callees is %+i insns.\n"
- " Estimated badness is %i.\n",
+ " Estimated badness is %i, frequency %.2f.\n",
cgraph_node_name (edge->caller),
cgraph_estimate_growth (edge->callee),
- cgraph_edge_badness (edge));
+ 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);
}
}
}
- if (!cgraph_maybe_hot_edge_p (edge) && growth > 0)
+ if ((!cgraph_maybe_hot_edge_p (edge) || optimize_size) && growth > 0)
{
if (!cgraph_recursive_inlining_p (edge->caller, edge->callee,
&edge->inline_failed))
else
{
struct cgraph_node *callee;
- if (!cgraph_check_inline_limits (edge->caller, edge->callee,
- &edge->inline_failed, true))
+ 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",
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 = fibheap_extract_min (heap)) != NULL)
+ while ((edge = (struct cgraph_edge *) fibheap_extract_min (heap)) != NULL)
{
gcc_assert (edge->aux);
edge->aux = NULL;
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)
overall_insns = initial_insns;
gcc_assert (!max_count || (profile_info && flag_branch_probabilities));
- max_insns = overall_insns;
- if (max_insns < PARAM_VALUE (PARAM_LARGE_UNIT_INSNS))
- max_insns = PARAM_VALUE (PARAM_LARGE_UNIT_INSNS);
-
- max_insns = ((HOST_WIDEST_INT) max_insns
- * (100 + PARAM_VALUE (PARAM_INLINE_UNIT_GROWTH)) / 100);
-
nnodes = cgraph_postorder (order);
if (dump_file)
/* Handle nodes to be flattened, but don't update overall unit size. */
if (lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
{
- int old_overall_insns = overall_insns;
- htab_t cycles;
if (dump_file)
fprintf (dump_file,
"Flattening %s\n", cgraph_node_name (node));
- cycles = htab_create (7, htab_hash_pointer, htab_eq_pointer, NULL);
- cgraph_find_cycles (node, cycles);
- cgraph_flatten_node (node, cycles);
- htab_delete (cycles);
- overall_insns = old_overall_insns;
- /* We don't need to consider always_inline functions inside the flattened
- function anymore. */
- continue;
+ cgraph_decide_inlining_incrementally (node, INLINE_ALL, 0);
}
if (!node->local.disregard_inline_limits)
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))
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 (node->callers && !node->callers->next_caller && !node->needed
&& node->local.inlinable && node->callers->inline_failed
+ && !CALL_CANNOT_INLINE_P (node->callers->call_stmt)
&& !DECL_EXTERNAL (node->decl) && !DECL_COMDAT (node->decl))
{
if (dump_file)
return 0;
}
-enum inlining_mode {
- INLINE_SIZE,
- INLINE_SPEED,
- INLINE_ALL
-};
+/* 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. */
-static unsigned int
-cgraph_decide_inlining_incrementally (struct cgraph_node *node, enum inlining_mode mode)
+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;
- unsigned int todo = 0;
+ enum inlining_mode old_mode;
#ifdef ENABLE_CHECKING
verify_cgraph_node (node);
#endif
- if (lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
+
+ 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)
- fprintf (dump_file, " Flattening %s\n", cgraph_node_name (node));
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Flattening %s\n", cgraph_node_name (node));
+ }
mode = INLINE_ALL;
}
+ node->aux = (void *)(size_t) mode;
+
/* First of all look for always inline functions. */
for (e = node->callees; e; e = e->next_callee)
- if ((e->callee->local.disregard_inline_limits
- || (mode == INLINE_ALL && e->callee->local.inlinable))
- && e->inline_failed
- && (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
- == gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
- && !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) || e->callee->inline_decl))
- {
- if (dump_file)
- {
- fprintf (dump_file, " Inlining always_inline %s",
- cgraph_node_name (e->callee));
- fprintf (dump_file, " into %s\n", cgraph_node_name (node));
- }
- 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)
- cgraph_decide_inlining_incrementally (e->callee, mode);
-
- inlined = true;
- }
-
- /* Now do the automatic inlining. */
- if (!flag_really_no_inline && mode != INLINE_ALL)
- 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)
- && (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
- == gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
- && (mode != INLINE_SIZE
- || (cgraph_estimate_size_after_inlining (1, e->caller, e->callee)
- <= e->caller->global.insns))
- && cgraph_check_inline_limits (node, e->callee, &e->inline_failed,
- false)
- && (DECL_SAVED_TREE (e->callee->decl) || e->callee->inline_decl))
+ {
+ 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)
{
- if (cgraph_default_inline_p (e->callee, &failed_reason))
+ 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)
{
- if (dump_file)
- {
- fprintf (dump_file, " Inlining %s",
- cgraph_node_name (e->callee));
- fprintf (dump_file, " into %s\n", cgraph_node_name (node));
- }
- cgraph_mark_inline (e);
- inlined = true;
- if (!flag_unit_at_a_time)
- cgraph_decide_inlining_incrementally (e->callee, mode);
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: recursive call.\n");
}
- else if (!flag_unit_at_a_time)
- e->inline_failed = failed_reason;
+ continue;
}
- if (flag_unit_at_a_time && inlined && !node->global.inlined_to)
- {
- timevar_push (TV_INTEGRATION);
- todo = optimize_inline_calls (current_function_decl);
- timevar_pop (TV_INTEGRATION);
+ 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);
}
- return todo;
+
+ /* Now do the automatic inlining. */
+ if (!flag_really_no_inline && mode != INLINE_ALL
+ && mode != INLINE_ALWAYS_INLINE)
+ for (e = node->callees; e; e = e->next_callee)
+ {
+ if (!e->callee->local.inlinable
+ || !e->inline_failed
+ || e->callee->local.disregard_inline_limits)
+ continue;
+ if (dump_file)
+ fprintf (dump_file, "Considering inline candidate %s.\n",
+ cgraph_node_name (e->callee));
+ if (cgraph_recursive_inlining_p (node, e->callee, &e->inline_failed))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: recursive call.\n");
+ }
+ continue;
+ }
+ if (gimple_in_ssa_p (DECL_STRUCT_FUNCTION (node->decl))
+ != gimple_in_ssa_p (DECL_STRUCT_FUNCTION (e->callee->decl)))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file, "Not inlining: SSA form does not match.\n");
+ }
+ continue;
+ }
+ /* When the function body would grow and inlining the function won't
+ eliminate the need for offline copy of the function, don't inline.
+ */
+ if (mode == INLINE_SIZE
+ && (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. */
cgraph_early_inlining (void)
{
struct cgraph_node *node = cgraph_node (current_function_decl);
+ unsigned int todo = 0;
if (sorrycount || errorcount)
return 0;
- return cgraph_decide_inlining_incrementally (node,
- flag_unit_at_a_time
- ? INLINE_SIZE : INLINE_SPEED);
+ 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. */
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);
- if (node->local.inlinable)
+ 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
- = lang_hooks.tree_inlining.disregard_inline_limits (current_function_decl);
+ = disregard_inline_limits_p (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. */
/* Even when not optimizing, ensure that always_inline functions get inlined.
*/
if (!optimize)
- cgraph_decide_inlining_incrementally (node, false);
+ 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. */
OSDN Git Service
