#include "tree-flow.h"
#include "rtl.h"
#include "ipa-prop.h"
+#include "except.h"
+
+#define MAX_TIME 1000000000
/* Mode incremental inliner operate on:
enum inlining_mode {
INLINE_NONE = 0,
INLINE_ALWAYS_INLINE,
+ INLINE_SIZE_NORECURSIVE,
INLINE_SIZE,
INLINE_ALL
};
/* Statistics we collect about inlining algorithm. */
static int ncalls_inlined;
static int nfunctions_inlined;
-static int overall_insns;
-static gcov_type max_count;
+static int overall_size;
+static gcov_type max_count, max_benefit;
/* Holders of ipa cgraph hooks: */
static struct cgraph_node_hook_list *function_insertion_hook_holder;
return &node->local.inline_summary;
}
-/* Estimate size of the function after inlining WHAT into TO. */
+/* Estimate self time of the function after inlining WHAT into TO. */
static int
-cgraph_estimate_size_after_inlining (int times, struct cgraph_node *to,
+cgraph_estimate_time_after_inlining (int frequency, struct cgraph_node *to,
struct cgraph_node *what)
{
- int size;
- tree fndecl = what->decl, arg;
- int call_insns = PARAM_VALUE (PARAM_INLINE_CALL_COST);
+ gcov_type time = (((gcov_type)what->global.time
+ - inline_summary (what)->time_inlining_benefit)
+ * frequency + CGRAPH_FREQ_BASE / 2) / CGRAPH_FREQ_BASE
+ + to->global.time;
+ if (time < 0)
+ time = 0;
+ if (time > MAX_TIME)
+ time = MAX_TIME;
+ return time;
+}
- for (arg = DECL_ARGUMENTS (fndecl); arg; arg = TREE_CHAIN (arg))
- call_insns += estimate_move_cost (TREE_TYPE (arg));
- size = (what->global.insns - call_insns) * times + to->global.insns;
+/* Estimate self time of the function after inlining WHAT into TO. */
+
+static int
+cgraph_estimate_size_after_inlining (int times, struct cgraph_node *to,
+ struct cgraph_node *what)
+{
+ int size = (what->global.size - inline_summary (what)->size_inlining_benefit) * times + to->global.size;
gcc_assert (size >= 0);
return size;
}
/* 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_can_remove_if_no_direct_calls_p (e->callee)
&& !cgraph_new_nodes)
{
gcc_assert (!e->callee->global.inlined_to);
if (e->callee->analyzed)
- overall_insns -= e->callee->global.insns, nfunctions_inlined++;
+ {
+ overall_size -= e->callee->global.size;
+ nfunctions_inlined++;
+ }
duplicate = false;
+ e->callee->local.externally_visible = false;
}
else
{
struct cgraph_node *n;
n = cgraph_clone_node (e->callee, e->count, e->frequency, e->loop_nest,
- update_original);
+ update_original, NULL);
cgraph_redirect_edge_callee (e, n);
}
}
cgraph_mark_inline_edge (struct cgraph_edge *e, bool update_original,
VEC (cgraph_edge_p, heap) **new_edges)
{
- int old_insns = 0, new_insns = 0;
+ int old_size = 0, new_size = 0;
struct cgraph_node *to = NULL, *what;
struct cgraph_edge *curr = e;
-
- if (e->callee->inline_decl)
- cgraph_redirect_edge_callee (e, cgraph_node (e->callee->inline_decl));
+ int freq;
+ bool duplicate = false;
+ int orig_size = e->callee->global.size;
gcc_assert (e->inline_failed);
e->inline_failed = CIF_OK;
DECL_POSSIBLY_INLINED (e->callee->decl) = true;
e->callee->global.inlined = true;
+ if (e->callee->callers->next_caller
+ || !cgraph_can_remove_if_no_direct_calls_p (e->callee))
+ duplicate = true;
cgraph_clone_inlined_nodes (e, true, update_original);
what = e->callee;
+ freq = e->frequency;
/* Now update size of caller and all functions caller is inlined into. */
for (;e && !e->inline_failed; e = e->caller->callers)
{
- old_insns = e->caller->global.insns;
- new_insns = cgraph_estimate_size_after_inlining (1, e->caller,
- what);
- gcc_assert (new_insns >= 0);
to = e->caller;
- to->global.insns = new_insns;
+ old_size = e->caller->global.size;
+ new_size = cgraph_estimate_size_after_inlining (1, to, what);
+ to->global.size = new_size;
+ to->global.time = cgraph_estimate_time_after_inlining (freq, to, what);
}
gcc_assert (what->global.inlined_to == to);
- if (new_insns > old_insns)
- overall_insns += new_insns - old_insns;
+ if (new_size > old_size)
+ overall_size += new_size - old_size;
+ if (!duplicate)
+ overall_size -= orig_size;
ncalls_inlined++;
- if (flag_indirect_inlining)
+ if (flag_indirect_inlining && !flag_wpa)
return ipa_propagate_indirect_call_infos (curr, new_edges);
else
return false;
struct cgraph_node *what = edge->callee;
struct cgraph_edge *e, *next;
- gcc_assert (!gimple_call_cannot_inline_p (edge->call_stmt));
+ gcc_assert (!edge->call_stmt_cannot_inline_p);
/* Look for all calls, mark them inline and clone recursively
all inlined functions. */
for (e = what->callers; e; e = next)
self_recursive = true;
if (e->inline_failed)
growth += (cgraph_estimate_size_after_inlining (1, e->caller, node)
- - e->caller->global.insns);
+ - e->caller->global.size);
}
/* ??? Wrong for non-trivially self recursive functions or cases where
we decide to not inline for different reasons, but it is not big deal
as in that case we will keep the body around, but we will also avoid
some inlining. */
- if (!node->needed && !DECL_EXTERNAL (node->decl) && !self_recursive)
- growth -= node->global.insns;
+ if (cgraph_only_called_directly_p (node)
+ && !DECL_EXTERNAL (node->decl) && !self_recursive)
+ growth -= node->global.size;
node->global.estimated_growth = growth;
return growth;
/* When inlining large function body called once into small function,
take the inlined function as base for limiting the growth. */
- if (inline_summary (to)->self_insns > inline_summary(what)->self_insns)
- limit = inline_summary (to)->self_insns;
+ if (inline_summary (to)->self_size > inline_summary(what)->self_size)
+ limit = inline_summary (to)->self_size;
else
- limit = inline_summary (what)->self_insns;
+ limit = inline_summary (what)->self_size;
limit += limit * PARAM_VALUE (PARAM_LARGE_FUNCTION_GROWTH) / 100;
/* Check the size after inlining against the function limits. But allow
the function to shrink if it went over the limits by forced inlining. */
newsize = cgraph_estimate_size_after_inlining (times, to, what);
- if (newsize >= to->global.insns
+ if (newsize >= to->global.size
&& newsize > PARAM_VALUE (PARAM_LARGE_FUNCTION_INSNS)
&& newsize > limit)
{
{
tree decl = n->decl;
- if (n->inline_decl)
- decl = n->inline_decl;
if (!flag_inline_small_functions && !DECL_DECLARED_INLINE_P (decl))
{
if (reason)
return false;
}
- if (!DECL_STRUCT_FUNCTION (decl)->cfg)
+ if (!n->analyzed)
{
if (reason)
*reason = CIF_BODY_NOT_AVAILABLE;
if (DECL_DECLARED_INLINE_P (decl))
{
- if (n->global.insns >= MAX_INLINE_INSNS_SINGLE)
+ if (n->global.size >= MAX_INLINE_INSNS_SINGLE)
{
if (reason)
*reason = CIF_MAX_INLINE_INSNS_SINGLE_LIMIT;
}
else
{
- if (n->global.insns >= MAX_INLINE_INSNS_AUTO)
+ if (n->global.size >= MAX_INLINE_INSNS_AUTO)
{
if (reason)
*reason = CIF_MAX_INLINE_INSNS_AUTO_LIMIT;
static int
cgraph_edge_badness (struct cgraph_edge *edge)
{
- int badness;
+ gcov_type badness;
int growth =
cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
- growth -= edge->caller->global.insns;
+ growth -= edge->caller->global.size;
/* Always prefer inlining saving code size. */
if (growth <= 0)
/* 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;
+ badness = ((int)((double)edge->count * INT_MIN / max_count / (max_benefit + 1))
+ * (inline_summary (edge->callee)->time_inlining_benefit + 1)) / growth;
/* When function local profile is available, base priorities on
growth / frequency, so we optimize for overall frequency of inlined
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;
+ int div = edge->frequency * 100 / CGRAPH_FREQ_BASE + 1;
+ badness = growth * 10000;
+ div *= MIN (100 * inline_summary (edge->callee)->time_inlining_benefit
+ / (edge->callee->global.time + 1) + 1, 100);
+
/* 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 > 10000)
+ div = 10000 + ceil_log2 (div) - 8;
if (div < 1)
div = 1;
if (badness > 0)
badness /= div;
badness += cgraph_estimate_growth (edge->callee);
+ if (badness > INT_MAX)
+ badness = INT_MAX;
}
/* When function local profile is not available or it does not give
useful information (ie frequency is zero), base the cost on
cgraph_node_name (node));
/* We need original clone to copy around. */
- master_clone = cgraph_clone_node (node, node->count, CGRAPH_FREQ_BASE, 1, false);
+ master_clone = cgraph_clone_node (node, node->count, CGRAPH_FREQ_BASE, 1,
+ false, NULL);
master_clone->needed = true;
for (e = master_clone->callees; e; e = e->next_callee)
if (!e->inline_failed)
fibheap_delete (heap);
if (dump_file)
fprintf (dump_file,
- "\n Inlined %i times, body grown from %i to %i insns\n", n,
- master_clone->global.insns, node->global.insns);
+ "\n Inlined %i times, body grown from size %i to %i, time %i to %i\n", n,
+ master_clone->global.size, node->global.size,
+ master_clone->global.time, node->global.time);
/* Remove master clone we used for inlining. We rely that clones inlined
into master clone gets queued just before master clone so we don't
cgraph_inline_failed_t failed_reason;
fibheap_t heap = fibheap_new ();
bitmap updated_nodes = BITMAP_ALLOC (NULL);
- int min_insns, max_insns;
+ int min_size, max_size;
VEC (cgraph_edge_p, heap) *new_indirect_edges = NULL;
- if (flag_indirect_inlining)
+ if (flag_indirect_inlining && !flag_wpa)
new_indirect_edges = VEC_alloc (cgraph_edge_p, heap, 8);
if (dump_file)
}
}
- max_insns = compute_max_insns (overall_insns);
- min_insns = overall_insns;
+ max_size = compute_max_insns (overall_size);
+ min_size = overall_size;
- while (overall_insns <= max_insns
+ while (overall_size <= max_size
&& (edge = (struct cgraph_edge *) fibheap_extract_min (heap)))
{
- int old_insns = overall_insns;
+ int old_size = overall_size;
struct cgraph_node *where;
int growth =
cgraph_estimate_size_after_inlining (1, edge->caller, edge->callee);
cgraph_inline_failed_t not_good = CIF_OK;
- growth -= edge->caller->global.insns;
+ growth -= edge->caller->global.size;
if (dump_file)
{
fprintf (dump_file,
- "\nConsidering %s with %i insns\n",
+ "\nConsidering %s with %i size\n",
cgraph_node_name (edge->callee),
- edge->callee->global.insns);
+ edge->callee->global.size);
fprintf (dump_file,
- " to be inlined into %s\n"
+ " to be inlined into %s in %s:%i\n"
" Estimated growth after inlined into all callees is %+i insns.\n"
" Estimated badness is %i, frequency %.2f.\n",
cgraph_node_name (edge->caller),
+ gimple_filename ((const_gimple) edge->call_stmt),
+ gimple_lineno ((const_gimple) edge->call_stmt),
cgraph_estimate_growth (edge->callee),
cgraph_edge_badness (edge),
edge->frequency / (double)CGRAPH_FREQ_BASE);
}
continue;
}
- if (!tree_can_inline_p (edge->caller->decl, edge->callee->decl))
+ if (!tree_can_inline_p (edge))
{
- gimple_call_set_cannot_inline (edge->call_stmt, true);
- edge->inline_failed = CIF_TARGET_OPTION_MISMATCH;
if (dump_file)
fprintf (dump_file, " inline_failed:%s.\n",
cgraph_inline_failed_string (edge->inline_failed));
if (where->global.inlined_to)
where = where->global.inlined_to;
if (!cgraph_decide_recursive_inlining (where,
- flag_indirect_inlining
+ flag_indirect_inlining && !flag_wpa
? &new_indirect_edges : NULL))
continue;
- if (flag_indirect_inlining)
+ if (flag_indirect_inlining && !flag_wpa)
add_new_edges_to_heap (heap, new_indirect_edges);
update_callee_keys (heap, where, updated_nodes);
}
else
{
struct cgraph_node *callee;
- if (gimple_call_cannot_inline_p (edge->call_stmt)
+ if (edge->call_stmt_cannot_inline_p
|| !cgraph_check_inline_limits (edge->caller, edge->callee,
&edge->inline_failed, true))
{
}
callee = edge->callee;
cgraph_mark_inline_edge (edge, true, &new_indirect_edges);
- if (flag_indirect_inlining)
+ if (flag_indirect_inlining && !flag_wpa)
add_new_edges_to_heap (heap, new_indirect_edges);
update_callee_keys (heap, callee, updated_nodes);
if (dump_file)
{
fprintf (dump_file,
- " Inlined into %s which now has %i insns,"
- "net change of %+i insns.\n",
+ " Inlined into %s which now has size %i and self time %i,"
+ "net change of %+i.\n",
cgraph_node_name (edge->caller),
- edge->caller->global.insns,
- overall_insns - old_insns);
+ edge->caller->global.time,
+ edge->caller->global.size,
+ overall_size - old_size);
}
- if (min_insns > overall_insns)
+ if (min_size > overall_size)
{
- min_insns = overall_insns;
- max_insns = compute_max_insns (min_insns);
+ min_size = overall_size;
+ max_size = compute_max_insns (min_size);
if (dump_file)
- fprintf (dump_file, "New minimal insns reached: %i\n", min_insns);
+ fprintf (dump_file, "New minimal size reached: %i\n", min_size);
}
}
while ((edge = (struct cgraph_edge *) fibheap_extract_min (heap)) != NULL)
int nnodes;
struct cgraph_node **order =
XCNEWVEC (struct cgraph_node *, cgraph_n_nodes);
- int old_insns = 0;
+ int old_size = 0;
int i;
- int initial_insns = 0;
bool redo_always_inline = true;
+ int initial_size = 0;
cgraph_remove_function_insertion_hook (function_insertion_hook_holder);
+ if (in_lto_p && flag_indirect_inlining && !flag_wpa)
+ ipa_update_after_lto_read ();
max_count = 0;
+ max_benefit = 0;
for (node = cgraph_nodes; node; node = node->next)
- if (node->analyzed && (node->needed || node->reachable))
+ if (node->analyzed)
{
struct cgraph_edge *e;
- initial_insns += inline_summary (node)->self_insns;
- gcc_assert (inline_summary (node)->self_insns == node->global.insns);
+ gcc_assert (inline_summary (node)->self_size == node->global.size);
+ initial_size += node->global.size;
for (e = node->callees; e; e = e->next_callee)
if (max_count < e->count)
max_count = e->count;
+ if (max_benefit < inline_summary (node)->time_inlining_benefit)
+ max_benefit = inline_summary (node)->time_inlining_benefit;
}
- overall_insns = initial_insns;
- gcc_assert (!max_count || (profile_info && flag_branch_probabilities));
+ gcc_assert (in_lto_p
+ || !max_count
+ || (profile_info && flag_branch_probabilities));
+ overall_size = initial_size;
nnodes = cgraph_postorder (order);
if (dump_file)
fprintf (dump_file,
- "\nDeciding on inlining. Starting with %i insns.\n",
- initial_insns);
+ "\nDeciding on inlining. Starting with size %i.\n",
+ initial_size);
for (node = cgraph_nodes; node; node = node->next)
node->aux = 0;
continue;
if (dump_file)
fprintf (dump_file,
- "\nConsidering %s %i insns (always inline)\n",
- cgraph_node_name (node), node->global.insns);
- old_insns = overall_insns;
+ "\nConsidering %s size:%i (always inline)\n",
+ cgraph_node_name (node), node->global.size);
+ old_size = overall_size;
for (e = node->callers; e; e = next)
{
next = e->next_caller;
- if (!e->inline_failed
- || gimple_call_cannot_inline_p (e->call_stmt))
+ if (!e->inline_failed || e->call_stmt_cannot_inline_p)
continue;
if (cgraph_recursive_inlining_p (e->caller, e->callee,
&e->inline_failed))
continue;
- if (!tree_can_inline_p (e->caller->decl, e->callee->decl))
- {
- gimple_call_set_cannot_inline (e->call_stmt, true);
- continue;
- }
+ if (!tree_can_inline_p (e))
+ continue;
if (cgraph_mark_inline_edge (e, true, NULL))
redo_always_inline = true;
if (dump_file)
fprintf (dump_file,
- " Inlined into %s which now has %i insns.\n",
+ " Inlined into %s which now has size %i.\n",
cgraph_node_name (e->caller),
- e->caller->global.insns);
+ e->caller->global.size);
}
/* Inlining self recursive function might introduce new calls to
themselves we didn't see in the loop above. Fill in the proper
e->inline_failed = CIF_RECURSIVE_INLINING;
if (dump_file)
fprintf (dump_file,
- " Inlined for a net change of %+i insns.\n",
- overall_insns - old_insns);
+ " Inlined for a net change of %+i size.\n",
+ overall_size - old_size);
}
}
if (node->callers
&& !node->callers->next_caller
- && !node->needed
+ && cgraph_only_called_directly_p (node)
&& node->local.inlinable
&& node->callers->inline_failed
- && !gimple_call_cannot_inline_p (node->callers->call_stmt)
+ && node->callers->caller != node
+ && node->callers->caller->global.inlined_to != node
+ && !node->callers->call_stmt_cannot_inline_p
&& !DECL_EXTERNAL (node->decl)
&& !DECL_COMDAT (node->decl))
{
+ cgraph_inline_failed_t reason;
+ old_size = overall_size;
if (dump_file)
{
fprintf (dump_file,
- "\nConsidering %s %i insns.\n",
- cgraph_node_name (node), node->global.insns);
+ "\nConsidering %s size %i.\n",
+ cgraph_node_name (node), node->global.size);
fprintf (dump_file,
" Called once from %s %i insns.\n",
cgraph_node_name (node->callers->caller),
- node->callers->caller->global.insns);
+ node->callers->caller->global.size);
}
- old_insns = overall_insns;
-
if (cgraph_check_inline_limits (node->callers->caller, node,
- NULL, false))
+ &reason, false))
{
cgraph_mark_inline (node->callers);
if (dump_file)
fprintf (dump_file,
- " Inlined into %s which now has %i insns"
- " for a net change of %+i insns.\n",
+ " Inlined into %s which now has %i size"
+ " for a net change of %+i size.\n",
cgraph_node_name (node->callers->caller),
- node->callers->caller->global.insns,
- overall_insns - old_insns);
+ node->callers->caller->global.size,
+ overall_size - old_size);
}
else
{
if (dump_file)
fprintf (dump_file,
- " Inline limit reached, not inlined.\n");
+ " Not inlining: %s.\n",
+ cgraph_inline_failed_string (reason));
}
}
}
}
/* Free ipa-prop structures if they are no longer needed. */
- if (flag_indirect_inlining)
+ if (flag_indirect_inlining && !flag_wpa)
free_all_ipa_structures_after_iinln ();
if (dump_file)
fprintf (dump_file,
"\nInlined %i calls, eliminated %i functions, "
- "%i insns turned to %i insns.\n\n",
- ncalls_inlined, nfunctions_inlined, initial_insns,
- overall_insns);
+ "size %i turned to %i size.\n\n",
+ ncalls_inlined, nfunctions_inlined, initial_size,
+ overall_size);
free (order);
return 0;
}
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;
+ bool inlined = false;
/* We've hit cycle? */
if (callee_mode)
if (mode == INLINE_ALL || always_inline)
cgraph_decide_inlining_incrementally (e->callee, mode, depth + 1);
+ inlined = true;
}
callee->aux = (void *)(size_t) callee_mode;
+ return inlined;
+}
+
+/* Return true when N is leaf function. Accept cheap (pure&const) builtins
+ in leaf functions. */
+static bool
+leaf_node_p (struct cgraph_node *n)
+{
+ struct cgraph_edge *e;
+ for (e = n->callees; e; e = e->next_callee)
+ if (!DECL_BUILT_IN (e->callee->decl)
+ || (!TREE_READONLY (e->callee->decl)
+ || DECL_PURE_P (e->callee->decl)))
+ return false;
return true;
}
old_mode = (enum inlining_mode) (size_t)node->aux;
- if (mode != INLINE_ALWAYS_INLINE
+ if (mode != INLINE_ALWAYS_INLINE && mode != INLINE_SIZE_NORECURSIVE
&& lookup_attribute ("flatten", DECL_ATTRIBUTES (node->decl)) != NULL)
{
if (dump_file)
node->aux = (void *)(size_t) mode;
/* First of all look for always inline functions. */
- for (e = node->callees; e; e = e->next_callee)
- {
- if (!e->callee->local.disregard_inline_limits
- && (mode != INLINE_ALL || !e->callee->local.inlinable))
- continue;
- if (gimple_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 (!tree_can_inline_p (node->decl, e->callee->decl))
- {
- gimple_call_set_cannot_inline (e->call_stmt, true);
- if (dump_file)
- {
- indent_to (dump_file, depth);
- fprintf (dump_file,
- "Not inlining: Target specific option mismatch.\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");
- }
+ if (mode != INLINE_SIZE_NORECURSIVE)
+ for (e = node->callees; e; e = e->next_callee)
+ {
+ if (!e->callee->local.disregard_inline_limits
+ && (mode != INLINE_ALL || !e->callee->local.inlinable))
continue;
- }
- if (!e->callee->analyzed && !e->callee->inline_decl)
- {
- if (dump_file)
- {
- indent_to (dump_file, depth);
- fprintf (dump_file,
- "Not inlining: Function body no longer available.\n");
- }
+ if (e->call_stmt_cannot_inline_p)
continue;
- }
- inlined |= try_inline (e, mode, depth);
- }
+ /* 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 (!tree_can_inline_p (e))
+ {
+ if (dump_file)
+ {
+ indent_to (dump_file, depth);
+ fprintf (dump_file,
+ "Not inlining: %s",
+ cgraph_inline_failed_string (e->inline_failed));
+ }
+ 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 (!e->callee->analyzed)
+ {
+ 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 (mode != INLINE_ALL && mode != INLINE_ALWAYS_INLINE)
for (e = node->callees; e; e = e->next_callee)
{
+ int allowed_growth = 0;
if (!e->callee->local.inlinable
|| !e->inline_failed
|| e->callee->local.disregard_inline_limits)
}
continue;
}
+
+ if (cgraph_maybe_hot_edge_p (e) && leaf_node_p (e->callee)
+ && optimize_function_for_speed_p (cfun))
+ allowed_growth = PARAM_VALUE (PARAM_EARLY_INLINING_INSNS);
+
/* 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
+ if (((mode == INLINE_SIZE || mode == INLINE_SIZE_NORECURSIVE)
|| (!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)
+ > e->caller->global.size + allowed_growth)
+ && cgraph_estimate_growth (e->callee) > allowed_growth)
{
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
- "Not inlining: code size would grow by %i insns.\n",
+ "Not inlining: code size would grow by %i.\n",
cgraph_estimate_size_after_inlining (1, e->caller,
e->callee)
- - e->caller->global.insns);
+ - e->caller->global.size);
}
continue;
}
if (!cgraph_check_inline_limits (node, e->callee, &e->inline_failed,
- false)
- || gimple_call_cannot_inline_p (e->call_stmt))
+ false)
+ || e->call_stmt_cannot_inline_p)
{
if (dump_file)
{
}
continue;
}
- if (!e->callee->analyzed && !e->callee->inline_decl)
+ if (!e->callee->analyzed)
{
if (dump_file)
{
}
continue;
}
- if (!tree_can_inline_p (node->decl, e->callee->decl))
+ if (!tree_can_inline_p (e))
{
- gimple_call_set_cannot_inline (e->call_stmt, true);
if (dump_file)
{
indent_to (dump_file, depth);
fprintf (dump_file,
- "Not inlining: Target specific option mismatch.\n");
+ "Not inlining: %s.",
+ cgraph_inline_failed_string (e->inline_failed));
}
continue;
}
{
struct cgraph_node *node = cgraph_node (current_function_decl);
unsigned int todo = 0;
+ int iterations = 0;
if (sorrycount || errorcount)
return 0;
- if (cgraph_decide_inlining_incrementally (node, INLINE_SIZE, 0))
+ while (iterations < PARAM_VALUE (PARAM_EARLY_INLINER_MAX_ITERATIONS)
+ && cgraph_decide_inlining_incrementally (node,
+ iterations
+ ? INLINE_SIZE_NORECURSIVE : INLINE_SIZE, 0))
{
timevar_push (TV_INTEGRATION);
- todo = optimize_inline_calls (current_function_decl);
+ todo |= optimize_inline_calls (current_function_decl);
+ iterations++;
timevar_pop (TV_INTEGRATION);
}
+ if (dump_file)
+ fprintf (dump_file, "Iterations: %i\n", iterations);
cfun->always_inline_functions_inlined = true;
return todo;
}
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
- PROP_cfg, /* properties_provided */
+ 0, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_dump_func /* todo_flags_finish */
cgraph_gate_ipa_early_inlining (void)
{
return (flag_early_inlining
+ && !in_lto_p
&& (flag_branch_probabilities || flag_test_coverage
|| profile_arc_flag));
}
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
- PROP_cfg, /* properties_provided */
+ 0, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_dump_cgraph /* todo_flags_finish */
}
};
+/* See if statement might disappear after inlining. We are not terribly
+ sophisficated, basically looking for simple abstraction penalty wrappers. */
+
+static bool
+likely_eliminated_by_inlining_p (gimple stmt)
+{
+ enum gimple_code code = gimple_code (stmt);
+ switch (code)
+ {
+ case GIMPLE_RETURN:
+ return true;
+ case GIMPLE_ASSIGN:
+ if (gimple_num_ops (stmt) != 2)
+ return false;
+
+ /* Casts of parameters, loads from parameters passed by reference
+ and stores to return value or parameters are probably free after
+ inlining. */
+ if (gimple_assign_rhs_code (stmt) == CONVERT_EXPR
+ || gimple_assign_rhs_code (stmt) == NOP_EXPR
+ || gimple_assign_rhs_code (stmt) == VIEW_CONVERT_EXPR
+ || gimple_assign_rhs_class (stmt) == GIMPLE_SINGLE_RHS)
+ {
+ tree rhs = gimple_assign_rhs1 (stmt);
+ tree lhs = gimple_assign_lhs (stmt);
+ tree inner_rhs = rhs;
+ tree inner_lhs = lhs;
+ bool rhs_free = false;
+ bool lhs_free = false;
+
+ while (handled_component_p (inner_lhs) || TREE_CODE (inner_lhs) == INDIRECT_REF)
+ inner_lhs = TREE_OPERAND (inner_lhs, 0);
+ while (handled_component_p (inner_rhs)
+ || TREE_CODE (inner_rhs) == ADDR_EXPR || TREE_CODE (inner_rhs) == INDIRECT_REF)
+ inner_rhs = TREE_OPERAND (inner_rhs, 0);
+
+
+ if (TREE_CODE (inner_rhs) == PARM_DECL
+ || (TREE_CODE (inner_rhs) == SSA_NAME
+ && SSA_NAME_IS_DEFAULT_DEF (inner_rhs)
+ && TREE_CODE (SSA_NAME_VAR (inner_rhs)) == PARM_DECL))
+ rhs_free = true;
+ if (rhs_free && is_gimple_reg (lhs))
+ lhs_free = true;
+ if (((TREE_CODE (inner_lhs) == PARM_DECL
+ || (TREE_CODE (inner_lhs) == SSA_NAME
+ && SSA_NAME_IS_DEFAULT_DEF (inner_lhs)
+ && TREE_CODE (SSA_NAME_VAR (inner_lhs)) == PARM_DECL))
+ && inner_lhs != lhs)
+ || TREE_CODE (inner_lhs) == RESULT_DECL
+ || (TREE_CODE (inner_lhs) == SSA_NAME
+ && TREE_CODE (SSA_NAME_VAR (inner_lhs)) == RESULT_DECL))
+ lhs_free = true;
+ if (lhs_free && (is_gimple_reg (rhs) || is_gimple_min_invariant (rhs)))
+ rhs_free = true;
+ if (lhs_free && rhs_free)
+ return true;
+ }
+ return false;
+ default:
+ return false;
+ }
+}
+
+/* Compute function body size parameters for NODE. */
+
+static void
+estimate_function_body_sizes (struct cgraph_node *node)
+{
+ gcov_type time = 0;
+ gcov_type time_inlining_benefit = 0;
+ int size = 0;
+ int size_inlining_benefit = 0;
+ basic_block bb;
+ gimple_stmt_iterator bsi;
+ struct function *my_function = DECL_STRUCT_FUNCTION (node->decl);
+ tree arg;
+ int freq;
+ tree funtype = TREE_TYPE (node->decl);
+
+ if (dump_file)
+ fprintf (dump_file, "Analyzing function body size: %s\n",
+ cgraph_node_name (node));
+
+ gcc_assert (my_function && my_function->cfg);
+ FOR_EACH_BB_FN (bb, my_function)
+ {
+ freq = compute_call_stmt_bb_frequency (node->decl, bb);
+ for (bsi = gsi_start_bb (bb); !gsi_end_p (bsi); gsi_next (&bsi))
+ {
+ gimple stmt = gsi_stmt (bsi);
+ int this_size = estimate_num_insns (stmt, &eni_size_weights);
+ int this_time = estimate_num_insns (stmt, &eni_time_weights);
+
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ {
+ fprintf (dump_file, " freq:%6i size:%3i time:%3i ",
+ freq, this_size, this_time);
+ print_gimple_stmt (dump_file, stmt, 0, 0);
+ }
+ this_time *= freq;
+ time += this_time;
+ size += this_size;
+ if (likely_eliminated_by_inlining_p (stmt))
+ {
+ size_inlining_benefit += this_size;
+ time_inlining_benefit += this_time;
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, " Likely eliminated\n");
+ }
+ gcc_assert (time >= 0);
+ gcc_assert (size >= 0);
+ }
+ }
+ time = (time + CGRAPH_FREQ_BASE / 2) / CGRAPH_FREQ_BASE;
+ time_inlining_benefit = ((time_inlining_benefit + CGRAPH_FREQ_BASE / 2)
+ / CGRAPH_FREQ_BASE);
+ if (dump_file)
+ fprintf (dump_file, "Overall function body time: %i-%i size: %i-%i\n",
+ (int)time, (int)time_inlining_benefit,
+ size, size_inlining_benefit);
+ time_inlining_benefit += eni_time_weights.call_cost;
+ size_inlining_benefit += eni_size_weights.call_cost;
+ if (!VOID_TYPE_P (TREE_TYPE (funtype)))
+ {
+ int cost = estimate_move_cost (TREE_TYPE (funtype));
+ time_inlining_benefit += cost;
+ size_inlining_benefit += cost;
+ }
+ for (arg = DECL_ARGUMENTS (node->decl); arg; arg = TREE_CHAIN (arg))
+ if (!VOID_TYPE_P (TREE_TYPE (arg)))
+ {
+ int cost = estimate_move_cost (TREE_TYPE (arg));
+ time_inlining_benefit += cost;
+ size_inlining_benefit += cost;
+ }
+ if (time_inlining_benefit > MAX_TIME)
+ time_inlining_benefit = MAX_TIME;
+ if (time > MAX_TIME)
+ time = MAX_TIME;
+ inline_summary (node)->self_time = time;
+ inline_summary (node)->self_size = size;
+ if (dump_file)
+ fprintf (dump_file, "With function call overhead time: %i-%i size: %i-%i\n",
+ (int)time, (int)time_inlining_benefit,
+ size, size_inlining_benefit);
+ inline_summary (node)->time_inlining_benefit = time_inlining_benefit;
+ inline_summary (node)->size_inlining_benefit = size_inlining_benefit;
+}
+
/* Compute parameters of functions used by inliner. */
unsigned int
compute_inline_parameters (struct cgraph_node *node)
/* Can this function be inlined at all? */
node->local.inlinable = tree_inlinable_function_p (current_function_decl);
-
- /* Estimate the number of instructions for this function.
- ??? At -O0 we don't use this information except for the dumps, and
- even then only for always_inline functions. But disabling this
- causes ICEs in the inline heuristics... */
- inline_summary (node)->self_insns
- = estimate_num_insns_fn (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);
-
+ estimate_function_body_sizes (node);
/* Inlining characteristics are maintained by the cgraph_mark_inline. */
- node->global.insns = inline_summary (node)->self_insns;
+ node->global.time = inline_summary (node)->self_time;
+ node->global.size = inline_summary (node)->self_size;
return 0;
}
{
{
GIMPLE_PASS,
- NULL, /* name */
+ "inline_param", /* name */
NULL, /* gate */
compute_inline_parameters_for_current,/* execute */
NULL, /* sub */
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
- PROP_cfg, /* properties_provided */
+ 0, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
0 /* todo_flags_finish */
return todo | execute_fixup_cfg ();
}
-struct ipa_opt_pass pass_ipa_inline =
+/* Read inline summary. Jump functions are shared among ipa-cp
+ and inliner, so when ipa-cp is active, we don't need to write them
+ twice. */
+
+static void
+inline_read_summary (void)
+{
+ if (flag_indirect_inlining && !flag_wpa)
+ {
+ ipa_register_cgraph_hooks ();
+ if (!flag_ipa_cp)
+ ipa_prop_read_jump_functions ();
+ }
+ function_insertion_hook_holder =
+ cgraph_add_function_insertion_hook (&add_new_function, NULL);
+}
+
+/* Write inline summary for node in SET.
+ Jump functions are shared among ipa-cp and inliner, so when ipa-cp is
+ active, we don't need to write them twice. */
+
+static void
+inline_write_summary (cgraph_node_set set)
+{
+ if (flag_indirect_inlining && !flag_ipa_cp)
+ ipa_prop_write_jump_functions (set);
+}
+
+struct ipa_opt_pass_d pass_ipa_inline =
{
{
IPA_PASS,
0, /* static_pass_number */
TV_INLINE_HEURISTICS, /* tv_id */
0, /* properties_required */
- PROP_cfg, /* properties_provided */
+ 0, /* properties_provided */
0, /* properties_destroyed */
TODO_remove_functions, /* todo_flags_finish */
TODO_dump_cgraph | TODO_dump_func
| TODO_remove_functions /* todo_flags_finish */
},
inline_generate_summary, /* generate_summary */
- NULL, /* write_summary */
- NULL, /* read_summary */
+ inline_write_summary, /* write_summary */
+ inline_read_summary, /* read_summary */
NULL, /* function_read_summary */
+ NULL, /* stmt_fixup */
0, /* TODOs */
inline_transform, /* function_transform */
NULL, /* variable_transform */