On 02/17/2015 10:03 PM, Jan Hubicka wrote:
Hi,
this patch should chase away the expensive thunks and aliases walks from most
of analysis code. I think only real use left is local_p predicate that needs to
stay because i386 expect local flag to match between caller and callee when
expanding assembler thunk. I at least optimized it by first moving the walk to
be conditional for nonlocal functions only and then reorganizing
call_for_symbol_thunks_and_aliases to first inspect aliases (that is cheap) and
only then work on thunks. Most likely this will find the non-local thunk/alias
faster. Other cases was leftovers from the conversion of thunks from aliases
to functions.
I also noticed a bug in ipa-profile that does not disable all the
transofrms with !ipa_profile_flag used on OPTIMIZTION_NODE and fixed it.
Bootstrapped/regtested x86_64-linux, comitted. I would be interested to
know if the call_for_symbol_thunks_and_aliases is now off your oprofiles
(sorry, easier to type than perf-profiles)
Honza
* ipa-visibility.c (function_and_variable_visibility): Only
check locality if node is not already local.
* ipa-inline.c (want_inline_function_to_all_callers_p): Use
call_for_symbol_and_aliases instead of
call_for_symbol_thunks_and_aliases.
(ipa_inline): Likewise.
* cgraph.c (cgraph_node::call_for_symbol_thunks_and_aliases):
first walk aliases.
* ipa.c (symbol_table::remove_unreachable_nodes): Use
call_for_symbol_and_aliases.
* ipa-profile.c (ipa_propagate_frequency_data): Add function_symbol.
(ipa_propagate_frequency_1): Use it; use opt_for_fn
(ipa_propagate_frequency): Update.
(ipa_profile): Add opt_for_fn gueards.
Index: ipa-visibility.c
===================================================================
--- ipa-visibility.c (revision 220741)
+++ ipa-visibility.c (working copy)
@@ -595,7 +595,8 @@ function_and_variable_visibility (bool w
}
FOR_EACH_DEFINED_FUNCTION (node)
{
- node->local.local |= node->local_p ();
+ if (!node->local.local)
+ node->local.local |= node->local_p ();
/* If we know that function can not be overwritten by a different
semantics
and moreover its section can not be discarded, replace all direct calls
Index: ipa-inline.c
===================================================================
--- ipa-inline.c (revision 220741)
+++ ipa-inline.c (working copy)
@@ -975,14 +975,14 @@ want_inline_function_to_all_callers_p (s
if (node->global.inlined_to)
return false;
/* Does it have callers? */
- if (!node->call_for_symbol_thunks_and_aliases (has_caller_p, NULL, true))
+ if (!node->call_for_symbol_and_aliases (has_caller_p, NULL, true))
return false;
/* Inlining into all callers would increase size? */
if (estimate_growth (node) > 0)
return false;
/* All inlines must be possible. */
- if (node->call_for_symbol_thunks_and_aliases (check_callers, &has_hot_call,
- true))
+ if (node->call_for_symbol_and_aliases (check_callers, &has_hot_call,
+ true))
return false;
if (!cold && !has_hot_call)
return false;
@@ -2359,9 +2359,9 @@ ipa_inline (void)
if (want_inline_function_to_all_callers_p (node, cold))
{
int num_calls = 0;
- node->call_for_symbol_thunks_and_aliases (sum_callers, &num_calls,
- true);
- while (node->call_for_symbol_thunks_and_aliases
+ node->call_for_symbol_and_aliases (sum_callers, &num_calls,
+ true);
+ while (node->call_for_symbol_and_aliases
(inline_to_all_callers, &num_calls, true))
;
remove_functions = true;
Index: cgraph.c
===================================================================
--- cgraph.c (revision 220741)
+++ cgraph.c (working copy)
@@ -2191,6 +2191,16 @@ cgraph_node::call_for_symbol_thunks_and_
if (callback (this, data))
return true;
+ FOR_EACH_ALIAS (this, ref)
+ {
+ cgraph_node *alias = dyn_cast <cgraph_node *> (ref->referring);
+ if (include_overwritable
+ || alias->get_availability () > AVAIL_INTERPOSABLE)
+ if (alias->call_for_symbol_thunks_and_aliases (callback, data,
+ include_overwritable,
+ exclude_virtual_thunks))
+ return true;
+ }
for (e = callers; e; e = e->next_caller)
if (e->caller->thunk.thunk_p
&& (include_overwritable
@@ -2202,16 +2212,6 @@ cgraph_node::call_for_symbol_thunks_and_
exclude_virtual_thunks))
return true;
- FOR_EACH_ALIAS (this, ref)
- {
- cgraph_node *alias = dyn_cast <cgraph_node *> (ref->referring);
- if (include_overwritable
- || alias->get_availability () > AVAIL_INTERPOSABLE)
- if (alias->call_for_symbol_thunks_and_aliases (callback, data,
- include_overwritable,
- exclude_virtual_thunks))
- return true;
- }
return false;
}
Index: ipa.c
===================================================================
--- ipa.c (revision 220741)
+++ ipa.c (working copy)
@@ -661,7 +661,7 @@ symbol_table::remove_unreachable_nodes (
if (node->address_taken
&& !node->used_from_other_partition)
{
- if (!node->call_for_symbol_thunks_and_aliases
+ if (!node->call_for_symbol_and_aliases
(has_addr_references_p, NULL, true)
&& (!node->instrumentation_clone
|| !node->instrumented_version
Index: ipa-profile.c
===================================================================
--- ipa-profile.c (revision 220741)
+++ ipa-profile.c (working copy)
@@ -322,6 +322,7 @@ ipa_profile_read_summary (void)
struct ipa_propagate_frequency_data
{
+ cgraph_node *function_symbol;
bool maybe_unlikely_executed;
bool maybe_executed_once;
bool only_called_at_startup;
@@ -342,7 +343,7 @@ ipa_propagate_frequency_1 (struct cgraph
|| d->only_called_at_startup || d->only_called_at_exit);
edge = edge->next_caller)
{
- if (edge->caller != node)
+ if (edge->caller != d->function_symbol)
{
d->only_called_at_startup &= edge->caller->only_called_at_startup;
/* It makes sense to put main() together with the static constructors.
@@ -358,7 +359,11 @@ ipa_propagate_frequency_1 (struct cgraph
errors can make us to push function into unlikely section even when
it is executed by the train run. Transfer the function only if all
callers are unlikely executed. */
- if (profile_info && flag_branch_probabilities
+ if (profile_info
+ && opt_for_fn (d->function_symbol->decl, flag_branch_probabilities)
+ /* Thunks are not profiled. This is more or less implementation
+ bug. */
+ && !d->function_symbol->thunk.thunk_p
&& (edge->caller->frequency != NODE_FREQUENCY_UNLIKELY_EXECUTED
|| (edge->caller->global.inlined_to
&& edge->caller->global.inlined_to->frequency
@@ -418,7 +423,7 @@ contains_hot_call_p (struct cgraph_node
bool
ipa_propagate_frequency (struct cgraph_node *node)
{
- struct ipa_propagate_frequency_data d = {true, true, true, true};
+ struct ipa_propagate_frequency_data d = {node, true, true, true, true};
bool changed = false;
/* We can not propagate anything useful about externally visible functions
@@ -432,8 +437,8 @@ ipa_propagate_frequency (struct cgraph_n
if (dump_file && (dump_flags & TDF_DETAILS))
fprintf (dump_file, "Processing frequency %s\n", node->name ());
- node->call_for_symbol_thunks_and_aliases (ipa_propagate_frequency_1, &d,
- true);
+ node->call_for_symbol_and_aliases (ipa_propagate_frequency_1, &d,
+ true);
if ((d.only_called_at_startup && !d.only_called_at_exit)
&& !node->only_called_at_startup)
@@ -597,6 +602,9 @@ ipa_profile (void)
{
bool update = false;
+ if (!opt_for_fn (n->decl, flag_ipa_profile))
+ continue;
+
for (e = n->indirect_calls; e; e = e->next_callee)
{
if (n->count)
@@ -697,7 +705,9 @@ ipa_profile (void)
order_pos = ipa_reverse_postorder (order);
for (i = order_pos - 1; i >= 0; i--)
{
- if (order[i]->local.local && ipa_propagate_frequency (order[i]))
+ if (order[i]->local.local
+ && opt_for_fn (order[i]->decl, flag_ipa_profile)
+ && ipa_propagate_frequency (order[i]))
{
for (e = order[i]->callees; e; e = e->next_callee)
if (e->callee->local.local && !e->callee->aux)
@@ -714,7 +724,9 @@ ipa_profile (void)
something_changed = false;
for (i = order_pos - 1; i >= 0; i--)
{
- if (order[i]->aux && ipa_propagate_frequency (order[i]))
+ if (order[i]->aux
+ && opt_for_fn (order[i]->decl, flag_ipa_profile)
+ && ipa_propagate_frequency (order[i]))
{
for (e = order[i]->callees; e; e = e->next_callee)
if (e->callee->local.local && !e->callee->aux)
Hi.
There's perf report and -ftime report of WPA phase.
Martin
Execution times (seconds)
phase setup : 0.00 ( 0%) usr 0.00 ( 0%) sys 0.00 ( 0%) wall
1977 kB ( 0%) ggc
phase opt and generate : 171.18 (65%) usr 2.29 (47%) sys 173.40 (65%) wall
2682609 kB (13%) ggc
phase stream in : 92.09 (35%) usr 2.55 (53%) sys 94.61 (35%)
wall18738048 kB (87%) ggc
callgraph optimization : 0.72 ( 0%) usr 0.00 ( 0%) sys 0.73 ( 0%) wall
16 kB ( 0%) ggc
ipa dead code removal : 5.12 ( 2%) usr 0.05 ( 1%) sys 5.07 ( 2%) wall
0 kB ( 0%) ggc
ipa virtual call target : 2.93 ( 1%) usr 0.03 ( 1%) sys 3.02 ( 1%) wall
0 kB ( 0%) ggc
ipa devirtualization : 0.26 ( 0%) usr 0.01 ( 0%) sys 0.34 ( 0%) wall
32646 kB ( 0%) ggc
ipa cp : 4.29 ( 2%) usr 0.48 (10%) sys 4.86 ( 2%) wall
851380 kB ( 4%) ggc
ipa inlining heuristics : 122.37 (46%) usr 0.42 ( 9%) sys 122.72 (46%) wall
807997 kB ( 4%) ggc
ipa comdats : 0.53 ( 0%) usr 0.00 ( 0%) sys 0.53 ( 0%) wall
0 kB ( 0%) ggc
ipa lto gimple in : 5.16 ( 2%) usr 1.09 (23%) sys 6.64 ( 2%) wall
1370302 kB ( 6%) ggc
ipa lto decl in : 79.11 (30%) usr 1.58 (33%) sys 80.64 (30%)
wall16957092 kB (79%) ggc
ipa lto constructors in : 0.37 ( 0%) usr 0.06 ( 1%) sys 0.37 ( 0%) wall
22897 kB ( 0%) ggc
ipa lto cgraph I/O : 1.44 ( 1%) usr 0.24 ( 5%) sys 1.69 ( 1%) wall
901960 kB ( 4%) ggc
ipa lto decl merge : 3.27 ( 1%) usr 0.01 ( 0%) sys 3.26 ( 1%) wall
16383 kB ( 0%) ggc
ipa lto cgraph merge : 4.63 ( 2%) usr 0.04 ( 1%) sys 4.68 ( 2%) wall
20432 kB ( 0%) ggc
whopr wpa : 1.70 ( 1%) usr 0.00 ( 0%) sys 1.71 ( 1%) wall
2 kB ( 0%) ggc
whopr partitioning : 4.72 ( 2%) usr 0.02 ( 0%) sys 4.73 ( 2%) wall
7796 kB ( 0%) ggc
ipa reference : 2.70 ( 1%) usr 0.10 ( 2%) sys 2.80 ( 1%) wall
0 kB ( 0%) ggc
ipa profile : 0.53 ( 0%) usr 0.03 ( 1%) sys 0.58 ( 0%) wall
0 kB ( 0%) ggc
ipa pure const : 3.13 ( 1%) usr 0.09 ( 2%) sys 3.21 ( 1%) wall
0 kB ( 0%) ggc
ipa icf : 16.96 ( 6%) usr 0.17 ( 4%) sys 17.06 ( 6%) wall
3087 kB ( 0%) ggc
inline parameters : 0.01 ( 0%) usr 0.00 ( 0%) sys 0.00 ( 0%) wall
0 kB ( 0%) ggc
tree SSA rewrite : 0.39 ( 0%) usr 0.05 ( 1%) sys 0.27 ( 0%) wall
51205 kB ( 0%) ggc
tree SSA other : 0.00 ( 0%) usr 0.00 ( 0%) sys 0.01 ( 0%) wall
0 kB ( 0%) ggc
tree SSA incremental : 0.50 ( 0%) usr 0.08 ( 2%) sys 0.50 ( 0%) wall
33556 kB ( 0%) ggc
tree operand scan : 0.45 ( 0%) usr 0.11 ( 2%) sys 0.47 ( 0%) wall
343892 kB ( 2%) ggc
dominance frontiers : 0.05 ( 0%) usr 0.00 ( 0%) sys 0.04 ( 0%) wall
0 kB ( 0%) ggc
dominance computation : 0.51 ( 0%) usr 0.08 ( 2%) sys 0.58 ( 0%) wall
0 kB ( 0%) ggc
varconst : 0.02 ( 0%) usr 0.06 ( 1%) sys 0.05 ( 0%) wall
0 kB ( 0%) ggc
loop fini : 0.12 ( 0%) usr 0.00 ( 0%) sys 0.13 ( 0%) wall
0 kB ( 0%) ggc
unaccounted todo : 1.19 ( 0%) usr 0.00 ( 0%) sys 1.15 ( 0%) wall
0 kB ( 0%) ggc
TOTAL : 263.27 4.84 268.01
21422636 kB
[ perf record: Woken up 254 times to write data ]
[ perf record: Captured and wrote 63.481 MB perf.data (~2773530 samples) ]
marxin@marxinbox:~/Programming/chromium/src/out/Release> perf report --stdio |
sed 's/\ *$//' | head -n50# To display the perf.data header info, please use
--header/--header-only options.
#
# Samples: 1M of event 'cycles'
# Event count (approx.): 945739511218
#
# Overhead Command Shared Object
# ........ ........ .................
..................................................................................................................................................................................................................................................................................................
#
19.88% lto1-wpa lto1 [.] nonremovable_p(cgraph_node*, void*)
9.17% lto1-wpa lto1 [.]
cgraph_node::used_from_object_file_p_worker(cgraph_node*, void*)
7.93% lto1-wpa lto1 [.]
cgraph_node::call_for_symbol_and_aliases_1(bool (*)(cgraph_node*, void*),
void*, bool)
6.37% lto1-wpa lto1 [.] inflate_fast
2.23% lto1-wpa lto1 [.] compare_tree_sccs_1(tree_node*,
tree_node*, tree_node***)
2.14% lto1-wpa lto1 [.]
streamer_read_uhwi(lto_input_block*)
1.96% lto1-wpa lto1 [.] ht_lookup_with_hash(ht*, unsigned
char const*, unsigned long, unsigned int, ht_lookup_option)
1.83% lto1-wpa lto1 [.] unify_scc(streamer_tree_cache_d*,
unsigned int, unsigned int, unsigned int, unsigned int)
1.61% lto1-wpa lto1 [.]
streamer_read_tree_bitfields(lto_input_block*, data_in*, tree_node*)
1.23% lto1-wpa lto1 [.]
lto_cgraph_replace_node(cgraph_node*, cgraph_node*)
1.21% lto1-wpa libc-2.19.so [.] msort_with_tmp.part.0
1.19% lto1-wpa lto1 [.]
streamer_get_pickled_tree(lto_input_block*, data_in*)
1.14% lto1-wpa lto1 [.]
symbol_table::remove_unreachable_nodes(_IO_FILE*)
1.08% lto1-wpa libc-2.19.so [.] _int_malloc
1.02% lto1-wpa lto1 [.]
ipa_icf::sem_variable::equals(tree_node*, tree_node*)
0.96% lto1-wpa lto1 [.] lto_input_tree_1(lto_input_block*,
data_in*, LTO_tags, unsigned int)
0.84% lto1-wpa lto1 [.] inflate
0.74% lto1-wpa lto1 [.] adler32
0.71% lto1-wpa lto1 [.] lto_input_tree(lto_input_block*,
data_in*)
0.68% lto1-wpa lto1 [.]
cgraph_node::call_for_symbol_thunks_and_aliases(bool (*)(cgraph_node*, void*),
void*, bool, bool)
0.66% lto1-wpa lto1 [.]
streamer_read_tree_body(lto_input_block*, data_in*, tree_node*)
0.64% lto1-wpa lto1 [.]
estimate_calls_size_and_time(cgraph_node*, int*, int*, int*, int*, unsigned
int, vec<tree_node*, va_heap, vl_ptr>, vec<ipa_polymorphic_call_context,
va_heap, vl_ptr>, vec<ipa_agg_jump_function*, va_heap, vl_ptr>) [clone
.isra.129]
0.63% lto1-wpa lto1 [.] lto_input_location(bitpack_d*,
data_in*)
