Hi,
this patch fixes profile updates while cloning. When new clone is produced
its global profile is subtracted from the original function. If the original
function profile drops to 0 we want to switch from global profiles to global0
profiles which is implemented by combine_with_ipa_count_within.
However this is done on all edges independnetly and it may happen that we end
up combining global and globa0 profiles in one functions which is not a good
idea.
This implements profile_count::combine_with_ipa_count_within which is able
to take into account that the counter is inside function with a given count.
Bootstrapped/regtested x86_64-linux, comitted.
Honza
* profile-count.h (profile_count::combine_with_ipa_count_within):
Declare.
* profile-count.c (profile_count::combine_with_ipa_count_within):
New.
* cgraphclones.c (cgraph_edge::clone, cgraph_node::create_clone): Use
it.
Index: profile-count.h
===================================================================
--- profile-count.h (revision 278809)
+++ profile-count.h (working copy)
@@ -1194,6 +1215,10 @@ public:
global0. */
profile_count combine_with_ipa_count (profile_count ipa);
+ /* Same as combine_with_ipa_count but inside function with count IPA2. */
+ profile_count combine_with_ipa_count_within
+ (profile_count ipa, profile_count ipa2);
+
/* The profiling runtime uses gcov_type, which is usually 64bit integer.
Conversions back and forth are used to read the coverage and get it
into internal representation. */
Index: profile-count.c
===================================================================
--- profile-count.c (revision 278809)
+++ profile-count.c (working copy)
@@ -383,6 +388,23 @@ profile_count::combine_with_ipa_count (p
return this->global0adjusted ();
}
+/* Sae as profile_count::combine_with_ipa_count but within function with count
+ IPA2. */
+profile_count
+profile_count::combine_with_ipa_count_within (profile_count ipa,
+ profile_count ipa2)
+{
+ profile_count ret;
+ if (!initialized_p ())
+ return *this;
+ if (ipa2.ipa () == ipa2 && ipa.initialized_p ())
+ ret = ipa;
+ else
+ ret = combine_with_ipa_count (ipa);
+ gcc_checking_assert (ret.compatible_p (ipa2));
+ return ret;
+}
+
/* The profiling runtime uses gcov_type, which is usually 64bit integer.
Conversions back and forth are used to read the coverage and get it
into internal representation. */
Index: cgraphclones.c
===================================================================
--- cgraphclones.c (revision 278809)
+++ cgraphclones.c (working copy)
@@ -136,8 +141,9 @@ cgraph_edge::clone (cgraph_node *n, gcal
/* Update IPA profile. Local profiles need no updating in original. */
if (update_original)
- count = count.combine_with_ipa_count (count.ipa ()
- - new_edge->count.ipa ());
+ count = count.combine_with_ipa_count_within (count.ipa ()
+ - new_edge->count.ipa (),
+ caller->count);
symtab->call_edge_duplication_hooks (this, new_edge);
return new_edge;
}
@@ -341,7 +349,14 @@ cgraph_node::create_clone (tree new_decl
/* Update IPA profile. Local profiles need no updating in original. */
if (update_original)
- count = count.combine_with_ipa_count (count.ipa () - prof_count.ipa ());
+ {
+ if (inlined_to)
+ count = count.combine_with_ipa_count_within (count.ipa ()
+ - prof_count.ipa (),
+ inlined_to->count);
+ else
+ count = count.combine_with_ipa_count (count.ipa () - prof_count.ipa
());
+ }
new_node->decl = new_decl;
new_node->register_symbol ();
new_node->origin = origin;
