diff options
| author | 卜部昌平 <shyouhei@ruby-lang.org> | 2019-09-18 17:18:48 +0900 |
|---|---|---|
| committer | 卜部昌平 <shyouhei@ruby-lang.org> | 2019-09-19 15:18:10 +0900 |
| commit | d74fa8e55ce64904f2f99dfef4cbdff94e290672 (patch) | |
| tree | 7bfd074fe668f719defa81a3b2fb7b9e291b3aa9 /internal.h | |
| parent | 9fb9f2d318520ddfdbe73809eea85847550b42ae (diff) | |
| download | ruby-d74fa8e55ce64904f2f99dfef4cbdff94e290672.tar.gz | |
reuse cc->call
I noticed that in case of cache misshit, re-calculated cc->me can
be the same method entry than the pevious one. That is an okay
situation but can't we partially reuse the cache, because cc->call
should still be valid then?
One thing that has to be special-cased is when the method entry
gets amended by some refinements. That happens behind-the-scene
of call cache mechanism. We have to check if cc->me->def points to
the previously saved one.
Calculating -------------------------------------
trunk ours
vm2_poly_same_method 1.534M 2.025M i/s - 6.000M times in 3.910203s 2.962752s
Comparison:
vm2_poly_same_method
ours: 2025143.9 i/s
trunk: 1534447.2 i/s - 1.32x slower
Diffstat (limited to 'internal.h')
| -rw-r--r-- | internal.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/internal.h b/internal.h index 3dbe9ad38e..2e8d23b085 100644 --- a/internal.h +++ b/internal.h @@ -2328,6 +2328,7 @@ enum method_missing_reason { MISSING_NONE = 0x40 }; struct rb_callable_method_entry_struct; +struct rb_method_definition_struct; struct rb_execution_context_struct; struct rb_control_frame_struct; struct rb_calling_info; @@ -2339,6 +2340,7 @@ struct rb_call_cache { /* inline cache: values */ const struct rb_callable_method_entry_struct *me; + const struct rb_method_definition_struct *def; VALUE (*call)(struct rb_execution_context_struct *ec, struct rb_control_frame_struct *cfp, |