diff options
author | 卜部昌平 <shyouhei@ruby-lang.org> | 2019-10-07 12:59:57 +0900 |
---|---|---|
committer | 卜部昌平 <shyouhei@ruby-lang.org> | 2019-11-07 17:41:30 +0900 |
commit | d45a013a1a3bcc860e6f7f303220b3297e2abdbc (patch) | |
tree | 9dd459d6b41542cdfcd75cede71a96e06981e3e0 /mjit_compile.c | |
parent | 3c252651e1ee28d015dbe1648dfdf0140232b733 (diff) |
extend rb_call_cache
Prior to this changeset, majority of inline cache mishits resulted
into the same method entry when rb_callable_method_entry() resolves
a method search. Let's not call the function at the first place on
such situations.
In doing so we extend the struct rb_call_cache from 44 bytes (in
case of 64 bit machine) to 64 bytes, and fill the gap with
secondary class serial(s). Call cache's class serials now behavies
as a LRU cache.
Calculating -------------------------------------
ours 2.7 2.6
vm2_poly_same_method 2.339M 1.744M 1.369M i/s - 6.000M times in 2.565086s 3.441329s 4.381386s
Comparison:
vm2_poly_same_method
ours: 2339103.0 i/s
2.7: 1743512.3 i/s - 1.34x slower
2.6: 1369429.8 i/s - 1.71x slower
Notes
Notes:
Merged: https://github.com/ruby/ruby/pull/2583
Diffstat (limited to 'mjit_compile.c')
-rw-r--r-- | mjit_compile.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/mjit_compile.c b/mjit_compile.c index 27ea836ef4..bf5143f6ed 100644 --- a/mjit_compile.c +++ b/mjit_compile.c @@ -87,7 +87,7 @@ has_valid_method_type(CALL_CACHE cc) { extern bool mjit_valid_class_serial_p(rb_serial_t class_serial); return GET_GLOBAL_METHOD_STATE() == cc->method_state - && mjit_valid_class_serial_p(cc->class_serial) && cc->me; + && mjit_valid_class_serial_p(cc->class_serial[0]) && cc->me; } // Returns true if iseq can use fastpath for setup, otherwise NULL. This becomes true in the same condition |