General

Profile

Yura Sokolov

Issues

Activity

07/13/2016

11:04 AM Ruby trunk Feature #12142: Hash tables with open addressing
Good day, everyone.
I've updated my version of st.c and hashing patch.
Main difference in st implementation from ...

04/30/2016

03:06 PM Ruby trunk Feature #12142: Hash tables with open addressing
I've put result for each combination: with/without jemalloc * old/new hash. (2*2=4)
There is two ways to get more ...
05:37 AM Ruby trunk Feature #12142: Hash tables with open addressing
And still, why don't you measure with realworld application too?
It is relatively easy to setup Redmine http://www...
05:30 AM Ruby trunk Feature #12142: Hash tables with open addressing
You forgot to include source for added benchmark files into diff: bm_hash_small{2,4,8}, bm_bighash, bm_hash_long

04/11/2016

11:31 AM Ruby trunk Feature #12236: Introduce `mmap` managed heap
> I believe we don't have any drawback with 256MB virtual memory allocation. (but it can depend on OSs)
It may dep...

04/01/2016

07:13 AM Ruby trunk Feature #12142: Hash tables with open addressing
> average improvement on MRI hash benchmarks is close to 40% on Intel Haswell and >55% on ARMv7
What about realwor...

03/17/2016

10:47 AM Ruby trunk Feature #12142: Hash tables with open addressing
I strongly prefer configure option with default to 32bit.
99% should not pay for 1% ability.
32bit version doesn'...

03/16/2016

05:36 PM Ruby trunk Feature #12180: switch id_table.c variant
In other words, big web applications are too big for global method cache, and too polymorphic for inline cache.
So g...
05:32 AM Ruby trunk Feature #12142: Hash tables with open addressing
Eric Wong wrote:
> vmakarov@redhat.com wrote:
> > * I also *changed the specialized hash function* (rb_num_hash_...
05:25 AM Ruby trunk Feature #12180: switch id_table.c variant
I just install Redmine - the same software that powers bugs.ruby-lang.org ,
then add several test issues, and bench ...

Also available in: Atom