[squeak-dev] Re: Performance (Re: Teleplace Cog VMs are now available)

Hilaire Fernandes hilaire.fernandes at gmail.com
Mon Jun 21 15:41:01 UTC 2010


...and Thanks a lot to share it.


o 0    o 0  o 0    o 0  o 0    o 0
|o  | |  o| |o  | |  o| |o  | |  o|
| o | | o | | o | | o | | o | | o |
|0  | |O  | |0  | |O  | |0  | |O  |
|  0| |  0| |  0| |  0| |  0| |  0|
|O  | |o  | |O  | |o  | |O  | |o  |
  \ /   \ /   \ /   \ /   \ /   \ /
   |     |     |     |     |     |
   |     |     |     |     |     |
   |     |     |     |     |     |
   |     |     |     |     |     |
  ---   ---   ---   ---   ---   ---


Hilaire

Hilaire Fernandes a écrit :
> Andreas Raab a écrit :
> 
>> The latter. You should expect a 2-3x performance improvement in pretty 
>> much any kind of code (more towards 2x when running primitive and I/O 
>> bound stuff; more torwards 3x when running "pure" Smalltalk code).
> 
> 
> I tested it with a DrGeoII programmed interactive sketch. The 
> instantiation time of a recursive morph canvas (about 320 morphs) was 
> boosted by a factor of ~300%:
> 
> [Carre new] timeToRun
> 
> CogVM: 750
> SqueakVM: 2200
> 
> 
> I seem to have an issue in the new image with the method 
> Point>>onLineFrom:to:within:
> 
> Alway return false in some circumstance. Need to find more.
> 
> Hilaire
> 
> 
> 




More information about the Squeak-dev mailing list