[Stackless] Re: Project
Christian Tismer
tismer at tismer.com
Sun Aug 24 06:08:45 CEST 2003
Mika Anttila wrote:
> Hi Christian,
>
> I tested latest code with testbench and it worked quite nicely.
> I will do some testing but overall from our point of view
> project has served its purpose. Thank You very much.
>
> There are few minor areas what could be enhanced like
> optimization (main tasklet initialization) and using just
> one interpreter ... but it can be done later if you are available
> to do this work.
Here is a test program which shows how badly the "call from outside"
performs today.
It's a shame...
D:\slpdev\src\2.2\src\Stackless\test>..\..\pcbuild\python taskspeed.py
2.2.3 Stackless 3.0 030821 (#28, Aug 24 2003, 06:03:14) [MSC 32 bit (Intel)]
10000000 frame switches took 3.87651 seconds, rate = 2579641/s
10000000 frame softswitches took 1.94712 seconds, rate = 5135795/s
10000000 cfunction calls took 2.07456 seconds, rate = 4820290/s
10000000 cframe softswitches took 0.46392 seconds, rate = 21555577/s
10000000 function calls took 4.92227 seconds, rate = 2031581/s
10000000 generator calls took 3.32308 seconds, rate = 3009252/s
10000000 cframe switches took 2.15792 seconds, rate = 4634097/s
10000000 cframe 100 words took 4.18344 seconds, rate = 2390380/s
10000000 cframe from outside took 41.19093 seconds, rate = 242771/s
The penalty per stack word is about 8.846 percent of raw switching.
Stack size of initial stub = 13
Stack size of frame tasklet = 56
Stack size of cframe tasklet = 34
ciao - chris
--
Christian Tismer :^) <mailto:tismer at tismer.com>
Mission Impossible 5oftware : Have a break! Take a ride on Python's
Johannes-Niemeyer-Weg 9a : *Starship* http://starship.python.net/
14109 Berlin : PGP key -> http://wwwkeys.pgp.net/
work +49 30 89 09 53 34 home +49 30 802 86 56 mobile +49 173 24 18 776
PGP 0x57F3BF04 9064 F4E1 D754 C2FF 1619 305B C09C 5A3B 57F3 BF04
whom do you want to sponsor today? http://www.stackless.com/
_______________________________________________
Stackless mailing list
Stackless at www.tismer.com
http://www.tismer.com/mailman/listinfo/stackless
More information about the Stackless
mailing list