[Pythonmac-SIG] Pystone numbers for different Macs...

[Jack Jansen]

On 20-Jan-2008, at 20:53 , skip at pobox.com wrote:

>    Daniel> I am assuming the GIL is limiting threading and therefore  
> I am
>    Daniel> really running on one or two cores--hence the tangible
>    Daniel> improvement is just CPU speed: from 2.33 GHz to 3.0 GHz  
> and a
>    Daniel> bit of the memory bandwidth increase as well.
>
> The GIL doesn't enter into things here.  The pystones benchmark isn't
> multithreaded so even if Python was free-threaded the pystones  
> benchmark
> wouldn't benefit from it.


Hmm, you're right. And there aren't any magic threads either (happens  
far too often nowadays, grmpf), I just checked that with gdb.

So: any other speculations as to why 2.66Ghz->3.0Ghz gives only a 1%  
increase in pystones?
I can't physically reach my Mac Pro for another week, but maybe  
someone else could try disabling three cores? If that increases the  
pystone number (in stead of decreasing it) this could point to a  
processor affinity problem in MacOSX.
--
Jack Jansen, <Jack.Jansen at cwi.nl>, http://www.cwi.nl/~jack
If I can't dance I don't want to be part of your revolution -- Emma  
Goldman