Re: [Bug-gnubg] profiler output (was: For Mac OS X users)

[Jim Segrave]

On Sun 13 Apr 2003 (12:56 +1200), Joseph Heled wrote:
> 
> Seeing this, I made an attempt to repair the incremental NN evaluation. 
> Please let me know if you encounter problems. Will be interesting to see 
>   a profiler run on the new code.
> 
> -Joseph

Ok - here's an analysis of the same match with the same settings and
today's (Sunday 13 April) code. 

A minor point - the previous posting may have been a profiler output of gnubg
compiled with gcc 2.95, as I'm not sure I'd set my CC environment
variable at the time. This one is definitely gcc 3.2.


> Jim Segrave wrote:
> > On Thu 10 Apr 2003 (17:06 +0200), Jim Segrave wrote:
> > 
> >>On Wed 09 Apr 2003 (14:02 +0000), Joern Thyssen wrote:
> >>
> >>>On Wed, Apr 09, 2003 at 03:32:45PM +0200, Olivier Baur wrote
> >>>
> >>>>Le mercredi, 9 avr 2003, à 10:09 Europe/Paris, Øystein O Johansen a 
> >>>>écrit :
> >>>>
> >>>>
> >>>>>Fantastic!
> >>>>>How is the speed? How many static evaluations can you get each sec?
> >>>>>(Analyse->Evaluation Speed->Calibrate)
> >>>>>I get about 17000 on my 2 GHz Intel XEON, and about 23000 on my 2.53 
> >>>>>GHz P4
> >>>>>
> >>>>>-Øystein
> >>>>
> >>>>On my PowerBook G4 768 MHz (no L3 cache :-)), I get about 9000 static 
> >>>>evals/sec. Quite poor compared to the numbers you give. I'm waiting for 
> >>>>someone to test it on a desktop G4 :-)
> >>>
> >>>I get 11k evals/sec on a 1GHz laptop. 
> >>>
> >>>I'm not very familiar with the G4 architecture, so I don't know what a
> >>>768MHz roughly corresponds to in Intel MHz.
> >>>
> >>>Jim once did some profiling. I can't remember how much time is spend in
> >>>NeuralNetEvaluate versus CalculateInputs?!
> >>
> >>I'll try to set up a profiled version and get statistics on a current
> >>one this weekend.
> > 
> > 
> > OK - attached is a profiler output of gnubg analyzing a 7 game match
> > of about 370 moves (the same one I profiled before). The analysis is a
> > 2 ply with very broad move filters. Compiled under FreeBSD with gcc
> > 3.2, running on a Dell L400 laptop
> > 
> > CPU: Pentium III/Pentium III Xeon/Celeron (696.97-MHz 686-class CPU)
> > 
> > which gives about 7700 evals/sec.
> > 
> > gnubg source is from cvs 12 April. 

-- 
Jim Segrave           address@hidden

mon.out.gz
Description: application/gunzip