That chessbrain is a commercial attempt of a few guys looking for
money, not an attempt to really search parallel in a decent manner.
This is why they kept their logfiles of course all 'secret'.
I'm not the only one who offered my help to them, without payment,
but that wasn't accepted at all.
In itself weird, they have little experience in parallellizing game
tree search at many processors.
The software they use is getting used in an embarrassingly parallel
manner.
So their speedup is real ugly bad of course.
A 8 core will easily totally outcalculate chessbrain with respect to
search depth.
Seems to me the project died, bad shame in itself.
It is very complicated to get something to work that can play
realtime. Long term analysis projects are more viable
and real interesting for several reasons. Yet what you see that most
of those projects do is keep the parallel search frame
source code secret. Just publish an article claiming victory, without
really data to statistically significant back that up.
That means in short, that no one can learn from them, nor objectively
draw conclusoins.
A team that isn't doing supreme effort in getting a good speedup will
of course not succeed.
Vincent
On Sep 28, 2008, at 2:15 PM, Claus Reinke wrote:
If you're looking for spare processors, how about a "[EMAIL PROTECTED]"
program for Go?-)
It appears that the Chess community has had such a project already:
ChessBrain: a Linux-Based Distributed Computing Experiment
http://www.linuxjournal.com/article/6929
ChessBrain II - A Hierarchical Infrastructure for Distributed
Inhomogeneous Speed-Critical Computation
IEEE CIG06, Reno NV, May 2006 (6 pages)
(IEEE Symposium on Computational Intelligence and Games)
http://chessbrain.net/docs/chessbrainII.pdf
old project site:
http://chessbrain.net/
From the chessbrainII paper, it seems they considered Go, but
before the recent developments that made parallel processing
promising. The papers might also be interesting for their discussion
of parallel tree search and communication issues.
Claus
Local versions of the top programs could offer to connect to their
main incarnation's games,
explaining internal state ("it is sure it will win", "it thinks
that group is dead", ..) in
exchange for borrowing processing resources. Or, instead of doing
this on a per-program basis,
there could be a standard protocol for donating processing power
from machines whose users view a
game online.
That way, the more kibitzes a game attracts, the better the computer
player plays; and if the game cannot hold an audience, the computer
player might start to seem distracted, losing all those borrowed
processors;-)
Mogo might even find some related research at INRIA ([EMAIL PROTECTED]
style (desktop) grid computing, ..), so perhaps there's scope for
collaboration there?
Claus
Q: why do you search for extra-terrestrial intelligence?
A: we've exhausted the local search space.
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/