Search found 643 matches

by smatovic
Thu Sep 22, 2011 1:27 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: LIFO stack based parallel processing?
Replies: 12
Views: 2783

LIFO stack based parallel processing?

Have some thoughts about a LIFO stack based parallel processing scheme,
so one thread gets one position from the stack and puts the generated childs back on the stack,

The point is that i dont have a clue how to handle the scores for such an process.

Does somebody have an idea or an hint?

--
Srdja
by smatovic
Wed Sep 21, 2011 7:44 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

Right, even without move ordering I am still surprise at the low speed... Maybe i should switch to newer hardware....the GTS250 is based on the the 8800 from 2006.... By the way, nice work! I am sure this was no easy task to program. thx, coding on such an architecture is definitely a new experienc...
by smatovic
Wed Sep 21, 2011 6:50 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

Wait you use a bubble sort???
I also tried a buttom up heapsort, not much better.

--
Srdja
by smatovic
Wed Sep 21, 2011 6:48 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

What will the NPS be without move ordering?
about 100 000 nps.

--
Srdja
by smatovic
Wed Sep 21, 2011 6:27 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

Well, bear in mind the GTS250 is quite slow overall compared to a top gaming card, and is much like a Celeron compared to a Sandy Bridge quad. Yepp, the ATI 69xx series for example has x8 more processing elements per SIMD Unit but runs with half of clock rate, so a speedup of x4 could be possible. ...
by smatovic
Sun Sep 18, 2011 9:39 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

Hmm... this is quite slow, and as Intel's CEO said last week that Intel is going toward massively parallel CPUs I guess that GPUs will never catch up with CPUs. Yepp, i dont think that a GPU Chess Programm will compete with a professional CPU based programm, there are too much restrictions in codin...
by smatovic
Sun Sep 18, 2011 9:05 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Re: Zeta Open CL Chess - v0.918 - Developer Release

Wow, congrats, Srdja! Very Happy How fast is it? (average nps) Thanks :) one SIMD Unit with 128 threads makes 10 000 to 50 000 nps on my NV GTS250 with 16 SIMD Units on board, but it is a Prototype, no castle moves or en passant inside... a lot of improvements possible... I am just glad that AB Pru...
by smatovic
Sun Sep 18, 2011 8:27 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Zeta Open CL Chess - v0.918 - Developer Release
Replies: 14
Views: 1721

Zeta Open CL Chess - v0.918 - Developer Release

fyi:

Got AlphaBeta Pruning with Move Ordering running on one SIMD Unit of a GPU with 128 threads.

More Information:
http://zeta-chess.blogspot.com/

Source Code:
https://github.com/smatovic/Zeta/tree/zeta_nvidia_0918

--
Srdja
by smatovic
Sat Sep 17, 2011 7:45 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Breadth-first search: revisiting
Replies: 6
Views: 1433

Re: Breadth-first search: revisiting

Other interesting approaches I've come across combine randomized components to speed up search. Got really blown away by is the Nagging Search idea by Alberto Segre.
Interesting,
do you have already some kind of expirience with the Nagging Search?

--
Srdja
by smatovic
Tue Sep 13, 2011 9:01 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Breadth-first search: revisiting
Replies: 6
Views: 1433

Re: Breadth-first search: revisiting

> or use usual PVS as "quiescence" for breadth-first search.

hmm, a breadth-first search until RAM is full and then a depth first search, imo this could give new ideas to use the full capacity of the upcoming many-core processors.

--
Srdja