Changes

Jump to: navigation, search

Zeta

224 bytes added, 1 July
Chess Engine
Zeta is written in [[C]] (host) and [[OpenCL]] (device). The host handles the IO, but all chess related computations are done via OpenCL (run-time-compilation) on the device.
Zeta v099 is a port of [[Zeta Dva]] to OpenCL, with parallel [[Alpha-Beta]] search, therefore 64 gpu-threads are coupled to one worker, used to work on the same node in parallel during move generation, move picking selection and evaluation in parallel.
Zeta v097 and v098 were designed to run thousands of independent [[Thread|threads]] on a [[GPU]], therefore they store the expanded game tree via an parallel [[Best-First Minimax Search]] search in [[Memory|memory]].
* [http://www.talkchess.com/forum/viewtopic.php?t=44165 Help with Best-First Select-Formula] by [[Srdja Matovic]], [[CCC]], June 23, 2012
* [http://www.talkchess.com/forum/viewtopic.php?t=46974 Kogge Stone, Vector Based] by [[Srdja Matovic]], [[CCC]], January 22, 2013 » [[Kogge-Stone Algorithm]] <ref>[https://en.wikipedia.org/wiki/Parallel_Thread_Execution Parallel Thread Execution from Wikipedia]</ref> <ref>NVIDIA Compute PTX: Parallel Thread Execution, ISA Version 1.4, March 31, 2009, [https://www.nvidia.com/content/CUDA-ptx_isa_1.4.pdf pdf]</ref>
* [http://www.talkchess.com/forum/viewtopic.php?t=60386 GPU chess update, local memory...] by [[Srdja Matovic]], [[CCC]], June 06, 2016
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=72684 RMO - Randomized Move Order - yet another Lazy SMP derivate] by [[Srdja Matovic]], [[CCC]], December 30, 2019 » [[Lazy SMP]]
* [https://gitlab.com/smatovic/Zeta GitLab - smatovic/Zeta: Experimental chess engine written in OpenCL]
* [https://zeta-chess.app26.de/ Zeta Chess blog]
* [https://zeta-chess.app26.de/post/zeta-milestones/ Zeta - Milestones]
==Misc==
446
edits

Navigation menu