Stockfish mcts sugar chess versions1/27/2024 ![]() ![]() ![]() Several algorithms and approaches Footnote 1 regarding parallelization of chess playing have been proposed. The typical algorithm for tree search in chess has been alpha-beta search. Some approaches have been proposed such as the Markovian interpretation for assessment of play by various players from various eras to be able to compare strengths of play. Performance of chess players, both human and engines, that play against each other is typically assessed using the Elo rating system. This is compared to both scalability and playing strength on server type Intel Xeon CPUs. We investigate performance of parallel chess game playing in the strong Stockfish engine, especially on the latest Intel Xeon Phi x200 processor which features upgraded internal mesh based architecture, MCDRAM memory and out of order execution. It is becoming very important to assess which computing devices perform best for particular classes of applications, especially when gains from increasing the number of threads are not obvious. The top system is based on Sunway manycore processors, the second is a hybrid multicore Intel Xeon + Intel Xeon Phi coprocessor based system and the third a hybrid multicore Intel Xeon + NVIDIA P100 GPUs. This is especially visible in top HPC systems on the TOP500 list. For the past several years, growth in performance of computing devices has been possible mainly through increasing the number of cores, apart from other improvements such as cache organization and size, much less through increase in processor clock speed. ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |