MCTS Playouts Parallelization with a MPPA Architecture - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

MCTS Playouts Parallelization with a MPPA Architecture

Résumé

We present a study of the use of a MultiPurpose Processor Array (MPPA) architecture for the parallelization of MCTS algorithms applied to the field of General Game Playing. We evaluate the constraints imposed by this architecture and show that the only feasible MCTS parallelization on MPPA is a leaf parallelization. We show that the MPPA provides good scalability when increasing the size of the communications which is useful when using synchronous communications to send large sets of game initial positions to be processed. We consider two approaches for the calculation of playouts: the distributed computing of a playout on each cluster and the calculation of several playouts per cluster; the second approach gives better results. Finally, we describe experiments concerning the thread management and present a surprising result: it is more efficient to create new threads than to synchronize permanent threads.
Fichier principal
Vignette du fichier
hufschmitt-2015-a.pdf (719.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02183609 , version 1 (15-07-2019)

Identifiants

  • HAL Id : hal-02183609 , version 1

Citer

Aline Hufschmitt, Jean Méhat, Jean-Noël Vittaut. MCTS Playouts Parallelization with a MPPA Architecture. 4th Workshop on General Intelligence in Game-Playing Agents, GIGA 2015, Held in Conjunction with the 24th International Conference on Artificial Intelligence, IJCAI 2015, Jul 2015, Buenos Aires, Argentina. ⟨hal-02183609⟩
33 Consultations
40 Téléchargements

Partager

Gmail Facebook X LinkedIn More