Parallel divide-and-evolve: experiments with OpenMP on a multicore machine

Multicore machines are becoming a standard way to speed up the system performance. After having instantiated the evolutionary metaheuristic DAEX with the forward search YAHSP planner, we investigate on the global parallelism approach, which exploits the intrinsic parallelism of the individual evaluation. This paper describes a parallel shared-memory version of the DAEYAHSP planning system using the OpenMP directive-based API. The parallelization scheme applies at a high level of abstraction and thus can be used by any evolutionary algorithm implemented with the Evolving Objects framework. The proof of concept is validated on a 48-core machine with two planning tasks extracted from the last international planning competition. Experiments show significant speedups with an increasing number of cores. This preliminary work opens an avenue for parallelizing any evolutionary algorithm developed with EO that would target multicore architectures.

[1]  Nicolas Lachiche,et al.  Coarse grain parallelization of evolutionary algorithms on GPGPU cards with EASEA , 2009, GECCO.

[2]  Marc Schoenauer,et al.  On the generality of parameter tuning in evolutionary planning , 2010, GECCO '10.

[3]  Patrik Haslum,et al.  Admissible Heuristics for Optimal Planning , 2000, AIPS.

[4]  Barbara M. Chapman,et al.  Towards a more efficient implementation of OpenMP for clusters via translation to global arrays , 2005, Parallel Comput..

[5]  Akihiro Kishimoto,et al.  Scalable, Parallel Best-First Search for Optimal Sequential Planning , 2009, ICAPS.

[6]  Marc Schoenauer,et al.  An Evolutionary Metaheuristic Based on State Decomposition for Domain-Independent Satisficing Planning , 2010, ICAPS.

[7]  Marc Schoenauer,et al.  Divide-and-Evolve: A New Memetic Scheme for Domain-Independent Temporal Planning , 2006, EvoCOP.

[8]  Wheeler Ruml,et al.  Best-First Heuristic Search for Multi-Core Machines , 2009, IJCAI.

[9]  S. Edelkamp,et al.  The Deterministic Part of IPC-4: An Overview , 2005, J. Artif. Intell. Res..

[10]  Vincent Vidal,et al.  Adaptive K-Parallel Best-First Search: A Simple but Efficient Algorithm for Multi-Core Domain-Independent Planning , 2010, SOCS.

[11]  Paolo Traverso,et al.  Automated planning - theory and practice , 2004 .

[12]  Jonathan Schaeffer,et al.  Transposition Table Driven Work Scheduling in Distributed Game-Tree Search , 2002, Canadian Conference on AI.

[13]  Enrique Alba,et al.  Parallelism and evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

[14]  Bernhard Nebel,et al.  The FF Planning System: Fast Plan Generation Through Heuristic Search , 2011, J. Artif. Intell. Res..

[15]  Nathan R. Sturtevant,et al.  Simultaneously Searching with Multiple Settings: An Alternative to Parameter Tuning for Suboptimal Single-Agent Search Algorithms , 2010, SOCS.

[16]  El-Ghazali Talbi,et al.  ParadisEO: A Framework for the Reusable Design of Parallel and Distributed Metaheuristics , 2004, J. Heuristics.

[17]  Paolo Traverso,et al.  Automated Planning: Theory & Practice , 2004 .

[18]  Jussi Rintanen.  Heuristic Planning with SAT: Beyond Uninformed Depth-First Search , 2010, Australasian Conference on Artificial Intelligence.

[19]  Vincent Vidal,et al.  A Lookahead Strategy for Heuristic Search Planning , 2004, ICAPS.

[20]  James A. Hendler,et al.  PRA*: Massively Parallel Heuristic Search , 1995, J. Parallel Distributed Comput..

[21]  Silvia Richter,et al.  The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks , 2010, J. Artif. Intell. Res..

[22]  José Nelson Amaral,et al.  Sequential and Parallel Algorithms for Frontier A* with Delayed Duplicate Detection , 2006, AAAI.

[23]  Maria Fox,et al.  PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains , 2003, J. Artif. Intell. Res..