Using GPU for Multi-agent Multi-scale Simulations
Multi-Agent System (MAS) is an interesting way to create models and simulators and is widely used to model complex systems. As the complex system community tends to build up larger models to fully represent real systems, the need for computing power raise significantly. Thus MAS often lead to long computing intensive simulations. Parallelizing such a simulation is complex and it execution requires the access to large computing resources. In this paper, we present the adaptation of a MAS system, Sworm, to a Graphical Processing Unit.We show that such an adaptation can improve the performance of the simulator and advocate for a more wider use of the GPU in Agent Based Models in particular for simple agents.
KeywordsGraphic Card Graphical Processing Unit Implementation Microbial Coloni Streaming Multiprocessor Global Memory Access
Unable to display preview. Download preview PDF.
- 2.Amouroux, E.: KIMONO: using the modelling process as an aid for research orientation. PhD thesis, UPMC, Paris, France (2011)Google Scholar
- 3.North, M.J., Howe, T.R., Collier, N.T., Vos, J.R.: A declarative model assembly infrastructure for verification and validation. In: Advancing Social Simulation: The First World Congress, FRG, Heidelberg (2007)Google Scholar
- 6.Sean, L., Cioffi-Revilla, C., Panait, L., Sullivan, K., Balan, G.: Mason: A multi-agent simulation environment. Simulation: Transactions of the Society for Modeling and Simulation International 82(7), 517–527 (2005)Google Scholar
- 7.Bleiweiss, A.: Multi agent navigation on the gpu. In: Game Developers Conference, GDC 2009 (2008)Google Scholar
- 8.Marilleau, N., Lang, C., Chatonnay, P., Philippe, L.: An agent based framework for urban mobility simulation. In: PDP, France, pp. 355–361 (2006)Google Scholar
- 11.JOCL: Java bindings for OpenCL (October 11, 2011), http://www.jocl.org/
- 12.JCUDA: Java bindings for CUDA (October 11, 2011), http://www.jcuda.org/