Multi-Agent Systems Meet GPU: Deploying Agent-Based Architectures on Graphics Processors

  • Roman Pavlov
  • Jörg P. Müller
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 394)


Even given today’s rich hardware platforms, computation-intensive algorithms and applications, such as large-scale simulations, are still challenging to run with acceptable response times. One way to increase the performance of these algorithms and applications is by using the computing power of Graphics Processing Units (GPU). However, effectively mapping distributed software models to GPU is a non-trivial endeavor. In this paper, we investigate ways of improving execution performance of multi-agent systems (MAS) models by means of relevant task allocation mechanisms, which are suitable for GPU execution. Several task allocation architecture variants for MAS using GPU are identified and their properties analyzed. In particular, we study three cases: Agents and their runtime environment can be (i) completely on the host (CPU); (ii) partly on host and device (GPU); (iii) completely on the device. For each of these architecture variants, we propose task allocation models that take GPU restrictions into account.


Multi-Agent Systems GPGPU CUDA 


  1. 1.
    Blatnig, S.: Microscopic Traffic Simulation with Intelligent Agents: Simulation of Human Driving Behaviour. VDM (2009)Google Scholar
  2. 2.
    Rehtanz, C.: Autonomous Systems and Intelligent Agents in Power System Control and Operation. Springer (2003)Google Scholar
  3. 3.
    Adler, J.L., et al.: A multi-agent approach to cooperative traffic management and route guidance. Transportation Research, Part B 39, 297–318 (2004)CrossRefGoogle Scholar
  4. 4.
    Amdahl, G.: Validity of the Single Processor Approach to Achieving Large-Scale Computing Capabilities. In: AFIPS Con. Proc., vol. (30), pp. 483–485 (1967)Google Scholar
  5. 5.
    Krumm, J.: Advances in Ubiquitous Computing. Chapman& Hall/CRC (2009)Google Scholar
  6. 6.
    Fiosins, M., Fiosina, J., Müller, J.P., Görmer, J.: Agent-Based Integrated Decision Making for Autonomous Vehicles in Urban Traffic. In: PAAMS 2011, pp. 173–178 (2011)Google Scholar
  7. 7.
  8. 8.
    Wooldridge, M.: An Introduction to Multi-Agent Systems, 2nd edn. John Wiley & Sons (2009)Google Scholar
  9. 9.
    Ehmke, J.F., Fiosins, M., Görmer, J., Schmidt, D., Schumacher, H., Tchouankem, H.: Decision Support for Dynamic City Traffic Management Using Vehicular Communication. In: Proc. of SIMULTECH 2011, pp. 327–332. SciTePress Digital Lib. (2011)Google Scholar
  10. 10.
    The Foundation for Intelligent Physical Agents,
  11. 11.
    Dastani, M.: Programming MAS. In: 5th Int. Work., ProMAS 2007, USA (2007)Google Scholar
  12. 12.
  13. 13.
  14. 14.
  15. 15.
    Laville, G., Mazouzi, K., Lang, C., Marilleau, N., Philippe, L.: Using GPU for Multi-agent Multi-scale Simulations. In: Omatu, S., Paz Santana, J.F., González, S.R., Molina, J.M., Bernardos, A.M., Rodríguez, J.M.C. (eds.) Distributed Computing and Artificial Intelligence. AISC, vol. 151, pp. 197–204. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  16. 16.
    dos Santos, L.G.O., Gonzales Clua, E.W., Bernardini, F.C.: A Parallel Fipa Architecture Based on GPU for Games and Real Time Simulations. In: Herrlich, M., Malaka, R., Masuch, M. (eds.) ICEC 2012. LNCS, vol. 7522, pp. 306–317. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    dos Santos, L.G.O., et al.: Mapping Multi-Agent Systems Based on FIPA Specification to GPU Architectures. In: VIDEOJOGOS 2010 (2010)Google Scholar
  18. 18.
  19. 19.
  20. 20.
    Johnson, T., Rankin, J.: Parallel Agent systems on a GPU for use with Simulations and Games. In: 12th WSEAS ACS 2012 (2012)Google Scholar
  21. 21.
  22. 22.
  23. 23.
  24. 24.
    Kallmann, M., Thalmann, D.: Modeling Objects for Interaction Tasks. In: 9th EGCAS, Lisbon, Portugal, pp. 73–86 (1998)Google Scholar
  25. 25.
    Smith, R.G.: The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver. IEEE Trans. Comput. 29(12), 1104–1113 (1980)CrossRefGoogle Scholar
  26. 26.
    Shoham, Y.: Agent-oriented programming. Artif. Intell. 60(1), 51–92 (1993)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Klügl, F., Bazzan, A.L.C.: Agent-Based Modeling and Simulation. AI Magazine 33(3), 29–40 (2012)Google Scholar
  28. 28.
    Fischer, K., Müller, J.P., Pischel, M.: Cooperative Transportation Scheduling: an Application Domain for DAI. Journal of Applied Artificial Intelligence 10, 1–33 (1996)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2013

Authors and Affiliations

  • Roman Pavlov
    • 1
  • Jörg P. Müller
    • 1
  1. 1.Clausthal University of TechnologyClausthal-ZellerfeldGermany

Personalised recommendations