Abstract
In the paper a new approach to the design of parallel genetic algorithms for execution in distributed systems with multicore processors is presented. The use of a distributed genetic algorithm based on new control implementation principles is proposed for an optimized irregular computational mesh partitioning for the FDTD (Finite-Difference Time-Domain) problem. The algorithm defines computational mesh partitions based on two objectives: load balancing and “min-cut” – the minimal number of edges between partition elements. The control in the parallel genetic algorithm assumes the use of program execution global control functions based on global application states monitoring. A control design infrastructure is provided to a programmer based on generalized synchronization/control processes called synchronizers. They collect local states of program computational elements, compute global control predicates and send back control signals. The paper describes how the assumed infrastructure can be used for convenient global program execution control at thread and process levels applied in the proposed genetic algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Babaoglu, O., Marzullo, K.: Consistent global states of distributed systems: fundamental concepts and mechanisms. In: Mullender, S.J. (ed.) Distributed Systems. Addison-Wesley, Reading (1993)
Borkowski, J.: Interrupt and cancellation as synchronization methods. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds.) PPAM 2001. LNCS, vol. 2328, pp. 3–9. Springer, Heidelberg (2002)
Borkowski, J.: Strongly consistent global state detection for on-line control of distributed applications. In: PDP 2004, pp. 126–133. IEEE CS, February 2004
Borkowski, J., Tudruj, M.: Dual communication network in program control based on global application state monitoring. In: ISPDC 2007, Hagenberg, Austria, pp. 37–44. IEEE CS, July 2007
Fiduccia, C.M., Mattheyses, R.M.: A linear time heuristic for improving network partitions. In: Proceedings of the Nineteenth Design Automation Conference, pp. 175–181 (1982)
Garey, M., Johnson, D., Stockmeyer, L.: Some simplified NP-complete graph problems. Theor. Comput. Sci. 1, 237–267 (1976)
Jingling, X.: Loop Tiling for Parallelism. Kluwer Academic Publishers, Dordrecht (2000)
Karypis, G., Kumar, V.: Unstructured graph partitioning and sparse matrix ordering, Technical Report, Department of Computer Science, University of Minesota (1995). http://www.cs.umn.edu/~kumar
Khan, M.S., Li, K.F.: Fast graph partitioning algorithms. In: Proceedings of IEEE Pacific Rim Conference on Communications, Computers, and Signal Processing, Victoria, B.C., Canada, pp. 337–342, May 1995
Smyk, A., Tudruj, M.: Parallel implementation of FDTD computations based on macro data flow paradigm. In: PARELEC 2004, Dresden, Germany, 7–10 September 2004
Tudruj, M., Borkowski, J., Masko, L., Smyk, A., Kopanski, D., Laskowski, E.: Program design environment for multicore processor systems with program execution controlled by global states monitoring. In: ISPDC 2011, Cluj-Napoca, pp. 102–109. IEEE CS, July 2011
Kopanski, D., Maśko, Ł., Laskowski, E., Smyk, A., Borkowski, J., Tudruj, M.: Distributed program execution control based on application global states monitoring in PEGASUS DA framework. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds.) PPAM 2013, Part I. LNCS, vol. 8384, pp. 302–314. Springer, Heidelberg (2014)
Stoller, S.D.: Detecting global predicates in distributed systems with clocks. Distrib. Comput. 13(2), 85–98 (2000)
Tudruj, M., Kacsuk, P.: Extending grade towards explicit process synchronization in parallel programs. Comput. Artif. Intell. 17, 507–516 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Smyk, A., Tudruj, M. (2014). Genetic Algorithms Execution Control Under a Global Application State Monitoring Infrastructure. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2013. Lecture Notes in Computer Science(), vol 8384. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55224-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-55224-3_36
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55223-6
Online ISBN: 978-3-642-55224-3
eBook Packages: Computer ScienceComputer Science (R0)