Abstract
In this paper, we evaluate message-passing applications in Grid environments using domain decomposition technique. We compare two domain decomposition strategies: a balanced and unbalanced one. The balanced strategy is commonly strategy used in homogenous computing environment. This strategy presents some problems related with the larger communication latency in Grid environments. We propose an unbalanced domain decomposition strategy in order to overlap communication latency with useful computation. This idea consists in assigning less workload to processors responsible for sending updates outside the host. We compare the results obtained with the classical balanced strategy. We show that the unbalanced distribution pattern improves the execution times of domain decomposition applications in Grid environments. We considered two kinds of meshes, which define the most typical cases. We show that the expected execution time can be reduced up to 53%. We also analyze the influence of the communication patterns on execution times using the Dimemas simulator.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Allen, G., Goodale, T., Russell, M., Seidel, E., Sahlf, J.: Classifying and enabling grid applications. Concurrency and Computation: Practice and Experience 00, 1–7 (2000)
Gropp, W.D., Keyes, D.E.: Complexity of Parallel Implementation of Domain Decomposition Techniques for Elliptic Partial Differential Equations. SIAM Journal on Scientific and Statistical Computing 9(2), 312–326 (1988)
Kaushik, D.K., Keyes, D.E., Smith, B.F.: On the Interaction of Architecture and Algorithm in the Domain-based Parallelization of an Unstructured Grid Incompressible Flow Code. In: 10th International Conference on Domain Decomposition Methods, pp. 311–319. Wiley, Chichester (1997)
Gropp, W., Kaushik, D., Keyes, D., Smith, B.: Latency, Bandwidth, and Concurrent Issue Limitations in High-Performance CFD. In: Computational Fluid and Solid Mechanics, MA, pp. 839–841 (2001)
Badia, R.M., Labarta, J., Giménez, J., Escale, F.: DIMEMAS: Predicting MPI Applications Behavior in Grid Environments. In: Workshop on Grid Applications and Programming Tools, GGF8 (2003)
Badia, R.M., Escale, F., Gabriel, E., Gimenez, J., Keller, R., Labarta, J., Müller, M.S.: Performance Prediction in a Grid Environment. In: 1st European across Grid Conference, SC, Spain (2003)
Li, Y., Lan, Z.: A Survey of Load Balancing in Grid Computing. In: Zhang, J., He, J.-H., Fu, Y. (eds.) CIS 2004. LNCS, vol. 3314, pp. 280–285. Springer, Heidelberg (2004)
Dimemas (2002), Internet http://www.cepba.upc.es/dimemas/
Badía, R.M., Gimenez, J., Labarta, J., Escalé, F., Keller, R.: “DAMIEN: Distributed Applications and Middleware for Industrial Use of European Networks D5.2/CEPBA (IST-2000-25406)
Badía, R.M., Escalé, F., Gimenez, J., Labarta, J.: DAMIEN: Distributed Applications and Middleware for Industrial Use of European Networks. D5.3/CEPBA (IST-2000-25406)
Otero, B. y J. M. Cela: Latencia y ancho de banda para simular ambientes Grid. TR UPC-DAC-2004-33, UPC. España (2004), http://www.ac.upc.es/recerca/reports/DAC/2004/index,ca.html
Keyes, D.E.: Domain Decomposition Methods in the Mainstream of Computational Science. In: 14thInternational Conference on Domain Decomposition Methods, Mexico City, pp. 79–93 (2003)
Cai, X.C.: Some Domain Decomposition Algorithms for Nonselfadjoint Elliptic and Parabolic Partial Differential Equations. TR 461, Courant Institute, NY (1989)
George, K., Vipin, K.: Multilevel Algorithms for Multi-Constraint Graph Partitioning. University of Minnesota, Department of Computer Science. Minneapolis. TR 98-019 (1998)
George, K., Vipin, K.: Multilevel k-way Partitioning Scheme for Irregular Graphs. University of Minnesota, Department of Computer Science. Minneapolis. TR 95-064 (1998)
Metis, Internet http://www.cs.umn.edu/~metis
Message Passing Interface Forum, MPI-2: Extensions to the Message Passing Interface (July 1997)
Karonis, N., Toonen, B., Foster, I.: Mpich-g2: A Grid-enabled Implementation of the Message Passing Interface. Journal of Parallel and Distributed Computing (2003)
Foster, I., Karonis, N.T.: A Grid-enabled MPI: Message Passing in Heterogeneous Distributed Computing Systems. In: Supercomputing, November 1998. IEEE, Los Alamitos (1998), http://www.supercomp.org/sc98
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Otero, B., Cela, J.M., Badia, R.M., Labarta, J. (2005). Data Distribution Strategies for Domain Decomposition Applications in Grid Environments. In: Hobbs, M., Goscinski, A.M., Zhou, W. (eds) Distributed and Parallel Computing. ICA3PP 2005. Lecture Notes in Computer Science, vol 3719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564621_24
Download citation
DOI: https://doi.org/10.1007/11564621_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29235-7
Online ISBN: 978-3-540-32071-5
eBook Packages: Computer ScienceComputer Science (R0)