Abstract
Solving systems of linear equations is one of the key operations in linear algebra. Many different algorithms are available in that purpose. These algorithms require a very accurate tuning to minimise runtime and memory consumption. The TLSE project provides, on one hand, a scenario-driven expert site to help users choose the right algorithm according to their problem and tune accurately this algorithm, and, on the other hand, a test-bed for experts in order to compare algorithms and define scenarios for the expert site. Both features require to run the available solvers a large number of times with many different values for the control parameters (and maybe with many different architectures). Currently, only the grid can provide enough computing power for this kind of application. The DIET middleware is the GRID backbone for TLSE. It manages the solver services and their scheduling in a scalable way.
This work was supported in part by the ACI GRID (ASP and TLSE) and the RNTL (GASP) of the French National Fund for Science.
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
P. Amestoy and M. Pantel. Grid-TLSE:A web expertise site for sparse linear algebra. In Sparse Days and Grid Computing in St Girons, June 2003. http://www.cerfacs.fr/algor/PastWorkshops/SparseDays2003.
P. R. Amestoy, T. A. Davis, and I. S. Duff. An approximate minimum degree ordering algorithm. SIAM Journal on Matrix Analysis and Applications, 17:886–905, 1996.
P. R. Amestoy, I. S. Duff, and J.-Y. L’Excellent. Multifrontal parallel distributed symmetric and unsymmetric solvers. Comput. Methods Appl. Mech. Eng., 184:501–520, 2000.
G. Antoniu, L. Bougé, and M. Jan. JuxMem: An adaptive supportive platform for data sharing on the grid. In Proceedings Workshop on Adaptive Grid Middleware (AGRIDM 2003), pages 49–59, 2003.
P. Arbenz, W. Gander, and J. Mori. The Remote Computational System. Parallel Computing, 23(10):1421–1428, 1997.
D. Arnold, S. Agrawal, S. Blackford, J. Dongarra, M. Miller, K. Sagi, Z. Shi, and S. Vadhiyar. Users’ Guide to NetSolve V1.4. Computer Science Dept. Technical Report CS-01-467, University of Tennessee, Knoxville, TN, July 2001.
D.C. Arnold, H. Casanova, and J. Dongarra. Innovations of the NetSolve Grid Computing System. Concurrency And Computation: Practice And Experience, 14:1–23, 2002.
E. Caron, P.K. Chouhan, and A. Legrand. Automatic Deployment for Hierarchical Network Enabled Server. In The 13th Heterogeneous Computing Workshop, 2004.
E. Caron and F. Desprez. DIET: A Scalable Toolbox to Build Network Enabled Servers on the Grid. Technical Report 2005-23, LIP ENS Lyon, 2005.
E. Caron, F. Desprez, F. Lombard, J.-M. Nicod, M. Quinson, and F. Suter. A Scalable Approach to Network Enabled Servers. In Proc. of EuroPar 2002, 2002.
E. Cuthill. Several strategies for reducing the bandwidth of matrices. In D. J. Rose and R. A. Willoughby, editors, Sparse Matrices and Their Applications, New York, 1972. Plenum Press.
T. A. Davis and I. S. Duff. A combined unifrontal/multifrontal method for unsymmetric sparse matrices. ACM Trans. on Mathematical Soft., 25(1): 1–19, 1999.
T.A. Davis. Algorithm 832: Umfpack v4.3—an unsymmetric-pattern multifrontal method. ACM Trans. Math. Softw., 30(2): 196–199, 2004.
M. Daydé, L. Giraud, M. Hernandez, J.-Y. L’Excellent, M. Pantel, and C. Puglisi. An overview of the Grid-TLSE project. In Proceedings of 6th International Meeting VEC-PAR’04, Valencia, Spain, pages pp 851–856, June 2004.
B. Del Fabbro, D. Laiymani, J.-M. Nicod, and L. Philippe. Data management in grid applications providers. In IEEE Int. Conf. DFMA’05, February 2005.
F. Desprez, M. Quinson, and F. Suter. Dynamic Performance Forecasting for Network Enabled Servers in a Metacomputing Environment. In Procs of the Int. Conf. on Parallel and Distributed Processing Techniques and Applications, 2001.
M.C. Ferris, M.P. Mesnier, and J.J. Mori. NEOS and Condor: Solving Optimization Problems Over the Internet. ACM Trans. on Mathematical Sofware, 26(1):1–18, 2000.
P. Hénon, P. Ramet, and J. Roman. PaStiX: A High-Performance Parallel Direct Solver for Sparse Symmetric Definite Systems. Parallel Computing, 28(2):301–321, January 2002.
HSL. A collection of Fortran codes for large scale scientific computation, 2000.
G. Karypis and V. Kumar. METIS — A Software Package for Partitioning Unstructured Graphs, Partitioning Meshes, and Computing Fill-Reducing Orderings of Sparse Matrices — Version 4.0. University of Minnesota, September 1998.
X. S. Li and J. W. Demmel. SuperLU_DIST: A scalable distributed-memory sparse direct solver for unsymmetric linear systems. ACM Trans. on Mathematical Soft., 29(2), 2003.
J. W. H. Liu. Modification of the minimum degree algorithm by multiple elimination. ACM Trans. on Mathematical Soft., 11(2): 141–153, 1985.
H. Nakada, M. Sato, and S. Sekiguchi. Design and Implementations of Ninf: towards a Global Computing Infrastructure. Future Generation Computing Systems, Metacomputing Issue, 15(5–6):649–658, 1999. http://ninf.apgrid.org/papers/papers.shtml.
M. Pantel, C. Puglisi, and P. Amestoy. Test for large scale systems of equations: meta-data for solvers, matrices and computers. In PMAA’04, 2004.
M. Pantel, C. Puglisi, and P. Amestoy. Grid, components and scientific computing. Technical Report TR/TLSE/05/07, ENSEEIHT-1RIT, 2005.
M. Quinson. Dynamic Performance Forecasting for Network-Enabled Servers in a Meta-computing Environment. In Int. Workshop on Performance Modeling, Evaluation, and Opt. of Parallel and Dist. Syst. (PMEO-PDS’02), in conjunction with IPDPS’ 02, 2002.
K. Seymour, C. Lee, F. Desprez, H. Nakada, and Y. Tanaka. The End-User and Middleware APIs for GridRPC. In Workshop on Grid Application Programming Interfaces, In conjunction with GGF12, Brussels, Belgium, September 2004.
S. Shirasuna, H. Nakada, S. Matsuoka, and S. Sekiguchi. Evaluating Web Services Based Implementations of GridRPC. In Proceedings of the 11th IEEE International Symposium on High Performance Distributed Computing (HPDC-11 2002), pages 237–245, 2002.
R. Wolski, N. T. Spring, and J. Hayes. The Network Weather Service: A Distributed Resource Performance Forecasting Service for Metacomputing. Future Generation Computing Systems, Metacomputing Issue, 15(5–6):757–768, Oct. 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer Science+Business Media, Inc.
About this chapter
Cite this chapter
Caron, E., Desprez, F., L’Excellent, JY., Hamerling, C., Pantel, M., Puglisi-Amestoy, C. (2006). Use of a Network-Enabled Server System for a Sparse Linear Algebra Grid Application. In: Getov, V., Laforenza, D., Reinefeld, A. (eds) Future Generation Grids. Springer, Boston, MA . https://doi.org/10.1007/978-0-387-29445-2_10
Download citation
DOI: https://doi.org/10.1007/978-0-387-29445-2_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-27935-0
Online ISBN: 978-0-387-29445-2
eBook Packages: Computer ScienceComputer Science (R0)