Abstract
Grid computing in general is a special type of parallel computing. It intends to deliver high-performance computing over distributed platforms for computation and data-intensive applications by making use of a very large amount of resources. The GMRES method is used widely to solve the large sparse linear systems. In this paper, we present an effective parallel hybrid asynchronous method, which combines the typical parallel GMRES method with the Least Square method that needs some eigenvalues obtained from a parallel Arnoldi process. And we apply it on a Grid Computing platform Grid5000. From the numeric results, we will present that this hybrid method has some advantage for some real or complex systems compared to the general method GMRES.
Chapter PDF
Similar content being viewed by others
References
Cunha, R.D., Da, H.T.: A Parallel Implementation of the Restarted GMRES Iterative Algorithm for Nonsymmetric Systems of Linear Equations. In: Advances in Computational Mathematics, vol. 2, pp. 261–277. Springer, Heidelberg (1994)
Saad, Y., Schultz, M.H.: GMRES: A Generalized GMRES Algorithm for Solving Nonsymmetric Linear Systems. J. SIAM. Sci. Statist. Compt. 7, 856–869 (1986)
Edjlali, G., Petiton, S., Emad, N.: Interleaved Parallel Hybrid Arnoldi Method for a Parallel Machine and a Network of Workstations. In: Conference on Information, Systems, Analysis and Synthesis (ISAS 1996), Orlando, pp. 22–26 (1996)
Saad, Y.: Variations on Arnoldi’s Method for Computing Eigenelements of Large Unsymmetric Matrices. Linear Algebra Appl. 34, 269–295 (1980)
Saad, Y.: Numerical Methods for Large Eigenvalue Problems. Manchester University Press, Manchester (1992)
Saad, Y.: Least Squares Polynomials in the Complex Plane and their Use for Solving Nonsymmetric Linear Systems. J. SIAM. Sci. Statist. Compt. 7, 155–169 (1987)
YinTsung, H., WeiDa, C.: A Low Complexity Complex QR Factorization Design for Signal Detection in MIMO OFDM Systems. In: International Symposium on Circuits and Systems, pp. 932–935. IEEE Press, Seattle (2008)
Baker, A.H., Jessup, E.R., Manteuffel, T.: A Technique for Accelerating the Convergence of Restarted GMRES. J. SIAM. MATRIX. Anal. Appl. 26, 962–984 (2005)
Essai, A., Bergere, G., Petiton, S.: Heterogeneous Parallel Hybrid GMRES/LS-Arnold Method. In: Ninth SIAM Conference on Parallel Processing for Scientific Computing, Texas (1999)
Manteuffel, T.A.: The Tchebychev Iteration for Nonsymmetric Linear Systems. J. Numer. Math. 28, 307–327 (1997)
Smolarski, D.C., Saylor, P.E.: An Optimum Iterative Method for Solving any Linear System with a Square Matrix. J. BIT. 28, 163–178 (1988)
Georgiou, Y., Richard, O., Neyron, P., Huard, G., Martin, C.: A Batch Scheduler with High Level Components. In: 5th International Symposium on Cluster Computing and the Grid, pp. 2, 776–783. IEEE Press, Cardiff (2005)
Franck, C., Eddy, C., Michel, D., Frederic, D., Yvon, J.: Grid’5000: a Large Scale and Highly Reconfigurable Grid Experimental Testbed. International Journal of High Performance Computing Applications 20, 481–494 (2006)
Benjamin, Q., Franck, C.: A Survey of Grid Research Tools: Simulators, Emulators and Real Life Platform. In: 17th IMACS World Congress Scientific Computation, Applied Mathematics and Simulation, Paris, France (2005)
Ye, Z., Bergere, G., Petiton, S.: A Parallel Hybrid Method of GMRES on GRID System. In: IEEE International Parallel and Distributed Processing Symposium, p. 356. IEEE Press, California (2007)
Grid’5000, http://www.grid5000.fr
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 IFIP International Federation for Information Processing
About this paper
Cite this paper
Zhang, Y., Bergere, G., Petiton, S. (2008). Grid Computing: A Case Study in Hybrid GMRES Method. In: Cao, J., Li, M., Wu, MY., Chen, J. (eds) Network and Parallel Computing. NPC 2008. Lecture Notes in Computer Science, vol 5245. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88140-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-88140-7_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88139-1
Online ISBN: 978-3-540-88140-7
eBook Packages: Computer ScienceComputer Science (R0)