Parallel Heuristics for an On-Line Scientific Database for Efficient Function Approximation (original) (raw)
Abstract
An effective approach for improving the efficiency of multi-scale combustion simulations is the use of on-line scientific databases. These databases allow for the approximation of computationally expensive functions by archiving previously computed exact values. A sequential software implementation of these database algorithms has proven to be extremely effective in decreasing the running time of complex reacting flow simulations. To enable the use of this approach on parallel computers, in this paper we introduce three heuristics for coordinating the distributed management of the database. We compare the performance of these heuristics on two limiting case test problems. These experiments demonstrate that a hybrid communication strategy offers the best promise for a large-scale, parallel implementation.
This work was supported by NSF grants CTS-0121573, ACI–9908057, and DGE–9987589 and ACI-0305743.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
- Maas, U., Pope, S.B.: Laminar flame calculations using simplified chemical kinetics based on intrinsic low-dimensional manifolds. In: Twenty-Fifth Symposium (International) Combustion/ The Combustion Institute, pp. 1349–1356 (1994)
Google Scholar - Pope, S.B.: Computationally efficient implementation of combustion chemistry using in situ adaptive tabulation. Combustion Theory Modeling 1, 41–63 (1997)
Article MATH MathSciNet Google Scholar - Veljkovic, I., Plassmann, P.E., Haworth, D.C.: A scientific on-line database for efficient function approximation. In: Kumar, V., Gavrilova, M.L., Tan, C.J.K., L’Ecuyer, P. (eds.) ICCSA 2003. LNCS, vol. 2667, pp. 643–653. Springer, Heidelberg (2003)
Chapter Google Scholar - Veljkovic, I., Plassmann, P.E., Haworth, D.C.: A parallel implementation of a scientific on-line database for efficient function approximation. In: Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications—PDPTA 2004, vol. 1, pp. 24–29 (2004)
Google Scholar - Embouazza, M., Haworth, D.C., Darabiha, N.: Implementation of detailed chemical mechanisms into multidimensional CFD using in situ adaptive tabulation: Application to HCCI engines. Journal of Fuels and Lubricants 111, 1544–1559 (2002)
Google Scholar - Pope, S.B.: ISAT-CK User manual (Version 3.0) (October 2000)
Google Scholar
Author information
Authors and Affiliations
- Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA
Ivana Veljkovic - The Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, 24061, USA
Paul E. Plassmann
Authors
- Ivana Veljkovic
- Paul E. Plassmann
Editor information
Editors and Affiliations
- Computer Science Department, University of Tennessee, 37996-3450, Knoxville, TN, USA
Jack Dongarra - Department of Informatics and Mathematical Modelling, Technical University of Denmark, DK-2800, Lyngby, Denmark
Kaj Madsen - Informatics & Mathematical Modeling, Technical University of Denmark, DK-2800, Lyngby, Denmark
Jerzy Waśniewski
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Veljkovic, I., Plassmann, P.E. (2006). Parallel Heuristics for an On-Line Scientific Database for Efficient Function Approximation. In: Dongarra, J., Madsen, K., Waśniewski, J. (eds) Applied Parallel Computing. State of the Art in Scientific Computing. PARA 2004. Lecture Notes in Computer Science, vol 3732. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11558958\_77
Download citation
- .RIS
- .ENW
- .BIB
- DOI: https://doi.org/10.1007/11558958\_77
- Publisher Name: Springer, Berlin, Heidelberg
- Print ISBN: 978-3-540-29067-4
- Online ISBN: 978-3-540-33498-9
- eBook Packages: Computer ScienceComputer Science (R0)Springer Nature Proceedings Computer Science
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.