Optimization algorithms for DSMC computations on parallel clusters
Authors
-
P.V. Vashchenkov
-
A.V. Kashkovsky
-
M.S. Ivanov
Keywords:
DSMC
parallel computations
clusters
algorithms
load balance
Abstract
The paper describes some algorithms of dynamic decomposition of computational domains when solving the problems of rarefied gas dynamics by the DSMC method on parallel computing clusters. The operation of these algorithms and their efficiency are considered on the basis of using the SMILE++ software system.
Section
Section 1. Numerical methods and applications
References
- Бeрд Г. Молекулярная газовая динамика. М.: Мир, 1981.
- Bird G.A. Molecular gas dynamics and the direct simulation of gas flows. Oxford: Clarendon Press, 1994.
- Ivanov M.S., Markelov G.N., Gimelshein S.F. Statistical simulation of reactive rarefied flows: numerical approach and applications // AIAA Paper 98-2669.
- Ivanov M., Markelov G., Taylor S., Watts J. Parallel DSMC strategies for 3D computations // Proc. Parallel CFD’96. P. Schiano, A. Ecer, J. Periaux, N. Satofuka (Eds.). Amsterdam: North Holland, 1997. 485-492.
- Antonov S., Pfreundt F.-J., Struckmeier J. Adaptive load balance techniques in parallel rarefied gas simulations // J. of Computational Physics. 1997. 138, Issue 2. 400-418.
- Nance R.P., Hassan H.A., Wilmoth R.G., Saltz J. Parallel DSMC solution of three-dimensional flow over a finite flat plate // AIAA and ASME. Joint Thermophysics and Heat Transfer Conference, 1994. AIAA-1994-2019.
- Foster I. Designing and building parallel programs: concepts and tool for parallel software engineering. Reading: Addison-Wesley Publishing Company, 1995.
- Kashkovsky A., Markelov G., Ivanov M. An object-oriented software design for the direct simulation Monte Carlo method // AIAA 2001-2895.
- Kashkovsky A.V., Bondar Ye.A., Zhukova G.A., Ivanov M.S., Gimelshein S.F. Object-oriented software design of real gas effects for the DSMC method // 24th Int. Symp. on Rarefied Gas Dynamics, Porto Giardino, Italy, July 10-16, 2004. AIP Conf. Proc. 2005. 762, Issue 1. 583-588.