Advertisement

The European Physical Journal Special Topics

, Volume 227, Issue 14, pp 1779–1788 | Cite as

Enabling unstructured domain decompositions for inhomogeneous short-range molecular dynamics in ESPResSo

  • Steffen HirschmannEmail author
  • Colin W. Glass
  • Dirk Pflüger
Regular Article
  • 16 Downloads
Part of the following topical collections:
  1. Particle Methods in Natural Science and Engineering

Abstract

In short-range molecular dynamics (MD) simulations, inhomogeneous particle distributions that dynamically change over time require flexible load-balancing methods to achieve good parallel efficiency. We have realized a general framework that can support different load-balancing methods and that can extend existing simulation packages in a minimally invasive way. This is a follow-up to recent work where we integrated it into the MD software ESPResSo to support load-balancing. We have realized a first partitioning strategy based on space-filling curves that can be used for efficient load-balanced multi-physics simulations. In this work we present a new graph-based partitioning strategy that leads to unstructured spatial domain decompositions and integrates well into the existing framework. We apply this to an inhomogeneous soot agglomeration scenario. For several load metrics, graph partitioning leads to better results than space-filling curves. The results indicate that the parallel performance for a given scenario requires a delicate combination of partitioning strategy and load metrics.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M.P. Allen, D.J. Tildesley, Computer simulation of liquids (Oxford Science Publ. Clarendon Press, 1989)Google Scholar
  2. 2.
    G. Inci, A. Kronenburg, R. Weeber, D. Pflüger, Flow Turbul. Combust. 98, 1 (2017)CrossRefGoogle Scholar
  3. 3.
    R.W. Hockney, J.W. Eastwood, Computer simulation using particles, (Taylor & Francis, Inc., Bristol, PA, USA, 1988)Google Scholar
  4. 4.
    S. Plimpton, J. Comput. Phys. 117, 1 (1995)ADSCrossRefGoogle Scholar
  5. 5.
    S. Hirschmann, M. Brunn, M. Lahnert, C.W. Glass, M. Mehl, D. Pflüger, Load balancing with p4est for short-range molecular dynamics with ESPResSo, in Advances in Parallel Computing, edited by S. Bassini et al. (IOS Press, 2017) , Vol. 32 , p. 455Google Scholar
  6. 6.
    A. Arnold, O. Lenz, S. Kesselheim, R. Weeber, F. Fahrenberger, D. Roehm, P. Košovan, C. Holm, ESPResSo 3.1: molecular dynamics software for coarse-grained models, in Meshfree Methods for Partial Differential Equations VI, edited by M. Griebel, M.A. Schweitzer(Springer, Berlin, Heidelberg, 2013), Vol. 89, p. 1Google Scholar
  7. 7.
    H. Sagan, Space-filling curves (Springer, New York, 1994)Google Scholar
  8. 8.
    A. Pnar, C. Aykanat, J. Parallel Distrib. Comput. 64, 974 (2004)CrossRefGoogle Scholar
  9. 9.
    S. Miguet, J.-M. Pierson, Heuristics for 1d rectilinear partitioning as a low cost and high quality answer to dynamic load balancing, in High-Performance Computing and Networking (Springer, Heidelberg, 1997), p. 550Google Scholar
  10. 10.
    P.M. Campbell, K.D. Devine, J.E. Flaherty, L.G. Gervasio, J.D. Teresco, Dynamic octree load balancing using space-filling curves, Tech. rep. CS-03-01 (Williamstown, MA 01267, Williams College Department of Computer Science, 2003)Google Scholar
  11. 11.
    C. Burstedde, L.C. Wilcox, O. Ghattas, SIAM J. Sci. Comput. 33, 1103 (2011)MathSciNetCrossRefGoogle Scholar
  12. 12.
    C.-E. Bichot, P. Siarry, Graph partitioning (John Wiley & Sons, New York, 2013)Google Scholar
  13. 13.
    G. Karypis, V. Kumar, SIAM J. Sci. Comput. 20, 359 (1998)MathSciNetCrossRefGoogle Scholar
  14. 14.
    M. Buchholz, Framework zur Parallelisierung von Molekulardynamiksimulationen in verfahrenstechnischen Anwendungen (Verlag Dr. Hut, 2010)Google Scholar
  15. 15.
    M. Buchholz, H.J. Bungartz, J. Vrabec, J. Comput. Sci. 2, 124 (2011)CrossRefGoogle Scholar
  16. 16.
    B. Hendrickson, T.G. Kolda, Parallel Comput. 26, 1519 (2000)MathSciNetCrossRefGoogle Scholar
  17. 17.
    U.V. Catalyurek, E.G. Boman, K.D. Devine, D. Bozdağ, R.T. Heaphy, L.A. Riesen, J. Parallel Distrib. Comput. 69, 711 (2009)CrossRefGoogle Scholar
  18. 18.
    S. Schambeger, J.M. Wierum, Int. Conf. Parallel Comput. Technol. 2763, 165 (2003)CrossRefGoogle Scholar
  19. 19.
    W.F. Mitchell, J. Parallel Distrib. Comput. 67, 417 (2007)CrossRefGoogle Scholar
  20. 20.
    C. Niethammer, S. Becker, M. Bernreuther, M. Buchholz, W. Eckhardt, A. Heinecke, S. Werth, H.J. Bungartz, C.W. Glass, H. Hasse, J. Vrabec, J. Chem. Theory Comput. 10, 4455 (2014)CrossRefGoogle Scholar
  21. 21.
    S. Seckler, N. Tchipev, H.J. Bungartz, P. Neumann, Load balancing for molecular dynamics simulations on heterogeneous architectures, in 2016 IEEE 23rd International Conference on High Performance Computing (HiPC) (2016), pp. 101–110Google Scholar
  22. 22.
    L. Isella, Y. Drossinos, Phys. Rev. E 82, 011404 (2010)ADSCrossRefGoogle Scholar
  23. 23.
    H.J. Limbach, A. Arnold, B.A. Mann, C. Holm, Comput. Phys. Commun. 174, 704 (2006)ADSCrossRefGoogle Scholar
  24. 24.
    S. Hirschmann, M. Brunn, M. Lahnert, C.W. Glass, M. Mehl, D. Pflüger, Load-balancing and spatial adaptivity for coarse-grained molecular dynamics applications, in High Performance Computing in Science and Engineering ‘18 (Springer, Berlin, Heidelberg, 2018), ForthcomingGoogle Scholar
  25. 25.
    M. Lahnert, C. Burstedde, C. Holm, M. Mehl, G. Rempfer, F. Weik, Minimally-invasive integration of p4est in ESPResSo for adaptive lattice-Boltzmann, in The 30th Computational Fluid Dynamics Symposium (Japan Society of Fluid Mechanics, 2016)Google Scholar
  26. 26.
    M. Lahnert, C. Burstedde, C. Holm, M. Mehl, G. Rempfer, F. Weik, Towards lattice-Boltzmann on dynamically adaptive grids–minimally-invasive grid exchange in ESPResSo, in VII European Congress on Computational Methods in Applied Sciences and Engineering, edited byM. Papadrakakis, et al. ECCOMAS (2016)Google Scholar
  27. 27.
    T. Isaac, C. Burstedde, L.C. Wilcox, O. Ghattas, SIAM J. Sci. Comput. 37, C497 (2015)CrossRefGoogle Scholar
  28. 28.
    S. Hirschmann, D. Pflüger, C.W. Glass, Towards understanding optimal load-balancing of heterogeneous short-range molecular dynamics 2016 IEEE 23rd International Conference on High Performance Computing (HiPC) (2016)Google Scholar
  29. 29.
    S. Succi, The lattice Boltzmann equation for fluid dynamics and beyond (Clarendon Press, 2001)Google Scholar
  30. 30.
    P. Ahlrichs, B. Dünweg, J. Chem. Phys. 111, 8225 (1999)ADSCrossRefGoogle Scholar
  31. 31.
    K. Schloegel, G. Karypis, V. Kumar, Parallel multilevel algorithms for multi-constraint graph partitioning, in European Conference on Parallel Processing (Springer, Berlin, Heidelberg, 2000), p. 296Google Scholar
  32. 32.
    G. Inci, A. Arnold, A. Kronenburg, R. Weeber, Aerosol Sci. Technol. 48, 842 (2014)ADSCrossRefGoogle Scholar
  33. 33.
    A. Pınar, E. Kartal Tabak, C. Aykanat, J. Parallel Distrib. Comput. 68, 1473 (2008)CrossRefGoogle Scholar

Copyright information

© EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Steffen Hirschmann
    • 1
    Email author
  • Colin W. Glass
    • 2
  • Dirk Pflüger
    • 1
  1. 1.Institute for Parallel and Distributed Systems, University of StuttgartStuttgartGermany
  2. 2.Department of Mechanical EngineeringHelmut Schmidt UniversityHamburgGermany

Personalised recommendations