Advertisement

Experiences with asynchronous parallel molecular dynamics simulations

  • Marcus Dormanns
  • Walter Sprangers
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1067)

Abstract

This article provides some insight in the runtime behavior of asynchronous methods for parallel molecular dynamics simulations that we recently introduced. From this, the advantages of the asynchronous mode of operation becomes very obvious, i.e. the abilities to hide message passing latencies, to reduce network congestion and to level out processing power and/or load fluctuations. The conclusions are validated by simulation runs on a network of up to 12 workstations, comparing the results to a synchronous mode of execution.

Keywords

molecular dynamics simulation parallel processing asynchronous algorithm performance analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Allen, M. P.; Tildesley, D. J.: Computer Simulation of Liquids. Oxford University Press, 1987.Google Scholar
  2. [2]
    Bertsekas, D. P.; Tsitsiklis, J. N.: Parallel and Distributed Computation: Numerical Methods. Prentice Hall, 1989.Google Scholar
  3. [3]
    Butenuth, R.: Message Passing in Parallel Operating Systems and Applications. Proc. High Performance Computing '96, New Orleans.Google Scholar
  4. [4]
    Dormanns, ML; Sprangers, W.: On the Precision of Asynchronous Parallel Molecular Dynamics Simulations. Technical Report, Chair for Operating Systems, RWTH Aachen, Oct. 1995.Google Scholar
  5. [5]
    Dormanns, M. Sprangers, W.; Bemmerl, T.: Feasibility of Asynchronous Parallel Molecular Dynamics Simulations. Proc. High Performance Computing '96, New Orleans.Google Scholar
  6. [6]
    Elliot, W. D.: Revisiting the Fast Multipole Algorithm Error Bounds. Technical Report 94-008, Duke University, Dept. of Electrical Engineering, Durham, NC, Jan. 1995.Google Scholar
  7. [7]
    Gropp, W.; Lusk, E.;Skjellum, A.: Using MPI: Portable Parallel Programming with the Message-Passing Interface. MIT Press, 1994.Google Scholar
  8. [8]
    Günther, H.; Bemmerl, T.: Programming Scalable HPC Systems: Tools and their Application. Speedup Journal, Vol. 9, No. 1, pp. 68–71, 1995.Google Scholar
  9. [9]
    Plimpton, S.: Fast Parallel Algorithms for Short-Range Molecular dynamics. J. of Comp. Phy., Vol. 117, pp. 1–19, March 1995.Google Scholar
  10. [10]
    Street, W. B.; Tildesley, D. J.; Saville, G.: Multiple time step methods in molecular dynamics. Mol. Phys., Vol. 35, No. 3, pp. 639–648, 1978.Google Scholar
  11. [11]
    Strumpen, V.; Casavant, T. T.: Implementing Communication Latency Hiding in High-Latency Computer Networks. Proc. HPCN '95, Springer LNCS, pp. 86–93, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Marcus Dormanns
    • 1
  • Walter Sprangers
    • 1
  1. 1.Lehrstuhl für BetriebssystemeRWTH AachenAachenGermany

Personalised recommendations