Parallel simulation of ion recombination in nonpolar liquids

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1225)


Ion recombination in nonpolar liquids is an important problem in radiation chemistry. We have designed and implemented a parallel Monte Carlo simulation for this computationally-intensive task on a network of workstations. The main problem with parallelizing this application is that the amount of work performed by each process decreases during execution, resulting in high communication overhead and load imbalances. We address this problem by dynamically adjusting the number of processors that are used. We have evaluated the performance of the parallel program on two systems, one using Ethernet and the other using Myrinet. On Ethernet, the program suffers from a large communication overhead. Using the Myrinet high-speed network in combination with a programming system (Orca) that is optimized for fast networks, however, the program obtains a high efficiency.


parallel Monte Carlo simulation N-body problem Myrinet Orca 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    H.E. Bal, R. Bhoedjang, R. Hofman, C. Jacobs, K. Langendoen, T. Rühl, and K. Verstoep. Performance of a High-Level Parallel Language on a High-Speed Network. Journal of Parallel and Distributed Computing, February 1997.Google Scholar
  2. 2.
    H.E. Bal, M.F. Kaashoek, and A.S. Tanenbaum. Orca: A Language for Parallel Programming of Distributed Systems. IEEE Transactions on Software Engineering, 18(3):190–205, March 1992.Google Scholar
  3. 3.
    W.M. Bartczak and A. Hummel. Computer simulation of ion recombination in irradiated nonpolar liquids. J. Chem. Phys., 87(9), November 1987.Google Scholar
  4. 4.
    W.M. Bartczak and A. Hummel. Computer Simulation Study of Spatial Distribution of the Ions and Electrons in Tracks of High-Energy Electrons and the Effect on the Charge Recombination. The Journal of Physical Chemistry, 97, 1993.Google Scholar
  5. 5.
    N.J. Boden, D. Cohen, R.E. Felderman, A.E. Kulawik, C.L. Seitz, J.N. Seizovic, and W. Su. Myrinet: A Gigabit-per-second Local Area Network. IEEE Micro, 15(1):29–36, February 1995.Google Scholar
  6. 6.
    J.C. Jacob and S.-Y. Lee. Task Spreading and Shrinking on a Network of Workstations with Various Edge Classes. In 1996 International Conference on Parallel Processing, Vol. III, pages 174–181, August 1996.Google Scholar
  7. 7.
    N. Reimer, S.U. Haenssgen, W.F. Tichy. Dynamically Adapting the Degree of Parallelism with Reflexive Programs. In Proceedings of Third International Workshop on Parallel Algorithms for Irregularly Structured Problems (IRREGULAR'96), pages 313–318, Santa Barbara, CA, August 1996.Google Scholar
  8. 8.
    A.S. Tanenbaum, M.F. Kaashoek, and H.E. Bal. Parallel Programming using Shared Objects and Broadcasting. IEEE Computer, 25(8):10–19, August 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  1. 1.Dept. of Mathematics and Computer ScienceVrije UniversiteitHV AmsterdamThe Netherlands
  2. 2.Dept. of Physics and AstronomyVrije UniversiteitHV AmsterdamThe Netherlands

Personalised recommendations