Advertisement

The Impact of Particle Sorting on Particle-In-Cell Simulation Performance

  • Andrzej DorobiszEmail author
  • Michał Kotwica
  • Jacek Niemiec
  • Oleh Kobzar
  • Artem Bohdan
  • Kazimierz Wiatr
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10777)

Abstract

The Particle-In-Cell (PIC) simulation method is a modern technique in studies of collisionless plasmas in applications to astrophysics and laboratory plasma physics. Inherent to this method is its parallel nature, which enables massively parallel MPI applications which can use thousands of CPU-cores on HPC systems. In order to achieve a good performance of a PIC code several techniques are available. In this work we study the impact of particle sorting on the performance of the PIC code THISMPI. We compare dual-pivot five-way quicksort with the standard quicksort. We focus on finding optimum sorting frequency.

Keywords

Particle-In-Cell Sorting Dual-pivot five-way quicksort MPI application Optimization 

Notes

Acknowledgement

This work has been supported by Narodowe Centrum Nauki through research project DEC-2013/10/E/ST9/00662 and in part by PL-Grid Infrastructure using Prometheus cluster at Academic Computer Center Cyfronet AGH.

References

  1. 1.
    Niemiec, J., Pohl, M., Stroman, T., Nishikawa, K.-I.: Production of magnetic turbulence by cosmic rays drifting upstream of supernova remnant shocks. Astrophys. J. 684, 1174–1189 (2008)CrossRefGoogle Scholar
  2. 2.
    Stroman, T., Pohl, M., Niemiec, J.: Kinetic simulations of turbulent magnetic-field growth by streaming cosmic rays. Astrophys. J. 706, 38–44 (2009)CrossRefGoogle Scholar
  3. 3.
    Bowers, K.J., Albright, B.J., Yin, L., Bergen, B., Kwan, T.J.T.: Ultrahigh performance three-dimensional electromagnetic relativistic kinetic plasma simulation. Phys. Plasmas 15, 055703 (2008)CrossRefGoogle Scholar
  4. 4.
    Fonseca, R.A., Martins, S.F., Silva, L.O., Tonge, J.W., Tsung, F.S., Mori, W.B.: One-to-one direct modeling of experiments and astrophysical scenarios: pushing the envelope on kinetic plasma simulations. Plasma Phys. Control. Fusion 50, 124034 (2008)CrossRefGoogle Scholar
  5. 5.
    Fonseca, R.A., Vieira, J., Fiuza, F., Davidson, A., Tsung, F.S., Mori, W.B., Silva, L.O.: Exploiting multi-scale parallelism for large scale numerical modelling of laser wakefield accelerators. Plasma Phys. Control. Fusion 55, 124011 (2013)CrossRefGoogle Scholar
  6. 6.
    Jocksch, A., Hariri, F., Tran, T.-M., Brunner, S., Gheller, C., Villard, L.: A bucket sort algorithm for the particle-in-cell method on manycore architectures. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015. LNCS, vol. 9573, pp. 43–52. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-32149-3_5 CrossRefGoogle Scholar
  7. 7.
    Buneman, O.: TRISTAN. In: Matsumoto, H., Omura, Y. (eds.) Computer Space Plasma Physics: Simulation Techniques and Software, pp. 67–84. Terra Scientific, Tokyo (1993)Google Scholar
  8. 8.
    Cai, D., Li, Y., Nishikawa, K.-I., Xiao, C., Yan, X., Pu, Z.: Parallel 3-D electromagnetic particle code using high performance FORTRAN: parallel TRISTAN. In: Büchner, J., Scholer, M., Dum, C.T. (eds.) Space Plasma Simulation. LNP, vol. 615, pp. 25–53. Springer, Heidelberg (2003).  https://doi.org/10.1007/3-540-36530-3_2 CrossRefGoogle Scholar
  9. 9.
    Niemiec, J., Pohl, M., Bret, A., Wieland, V.: Nonrelativistic parallel shocks in unmagnetized and weakly magnetized plasmas. Astrophys. J. 759, 73 (2012)CrossRefGoogle Scholar
  10. 10.
    Greenwood, A.D., Cartwright, K.L., Luginsland, J.W., Baca, E.A.: On the elimination of numerical Cerenkov radiation in PIC simulations. J. Comput. Phys. 201, 665–684 (2004)CrossRefzbMATHGoogle Scholar
  11. 11.
    Umeda, T., Omura, Y., Tominaga, T., Matsumoto, H.: A new charge conservation method in electromagnetic particle-in-cell simulations. Comput. Phys. Commun. 156, 73–85 (2003)CrossRefGoogle Scholar
  12. 12.
    Vay, J.-L.: Simulation of beams or plasmas crossing at relativistic velocity. Phys. Plasmas 15, 056701 (2008)CrossRefGoogle Scholar
  13. 13.
    Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in FORTRAN: The Art of Scientific Computing, 2nd edn, pp. 329–333. Cambridge University Press, Cambridge (1992). Chap. 8, Sect. 4zbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Andrzej Dorobisz
    • 1
    Email author
  • Michał Kotwica
    • 1
  • Jacek Niemiec
    • 2
  • Oleh Kobzar
    • 2
  • Artem Bohdan
    • 2
  • Kazimierz Wiatr
    • 1
    • 3
  1. 1.ACC Cyfronet AGHKrakówPoland
  2. 2.Institute of Nuclear Physics PANKrakówPoland
  3. 3.AGH University of Science and TechnologyKrakówPoland

Personalised recommendations