New Parallel Implementation of an Air Pollution Computer Model – Performance Study on an IBM Blue Gene/P Computer

  • Krassimir Georgiev
  • Tzvetan Ostromsky
  • Zahari Zlatev
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7116)


A new parallel version of the Danish Eulerian model for long transport of air pollutants over the territory of Europe (UNI–DEM) is presented. It is based on the domain partitioning of the space domain both in the Ox and Oy directions. This new approach gives possibilities to use large number of processors (or cores) on the IBM BlueGene/P computer. The new version of the parallel code of the UNI–DEM is created by using MPI standard library and appears to be highly portable and shows good efficiency and scalability. Discussions according to the performance, speed-ups and efficiency achieved in the first testing runs of the new parallel code on an IBM Blue Gene/P computer are presented.


Message Passing Interface Parallel Implementation Space Domain Horizontal Advection Parallelization Strategy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abdalmogith, S., Harrison, R.M., Zlatev, Z.: Intercomparison of inorganic aerosol concentrations in the UK with predictions of the Danish Eulerian Model. Journal of Atmospheric Chemistry 54, 43–66 (2006)CrossRefGoogle Scholar
  2. 2.
    Alexandrov, V., Owczarz, W., Thomsen, P.G., Zlatev, Z.: Parallel runs of large air pollution models on a grid of SUN computers. Mathematics and Computers in Simulations 65, 557–577 (2004)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Antonov, A., Georgiev, K., Komsalova, E., Zlatev, Z.: Implementation of Bilinear Nonconforming Finite Elements in an Eulerian Air Pollution Model: Results Obtained by Using the Rotational Test. In: Dimov, I.T., Lirkov, I., Margenov, S., Zlatev, Z. (eds.) NMA 2002. LNCS, vol. 2542, pp. 379–386. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  4. 4.
    Directive 2002/3/EC of the European Parliament and the Council of 12 February 2002 relating to ozone in ambient air. Official Journal of the European Communities L67, 14–30 (2002)Google Scholar
  5. 5.
    Georgiev, K., Ostromsky, T.: Performance results of a large-scale air pollution model on two parallel computers. Int. J. of Environment and Pollution 22(1/2), 43–50 (2004)Google Scholar
  6. 6.
    Georgiev, K., Zlatev, Z.: Running an Advection-Chemistry Code on Message Passing Computers. In: Alexandrov, V., Dongarra, J. (eds.) PVM/MPI 1998. LNCS, vol. 1497, pp. 354–363. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  7. 7.
    Georgiev, K., Zlatev, Z.: Parallel sparse matrix algorithms for air pollution models. Parallel and Distributed Computing Practices 2, 429–442 (2000)Google Scholar
  8. 8.
    Georgiev, K., Zlatev, Z.: Runs of UNI–DEM Model on IBM Blue Gene/P Computer and Analysis of the Model Performance. In: Lirkov, I., Margenov, S., Waśniewski, J. (eds.) LSSC 2009. LNCS, vol. 5910, pp. 188–196. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Gropp, W., Lusk, E., Skjellum, A.: Using MPI: Portable programming with the message passing interface. MIT Press, Cambridge (1994)Google Scholar
  10. 10.
    Hov, Ø., Zlatev, Z., Berkowicz, R., Eliassen, A., Prahm, L.P.: Comparison of numerical techniques for use in air pollution models with non-linear chemical reactions. Atmospheric Environment 23, 967–983 (1988)Google Scholar
  11. 11.
    Marchuk, G.I.: Mathematical modeling for the problem of the environment. Studies in Mathematics and Applications, vol. 16. North-Holland, Amsterdam (1985)Google Scholar
  12. 12.
    McRae, G.J., Goodin, W.R., Seinfeld, J.H.: Numerical solution of the atmospheric diffusion equations for chemically reacting flows. J. Comp. Physics 45, 1–42 (1984)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Ostromsky, T., Owczarz, W., Zlatev, Z.: Computational Challenges in Large-scale Air Pollution Modelling. In: Proc. 2001 International Conference on Supercomputing in Sorrento, pp. 407–418. ACM Press (2001)Google Scholar
  14. 14.
    Ostromsky, T., Zlatev, Z.: Parallel Implementation of a Large-Scale 3-D Air Pollution Model. In: Margenov, S., Waśniewski, J., Yalamov, P. (eds.) LSSC 2001. LNCS, vol. 2179, pp. 309–316. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  15. 15.
    Ostromsky, T., Zlatev, Z.: Flexible Two-Level Parallel Implementations of a Large Air Pollution Model. In: Dimov, I.T., Lirkov, I., Margenov, S., Zlatev, Z. (eds.) NMA 2002. LNCS, vol. 2542, pp. 545–554. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  16. 16.
    Owczarz, W., Zlatev, Z.: Running a large-scale air pollution model on fast supercomputer. In: Chok, D.P., Carmichael, G.R. (eds.) Atmospheric Modelling, pp. 185–204. Springer, Heidelberg (2000)Google Scholar
  17. 17.
    WEB-site of the Danish Eulerian Model,
  18. 18.
    Zlatev, Z.: Computer treatment of large air pollution models. Kluwer (1995)Google Scholar
  19. 19.
    Zlatev, Z., Dimov, I.: Computational and Environmental Challenges in Environmental Modelling. Elsevier (2006)Google Scholar
  20. 20.
    Zlatev, Z., Dimov, I., Georgiev, K.: Three-dimensional version of the Danish Eulerian Model. Zeitschrift für Angewandte Mathematik und Mechanik 76, 473–476 (1996)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Krassimir Georgiev
    • 1
  • Tzvetan Ostromsky
    • 1
  • Zahari Zlatev
    • 2
  1. 1.Institute of Information and Communication TechnologiesBulgarian Academy of SciencesSofiaBulgaria
  2. 2.National Environmental Research InstituteAarhus UniversityRoskildeDenmark

Personalised recommendations