Automated Parallelization of a Simulation Method of Elastic Wave Propagation in Media with Complex 3D Geometry Surface on High-Performance Heterogeneous Clusters

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10421)


The paper considers application of DVM and SAPFOR in order to automate mapping of 3D elastic waves simulation method on high-performance heterogeneous clusters. A distinctive feature of the proposed method is the use of a curved three-dimensional grid, which is consistent with the geometry of free surface. Usage of curved grids considerably complicates both manual and automated parallelization. Technique to map curved grid on a structured grid has been presented to solve this problem. The sequential program based on the finite difference method on a structured grid, has been parallelized using Fortran-DVMH language. Application of SAPFOR analysis tools simplified this parallelization process. Features of automated parallelization are described. Authors estimate efficiency and acceleration of the parallel program and compare performance of the DVMH based program with a program obtained after manual parallelization using MPI programming technology.


Automation of parallelization Heterogeneous computational cluster 3D modeling Curvilinear grid GPU Xeon Phi 


  1. 1.
    Glinskiy, B.M., Karavaev, D.A., Kovalevskiy, V.V., Martynov, V.N.: Numerical modeling and experimental research of the “Karabetov Mountain” mud volcano by vibroseismic methods (in Russian). Numer. Methods Program. 11, 95–104 (2010)Google Scholar
  2. 2.
    Graves, R.W.: Simulating seismic wave propagation in 3D elastic media using staggered grid finite differences. Bull. Seismol. Soc. Am. 86(4), 1091–1106 (1996)Google Scholar
  3. 3.
    Liseykin, V.D.: Difference Grid, Theory and Applications (in Russian), p. 3254. FUE Publishing House SB RAS, Novosibirsk (2014)Google Scholar
  4. 4.
    Khakimzyanov, G.S., Shokin, Y.I.: Difference schemes on adaptive grids (in Russian). Publishing Center NGU, Novosibirsk (2005)Google Scholar
  5. 5.
    Appelo, D., Petersson, N.A.: A stable finite difference method for the elastic wave equation on complex geometries with free surfaces. Commun. Comput. Phys. 5(1), 84–107 (2009)MathSciNetzbMATHGoogle Scholar
  6. 6.
    Komatitsch, D., Erlebacher, G., Goddeke, D., Michea, D.: High-order finite-element seismic wave propagation modeling with MPI on a large GPU cluster. J. Comput. Phys. 229(20), 7692–7714 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Karavaev, D.A., Glinsky, B.M., Kovalevsky, V.V.: A technology of 3D elastic wave propagation simulation using hybrid supercomputers. In: CEUR Workshop Proceedings 1st Russian Conference on Supercomputing Days 2015, vol. 1482, pp. 26–33 (2015)Google Scholar
  8. 8.
  9. 9.
    Sah, S., Vaidya, V.G.: Review of parallelization tools and introduction to easypar. Int. J. Comput. Appl. 56(12), 17–29 (2012)Google Scholar
  10. 10.
    Bakhtin, V.A., Borodich, I.G., Kataev, N.A., Klinov, M.S., Kovaleva, N.V., Krukov, V.A., Podderugina, N.V.: Interaction with the programmer in the system for automation parallelization SAPFOR. Vestnik of Lobachevsky State University of Nizhni Novgorod 5(2), 242–245 (2012). Nizhni Novgorod State University Press, Nizhni Novgorod (in Russian)Google Scholar
  11. 11.
    ParaWise Widening Accessibility to Efficient and Scalable Parallel Code. Parallel Software Products White Paper WP-2004-01 (2004)Google Scholar
  12. 12.
    Konovalov, N.A., Krukov, V.A., Mikhajlov, S.N., Pogrebtsov, A.A.: Fortan DVM: a language for portable parallel program development. Program. Comput. Softw. 21(1), 35–38 (1995)zbMATHGoogle Scholar
  13. 13.
    Bakhtin, V.A., Klinov, M.S., Krukov, V.A., Podderugina, N.V., Pritula, M.N., Sazanov, Y.: Extension of the DVM-model of parallel programming for clusters with heterogeneous nodes. Bulletin of South Ural State University. Series: Mathematical Modeling, Programming and Computer Software, vol. 18 (277), no. 12, pp. 82–92. Publishing of the South Ural State University, Chelyabinsk (2012). (in Russian)Google Scholar
  14. 14.
    Kataev, N.A.: Static analysis of sequential programs in the automatic parallelization environment SAPFOR. Vestnik of Lobachevsky University of Nizhni Novgorod, vol. 5(2), pp. 359–366. Nizhni Novgorod State University Press, Nizhni Novgorod (2012)Google Scholar
  15. 15.
    Exmaple of program parallelization using DVMH-model.
  16. 16.
    Heterogeneous cluster K100.
  17. 17.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Keldysh Institute of Applied Mathematics RASMoscowRussia
  2. 2.Moscow State UniversityMoscowRussia
  3. 3.Institute of Computational Mathematics and Mathematical Geophysics SB RASNovosibirskRussia

Personalised recommendations