Advertisement

On the Parallel Strategies in Mathematical Modeling

  • Valery Il’inEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 753)

Abstract

The article considers parallel strategies and tactics at different stages of mathematical modeling. These technological steps include geometrical and functional modeling, discretization and approximation, algebraic solvers and optimization methods for inverse problems, postprocessing and visualization of numerical results, as well as decision-making systems. Scalable parallelism can be provided by combined application of MPI tools, multi-thread computing, vectorization, and the use of graphics accelerators. The general method to achieve high-performance computing consists in minimizing data communications, which are the most time and energy consuming. The construction of efficient parallel algorithms and code optimization is based on various approaches at different levels of computational schemes. The implementation of the biggest interdisciplinary direct and inverse problems in cloud computing technologies is considered. The corresponding applied software with a long life cycle is represented as integrated environment oriented to large groups of end users.

Keywords

Scalable parallelism Domain decomposition Runtime Communications Multi-thread computing Vectorization Exchange buffers Hierarchical memory Speedup Accelerators 

References

  1. 1.
    ANSYS - Simulation Driven Product Development. http://www.ansys.com
  2. 2.
    Logg, F., Mardal, K.-A., Wells, G.N. (eds.): Automated Solution of Partial Differential Equations by Finite Element Method: The FEniCS Book. Springer, Heidelberg (2011)Google Scholar
  3. 3.
    Schoberl, J.: Netgen - an advancing front 2D/3D mesh generator based on abstract rules. Comput. Vis. Sci. 1, 41–52 (1997). doi: 10.1007/s007910050004 CrossRefzbMATHGoogle Scholar
  4. 4.
  5. 5.
    Open FOAM - The Open Source Computational Fluid Dynamics (CFD) Toolbox. http://www.open-foam.com
  6. 6.
    DUNE Numerics. Distributed Unified Numerical Environment. http://www.dune-project.org
  7. 7.
    Il’in, V.P., Skopin, I.N.: Computational programming technologies. Programm. Comput. Softw. 37(4), 210–222 (2011). doi: 10.1134/s0361768811040037 CrossRefGoogle Scholar
  8. 8.
    Ilin, V.P.: Fundamental Issues of mathematical modeling. Herald Rus. Acad. Sci. 86, 118–126 (2016). doi: 10.1134/s101933161602009x CrossRefGoogle Scholar
  9. 9.
    AlgoWiki: Open encyclopedia of algorithm properties. http://algowiki-project.org
  10. 10.
    Il’in, V.P., Skopin, I.N.: About performance and intellectuality of supercomputer modeling. Program. Comput. Softw. 42, 5–16 (2016). doi: 10.1134/s0361768816010047 CrossRefGoogle Scholar
  11. 11.
    Golubeva, L.A., Il’in, V.P., Kozyrev, A.N.: Programming technologies in geometric aspects of mathematical modeling. Vestnik NGU. Seria: Inf. Tekhnol. 10, 25–33 (2012). (in Russian)Google Scholar
  12. 12.
    Il’in, V.P.: DELAUNAY: A technological environment for mesh generation. Siberian Zhurnal Indus. Math. 16, 83–97 (2013). (in Russian)zbMATHGoogle Scholar
  13. 13.
    Butygin, D.S., Il’in, V.P.: Chebyshev: Principles of automation of algorithm construction in an integrated environment for mesh approximations of initial boundary value problems. In: Proceedings of International Conference on Parallel Computational Technologies 2014, Izd. YuUrGU, Chelyabinsk, pp. 42–50 (2014). (in Russian)Google Scholar
  14. 14.
    Intel Math. Kernel Library. http://software.intel.com/en-us/intel-mkl
  15. 15.
    Butyugin, D.S., Gurieva, Y.L., Il’in, V.P., et al.: Functionality and technologies of algebraic solvers in Krylov’s library. Mathematical Modeling, Programming & Computer software, pp. 76–86. Bulletin of south Ural state university, Russain Federation (2013). (in Russian)Google Scholar
  16. 16.
    Konshin, I.N.: Parallel Computational Models to Estimate an Actual Speedup of Analyzed Algorithm. Russian Supercomputing Days: Proceedings of the International Conference, pp. 269–280. MSU Publ. (2016) (in Russian). doi: 10.1007/978-3-319-55669-7_24
  17. 17.
    Dolean, V., Jolivet, P., Nataf, F.: An Introduction to Domain Decomposition Methods: algorithms, theory and parallel implementation. doi: 10.1137/1.9781611974065.. https://archives-ouvertes.fr/cel-01100932
  18. 18.
    Il’in, V.P.: Problems of parallel solution of large systems of linear algebraic equations. J. Math. Sci. 216, 795–804 (2016). doi: 10.1007/s10958-016-2945-4 CrossRefzbMATHGoogle Scholar
  19. 19.
    Saad, Y., Sosonkina, M.: pARMS: A package for the parallel iterative solution of general large sparse linear systems user’s guide. Report UMSI 2004–8, Minnesota Supercomp. Inst., Univer. of Minnesota, MN (2004)Google Scholar
  20. 20.
    Gander, M.J.: 50 Years of Time Parallel Time Integration. doi: 10.1007/978-3-319-23321-5_3. http://www.unige.ch/~gander/Preprints/50YearsTimeParallel.pdf
  21. 21.
    Il’in, V.P.: Numeric solving of direct and inverse problems of electromagnetic prospecting. Sibirian Zhurnal of Vychislitelnoi Mathematiki 6, 381–394 (2003). (in Russian)Google Scholar
  22. 22.
    Il’in, V.P.: Component technologies of high-performance mathematical modeling. In: Proceedings of the International Conference on Parallel Computational Technologies - 2015 (UFU, IMM UrO RAN, Yekaterinburg), pp. 166–171 (2015). (in Russian)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Institute of Computational Mathematics and Mathematical Geophysics RASNovosibirsk State UniversityNovosibirskRussia

Personalised recommendations