Advertisement

Numerical Library Based on Hierarchical Domain Decomposition

  • Ryuji Shioya
  • Masao Ogino
  • Yoshitaka Wada
  • Kohei Murotani
  • Seiichi Koshizuka
  • Hiroshi Kawai
  • Shin-ichiro Sugimoto
  • Amane Takei
Chapter

Abstract

We have been developing an open-source computer-aided engineering (CAE) software, ADVENTURE, which is a general-purpose parallel finite element analysis system and can simulate a large-scale analysis model with supercomputer. For supercomputer architecture such as an exa-scale system, to obtain high computational efficiency for software that requires large-scale numerical calculation data processing, a programming model that considers the hierarchical structure of hardware, such as a microprocessor and memory, is necessary. From this point of view, ADVENTURE system was developed using the hierarchical domain decomposition method (HDDM) as the basic technology for a large-scale data system. HDDM is technology developed by ourselves mainly for numerical analysis method. In particular, we have developed application-specific system software that can obtain high performance by focusing on simulation of continuum mechanics by finite element method (FEM) and particle method which are highly demanded by academic research and industry. We have developed four research items “DDM I/O (input/output) library,” “DDM solver library,” “DSL for continuum mechanics,” and “continuous mechanics simulator.” The software, which is the result of our research, is released as open-source software on the sub-project page in the ADVENTURE project homepage. In this chapter, some of those libraries are described in detail.

References

  1. 1.
    Yagawa, G., Shioya, R.: Parallel finite elements on a massively parallel computer with domain decomposition. Comput. Syst. Eng. 4, 495–503 (1994)CrossRefGoogle Scholar
  2. 2.
  3. 3.
    LexADV: Development of a numerical library based on hierarchical domain decomposition for post petascale simulation (2018). http://adventure.sys.t.u-tokyo.ac.jp/lexadv/index.html
  4. 4.
    Glowinski, R., Dinh, Q. V., Periaux, J.: Domain decomposition methods for nonlinear problems in fluid dynamics. Comput. Methods Appl. Mech. Eng. 40, 27–109 (1983)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Quarteroni, A., Vali, A.: Domain Decomposition Methods for Par-tial Differential Equations (Clarendon Press, Oxford, 1999)Google Scholar
  6. 6.
    Yoshimura, S., Shioya, R., Noguchi, H., Miyamura, T.: Advanced general-purpose computational mechanics system for large scale analysis and design. J. Comput. Appl. Math. 149, 279–296 (2002)CrossRefGoogle Scholar
  7. 7.
    Amestoy, P.R., Duf, I.S. and L’Excellent, J.-Y.: Multifrontal parallel distributed symmetric and unsymmetric solvers. Comput. Methods Appl. Mech. Eng. 184, 501–520 (2000)CrossRefGoogle Scholar
  8. 8.
    Fujii, A., Nishida, A., Oyanagi Y.: Evaluation of parallel aggregate creation orders: smoothed aggregation algebraic multigrid method. In: High Performance Computational Science and Engineering, pp. 99–122. Springer, New York (2005)Google Scholar
  9. 9.
    Ogino, M., Shioya, R., Kanayama, H.: An inexact balancing preconditioner for large-scale structural analysis. J. Comput. Sci. Tech. 2, 150–161 (2008)CrossRefGoogle Scholar
  10. 10.
    Mandel, J.: Balancing domain decomposition. Commun. Numer. Methods Eng. 9, 233–241 (1993)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Okuda, H., et al.: Parallel Finite Element Analysis Platform for the Earth Simulator: GeoFEM. Lecture Notes in Computer Science, vol. 2659, pp. 773–780. Springer, Berlin/Heidelberg (2003)Google Scholar
  12. 12.
    Dongarra, J., et al.: The international exascale software project roadmap. Int. J. High Perform. Comput. Appl. 25, 3–60 (2011)CrossRefGoogle Scholar
  13. 13.
    Fabian, N., et al.: The paraview coprocessing library: a scalable, general purpose in situ visualization library. IEEE Symposium on Large Data Analysis and Visualization, Providence, pp. 89–96 (2011)Google Scholar
  14. 14.
    Wada, Y., et al.: High-resolution visualization library for ex-ascale supercomputer. In: Dobashi, Y., Ochiai, H. (eds.) Mathematical Progress in Expressive Image Synthesis III. Springer Science Mathematics for Industry, pp. 83–94. Springer, Singapore (2016)Google Scholar
  15. 15.
    Wada, Y., et al.: Development of LexADV_VSCG library for a viewer with high resolution image. In: Proceedings of 21th JSCES Conference, vol. 21, 2p (2016)Google Scholar
  16. 16.
    Koshizuka, S., Oka, Y.: Moving-particle semi-implicit method for frag-mentation of incompressible fluid. Nucl. Sci. Eng. 123, 421–434 (1996)CrossRefGoogle Scholar
  17. 17.
    Murotani, K., et al.: Development of hierarchical domain decomposition explicit MPS method and application to large-scale tsunami analysis with floating objects. J. Adv. Simul. Sci. Eng. 1(1), 16–35 (2014)CrossRefGoogle Scholar
  18. 18.
    Koshizuka, S., Nobe, A., Oka, Y.: Numerical analysis of breaking waves using the moving particle semi-implicit method. Int. J. Numer. Methods Fluids 26, 751–769 (1998)CrossRefGoogle Scholar
  19. 19.
    Kawai, H., et al.: AutoMT, a library for tensor operations and its performance evaluation for solid continuum mechanics applications. Mech. Eng. Lett. 1, Paper No. 15-00349 (2015)CrossRefGoogle Scholar
  20. 20.
    Holzapfel, G.A.: Nonlinear Solid Mechanics – A Continuum Approach for Engineering. Wiley, New York (2000)zbMATHGoogle Scholar
  21. 21.
    Bonet, J., Wood, R.D.: Nonlinear Continuum Mechanics for Finite Element Analysis. Cambridge University Press, Cambridge/New York (2008)CrossRefGoogle Scholar
  22. 22.
    Kanayama, H., Zheng H., Maeno, N.: A domain decomposition method for large-scale 3-D nonlinear magnetostatic problems. Theor. Appl. Mech. Jpn. 52, 247–254 (2003)Google Scholar
  23. 23.
    Sugimoto, S., Ogino, M., Kanayama, H., Yoshimura, S.: Introduction of a direct method at subdomains in non-linear magnetostatic analysis with HDDM. In: 2010 International Conference on Broadband, Wireless Computing, Communication and Applications, Fukuoka, pp. 304–309 (2010)Google Scholar
  24. 24.
    Kanayama, H., Sugimoto, S.: Effectiveness A-ϕ method in a parallel computing with an iterative domain decomposition method. IEEE Trans. Magn. 42(4), 539–542 (2006)CrossRefGoogle Scholar
  25. 25.
    Sugimoto, S., et al.: Improvement of convergence in time-harmonic eddy current analysis with hierar-chical domain decomposition method. Trans. Jpn. Soc. Simul. Tech. (in Japanese) 7(1), 110–17 (2015)Google Scholar
  26. 26.
    Sugimoto, S., Takei, A., Ogino, M.: Finite element analysis with tens of billions of degrees of freedom in a high-frequency electromagnetic field. Mech. Eng. Lett. 3, Paper No. 16-0067 (2017)CrossRefGoogle Scholar
  27. 27.
    Takei, A., Yoshimura, S., Kanayama, H.: Large scale parallel finite element analyses of high frequency electromagnetic field in commuter trains. Comput. Model. Eng. Sci. 31(1), 13–24 (2008)MathSciNetzbMATHGoogle Scholar
  28. 28.
    Kanai, Y.: Description of TEAM workshop problem 29: whole body cavity resonator. Technical report TEAM Workshop in Tucson (1998)Google Scholar
  29. 29.
    Sugimoto, S., Ogino, M., Kanayama H., Takei, A.: Hierarchical domain decomposition method for devices including moving bodies. J. Adv. Simul. Sci. Eng. 4(1), 99–116 (2018)CrossRefGoogle Scholar
  30. 30.
    NICT EMC group home page (2018). http://emc.nict.go.jp/bio/index.html
  31. 31.
    Conil, E., et al.: Variability analysis of SAR from 20 MHz to 2.4 GHz for different adult and child models using finite-difference time-domain. Phys. Med. Biol. 53, 1511–1525 (2008)CrossRefGoogle Scholar
  32. 32.
    Karypis, G., Kumar, V.: A fast and highly quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1999)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Ryuji Shioya
    • 1
  • Masao Ogino
    • 2
  • Yoshitaka Wada
    • 3
  • Kohei Murotani
    • 4
  • Seiichi Koshizuka
    • 5
  • Hiroshi Kawai
    • 1
  • Shin-ichiro Sugimoto
    • 6
  • Amane Takei
    • 7
  1. 1.Toyo UniversityTokyoJapan
  2. 2.Nagoya UniversityNagoyaJapan
  3. 3.Kindai UniversityHigashi-osakaJapan
  4. 4.Railway Technical Research InstituteTokyoJapan
  5. 5.University of TokyoTokyoJapan
  6. 6.Hachinohe Institute of TechnologyHachinoheJapan
  7. 7.Miyazaki UniversityMiyazakiJapan

Personalised recommendations