Modular fem framework “ModFEM” for generic scientific parallel simulations

• Autorzy: Michalik K. , Banaś K. , Płaszewski P. , Cybułka P.
• Języki publikacji: EN

Abstrakty

EN

We present the design for, and implementation of, aflexible and robust parallel modular finite element (FEM) framework called ModFEM. The designis based on reusable modules which use narrow and well-defined interfaces to cooperate. At the top of the architecture, there are problem - dependent modules. Problem - - dependent modules can be additionally grouped together by“super-modules”. The structure allows for reusing the sequential code for parallel environments, and also supports solving multi-physics and multi-scale problems.

Słowa kluczowe

EN

FEM; modules; parallelism; grid; framework

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2013
• Tom: Vol. 14 (3)
• Strony: 513--528
• Opis fizyczny: Bibliogr. 17 poz., rys.

Twórcy

autor

Michalik K.

• ACC Cyfronet AGH, ul. Nawojki 11, 30-950 Kraków 61, P.O.Box 386

autor

Banaś K.

• AGH University of Science and Technology, Krakow

autor

Płaszewski P.

• AGH University of Science and Technology, Krakow,

autor

Cybułka P.

• AGH University of Science and Technology, Krakow,

Bibliografia

• [1] DednerA.,Klofkorn M.N.M.O.:A general object oriented framework for discretizing nonlinear evolution equations. Proc. of The 1st Kazakh-German Advanced Research Workshop on Computational Science and High Performance Computing, 2005.
• [2] Anders Logg, Kent-Andre Mardal G. W.: Automated solution of differential equations by the finite element method Lecture Notes in Computational Science and Engineering vol.84, 2012.
• [3] LaSalle D., Karypis G.: Multi-Threaded Graph Partitioning. 27th IEEE International Parallel & Distributed Processing Symposium, 2013.
• [4] Shephard M.S., Seol S.: Flexible Distributed Mesh Data Structure for Parallel Adaptive Analysis. Advanced Computational Infrastructures for Parallel and Distributed Adaptive Applications, chapter 19, Wiley 2009.
• [5] Oliker L., Biswas R., Gabow H.N.: Parallel tetrahedral mesh adaptation with dynamic loadbalancing Parallel Computing, 26:1583–1608,1999
• [6] Banaś K.: A model for parallel adaptive finite element software. Domain Decomposition Methods in Science and Engineering, Vol. 40 of Lecture Notes in Computational Science and Engineering, pp.159–166, 2004.
• [7] BanaśK.: Amodular design for parallel adaptive finite element computational kernels. Computational Science–ICCS2004, 4th International Conference, Krakow, Poland, June2004, Proc., Part II, vol. 3037 of Lecture Notes in Computer Science, pp.155–162, 2004.
• [8] Banaś K.: Parallelization of large scale adaptive finite element computations. Parallel Processing and Applied Mathematics, Proc. of Vth International Conference, PPAM2003, Czestochowa, Poland, vol. 3019, pp. 431–438, 2004.
• [9] Bangerth W., Hartmann R., Kanschat G.: deal.II–Ageneral purpose object oriented finite element library. ACM Trans. Math. Softw., 33(4):24/1–24/27, 2007.
• [10] Jaein Jeong T.G., WuX.: Aninter active parallel multigrid fem simulator. Medical Simulation, Vol. 3078 of Lecture Notes in Computational Science, pp.124–133, 2004.
• [11] Banaś K., et al.: Towards using adaptive hybrid meshes in FEM simulations of flow in artificial heart chambers. Procedia Computer Science; ISSN 1877-0509. vol.1,pp. 2037–2045, 2011.
• [12] Banaś K., Michalik K.: Design and development of an adaptive mesh manipula- tion module for detailed FEM simulation of flows. Procedia Computer Science; ISSN1877-0509.vol.1, pp. 2037–2045, 2010.
• [13] Kopernik A.M.: Two-scale finite element model of multilayer blood chamber of polvad-ext.Archives of Civil and Mechanical Engineering/PolishAcademy of Sciences. Wrocław Branch, Wrocław University of Technology; ISSN1644-9665, pp.178–185, 2010.
• [14] Patzak B.,Rypl D.: Object-oriented, parallel finite element framework with dynamic load balancing. Advances in Engineering Software vol.47, pp.35–50, 2012.
• [15] Cybułka P.,et al.: Simulation of droplet motion in welding arcs as a case study of remeshing. Computer Methods in Materials Science: quarterly / Akademia Górniczo-Hutnicza;ISSN1641-8581, page 381–386, 2011.
• [16] Resch M.M.: Sustained Simulation Performance 2012. Proc. of the joint Work-shop on High Performance Computing on Vector Systems, Stuttgart (HLRS), and Work shop on Sustained Simulation Performance,Tohoku University. Springer Berlin Heidelberg, 2012.
• [17] Selim G.,Akl M. N.:Parallel Computing. The Future of Parallel Computation. Springer London, 2009.