ParMooN-A modernized program package based on mapped finite elements

被引:37
作者
Wilbrandt, Ulrich [1 ]
Bartsch, Clemens [1 ]
Ahmed, Naveed [1 ]
Alia, Najib [1 ]
Anker, Felix [1 ]
Blank, Laura [1 ]
Caiazzo, Alfonso [1 ]
Ganesan, Sashikumaar [2 ]
Giere, Swetlana [1 ]
Matthies, Gunar [3 ]
Meesala, Raviteja [2 ]
Shamim, Abdus [2 ]
Venkatesan, Jagannath [2 ]
John, Volker [1 ,4 ]
机构
[1] Leibniz Inst Forsch Verbund Berlin eV WIAS, Weierstrss Inst Appl Anal & Stochast, Mohrenstr 39, D-10117 Berlin, Germany
[2] Indian Inst Sci, Dept Computat & Data Sci, Bangalore 560012, Karnataka, India
[3] Tech Univ Dresden, Inst Numer Math, Dept Math, D-01062 Dresden, Germany
[4] Free Univ Berlin, Dept Math & Comp Sci, Arnimallee 6, D-14195 Berlin, Germany
关键词
Mapped finite elements; Geometric multigrid method; Parallelization; PARALLEL; DISCRETIZATIONS; SOLVER;
D O I
10.1016/j.camwa.2016.12.020
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
PARMooN is a program package for the numerical solution of elliptic and parabolic partial differential equations. It inherits the distinct features of its predecessor MooNMD (John and Matthies, 2004): strict decoupling of geometry and finite element spaces, implementation of mapped finite elements as their definition can be found in textbooks, and a geometric multigrid preconditioner with the option to use different finite element spaces on different levels of the multigrid hierarchy. After having presented some thoughts about in-house research codes, this paper focuses on aspects of the parallelization for a distributed memory environment, which is the main novelty of PARMooN. Numerical studies, performed on compute servers, assess the efficiency of the parallelized geometric multigrid preconditioner in comparison with some parallel solvers that are available in the library PETSc. The results of these studies give a first indication whether the cumbersome implementation of the parallelized geometric multigrid method was worthwhile or not. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:74 / 88
页数:15
相关论文
共 34 条
  • [1] Alns Martin, 2015, ARCH NUMER SOFTW, V3
  • [2] Hybrid scheduling for the parallel solution of linear systems
    Amestoy, PR
    Guermouche, A
    L'Excellent, JY
    Pralet, S
    [J]. PARALLEL COMPUTING, 2006, 32 (02) : 136 - 156
  • [3] A fully asynchronous multifrontal solver using distributed dynamic scheduling
    Amestoy, PR
    Duff, IS
    L'Excellent, JY
    Koster, J
    [J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2001, 23 (01) : 15 - 41
  • [4] [Anonymous], 2015, MPI MESSAGE PASSING
  • [5] [Anonymous], 1978, STUDIES MATH ITS APP
  • [6] [Anonymous], 2009, METIS UNSTRUCTURED G
  • [7] An assessment of discretizations for convection-dominated convection-diffusion equations
    Augustin, Matthias
    Caiazzo, Alfonso
    Fiebach, Andre
    Fuhrmann, Juergen
    John, Volker
    Linke, Alexander
    Umla, Rudolf
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2011, 200 (47-48) : 3395 - 3409
  • [8] Ayachit U., 2015, PARAVIEW GUIDE PARAL
  • [9] Balay S, 1997, MODERN SOFTWARE TOOLS FOR SCIENTIFIC COMPUTING, P163
  • [10] Balay Satish, 2016, ANL9511 ARG NAT LAB