Hybrid OpenMP/MPI anisotropic mesh smoothing

被引:13
|
作者
Gorman, G. J. [1 ]
Southern, J. [2 ]
Farrell, P. E. [1 ]
Piggott, M. D. [1 ]
Rokos, G. [1 ]
Kelly, P. H. J. [1 ]
机构
[1] Imperial Coll London, Appl Modelling & Computat Grp, Dept Earth Sci & Engn, London SW7 2AZ, England
[2] Fujitsu Labs Europe, Hayes UB4 8FE, Middx, England
来源
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE, ICCS 2012 | 2012年 / 9卷
基金
英国工程与自然科学研究理事会;
关键词
unstructured mesh; mesh smoothing; ccNUMA; parallel; OpenMP; MPI; JACOBIAN MATRIX; OPTIMIZATION; QUANTITIES; FRAMEWORK; QUALITY; NORM;
D O I
10.1016/j.procs.2012.04.166
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Mesh smoothing is an important algorithm for the improvement of element quality in unstructured mesh finite element methods. A new optimisation based mesh smoothing algorithm is presented for anisotropic mesh adaptivity. It is shown that this smoothing kernel is very effective at raising the minimum local quality of the mesh. A number of strategies are employed to reduce the algorithm's cost while maintaining its effectiveness in improving overall mesh quality. The method is parallelised using hybrid OpenMP/MPI programming methods, and graph colouring to identify independent sets. Different approaches are explored to achieve good scaling performance within a shared memory compute node.
引用
收藏
页码:1513 / 1522
页数:10
相关论文
共 50 条
  • [41] Hybrid MPI plus OpenMP Parallelization of Scramjet Simulation with Hypergraph Partitioning
    Zeng Yao-yuan
    Zhao Wen-tao
    Wang Zheng-hua
    ADVANCES IN MANUFACTURING SCIENCE AND ENGINEERING, PTS 1-4, 2013, 712-715 : 1294 - +
  • [42] Solving the symmetric tridiagonal eigenproblem using MPI/OpenMP hybrid parallelization
    Zhao, YH
    Chen, J
    Chi, XB
    ADVANCED PARALLEL PROCESSING TECHNOLOGIES, PROCEEDINGS, 2005, 3756 : 164 - 173
  • [43] Hybrid MPI/OpenMP Parallel Linear Support Vector Machine Training
    Woodsend, Kristian
    Gondzio, Jacek
    JOURNAL OF MACHINE LEARNING RESEARCH, 2009, 10 : 1937 - 1953
  • [44] Enabling Low-Overhead Hybrid MPI/OpenMP Parallelism with MPC
    Carribault, Patrick
    Perache, Marc
    Jourdren, Herve
    BEYOND LOOP LEVEL PARALLELISM IN OPENMP: ACCELERATORS, TASKING AND MORE, PROCEEDINGS, 2010, 6132 : 1 - 14
  • [45] Parallel implementation of LS-DEM with hybrid MPI plus OpenMP
    Tan, Peng
    Sitar, Nicholas
    COMPUTERS AND GEOTECHNICS, 2024, 172
  • [46] An implementation of MPI and hybrid OpenMP/MPI parallelization strategies for an implicit 3D DDG solver
    He, Xiaofeng
    Wang, Kun
    Feng, Yiwei
    Lv, Lili
    Liu, Tiegang
    COMPUTERS & FLUIDS, 2022, 241
  • [47] Compile-Aided Type Correctness of Hybrid MPI-OpenMP Applications
    Hueck, Alexander
    Kreutzer, Sebastian
    Lehr, Jan-Patrick
    Bischof, Christian
    Protze, Joachim
    Terboven, Christian
    Mueller, Matthias S.
    IT PROFESSIONAL, 2022, 24 (02) : 45 - 51
  • [48] Study on MPI/OpenMP hybrid parallelism for Monte Carlo neutron transport code
    Liang, Jin-Gang
    Liu, Shi-Wen
    Xu, Qi
    Wang, Kan
    Yuanzineng Kexue Jishu/Atomic Energy Science and Technology, 2013, 47 (SUPPL.): : 654 - 659
  • [49] Enabling Mixed OpenMP/MPI Programming on Hybrid CPU/GPU Computing Architecture
    Liang, Tyng-Yeu
    Li, Hung-Fu
    Chiu, Jun-Yao
    2012 IEEE 26TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS & PHD FORUM (IPDPSW), 2012, : 2369 - 2377
  • [50] Directionally unsplit hydrodynamic schemes with hybrid MPI/OpenMP/GPU parallelization in AMR
    Schive, Hsi-Yu
    Zhang, Ui-Han
    Chiueh, Tzihong
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2012, 26 (04): : 367 - 377