A DYNAMIC MPI-OPENMP MODEL FOR STRUCTURED ADAPTIVE MESH REFINEMENT

被引：0
|
作者：
Rantakokko, Jarmo [1 ]
机构：
[1] Uppsala Univ, Dept Informat Technol, Sci Comp, Box 337, S-75105 Uppsala, Sweden
来源：
PARALLEL PROCESSING LETTERS | 2005年 / 15卷 / 1-2期
关键词：
OpenMP; PDE; Structured Adaptive Mesh Refinement;
D O I：
10.1142/S0129626405002040
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
We compare experimentally different parallelization models using MPI and OpenMP for structured adaptive mesh refinement on a shared-memory parallel computer, a Sun-Fire 15K. Due to the dynamic properties of the mesh no static parallelization model with fixed number of processes and threads performs best in all stages. Different combinations of MPI and OpenMP are preferable in different settings of the application and grid hierarchy. We suggest a new dynamic approach using a mixed MPI-OpenMP model that adapts the number of threads during run time and gives good performance in all stages throughout the whole run as the solution state changes, i.e. the resolution in the computational grid changes.
引用
收藏
页数：11
相关论文
共 50 条
  • [21] MPI-OpenMP Algorithms for the Parallel Space-Time Solution of Time Dependent PDEs
    Haynes, Ronald D.
    Ong, Benjamin W.
    DOMAIN DECOMPOSITION METHODS IN SCIENCE AND ENGINEERING XXI, 2014, 98 : 179 - 187
  • [22] A hybrid MPI-OpenMP implementation of an implicit finite-element code on parallel architectures
    Mahinthakumar, G
    Saied, F
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2002, 16 (04): : 371 - 393
  • [23] In Search of the Best MPI-OpenMP Distribution for Optimum Intel-MIC Cluster Performance
    Utrera, Gladys
    Gil, Marisa
    Martorell, Xavier
    PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS 2015), 2015, : 429 - 435
  • [24] Addressing spatiotemporal and computational heterogeneity in structured adaptive mesh refinement
    Chandra, Sumir
    Parashar, Manish
    COMPUTING AND VISUALIZATION IN SCIENCE, 2006, 9 (03) : 145 - 163
  • [25] Hierarchical Partitioning Techniques for Structured Adaptive Mesh Refinement Applications
    Xiaolin Li
    Manish Parashar
    The Journal of Supercomputing, 2004, 28 : 265 - 278
  • [26] Hierarchical partitioning techniques for structured adaptive mesh refinement applications
    Li, XL
    Parashar, M
    JOURNAL OF SUPERCOMPUTING, 2004, 28 (03): : 265 - 278
  • [27] Composite matrix construction for structured grid adaptive mesh refinement
    Adams, Mark F.
    Cornford, Stephen L.
    Martin, Daniel F.
    McCorquodale, Peter
    COMPUTER PHYSICS COMMUNICATIONS, 2019, 244 : 35 - 39
  • [28] An MPI-OpenMP Hybrid Parallel H-LU Direct Solver for Electromagnetic Integral Equations
    Guo, Han
    Hu, Jun
    Nie, Zaiping
    INTERNATIONAL JOURNAL OF ANTENNAS AND PROPAGATION, 2015, 2015
  • [29] A hybrid MPI-OpenMP parallel implementation for pseudospectral simulations with application to Taylor-Couette flow
    Shi, Liang
    Rampp, Markus
    Hof, Bjoern
    Avila, Marc
    COMPUTERS & FLUIDS, 2015, 106 : 1 - 11
  • [30] Enhanced Hybrid MPI-OpenMP Parallel Electromagnetic Simulations Based on Low-Rank Compressions
    Wang, Xiren
    Jandhyala, Vikram
    2008 IEEE INTERNATIONAL SYMPOSIUM ON ELECTROMAGNETIC COMPATIBILITY, VOLS 1-3, 2008, : 803 - 807
12345