Performance analysis of a 3D unstructured mesh hydrodynamics code on multi-core and many-core architectures

被引：2
作者：
Waltz, J.
Wohlbier, J. G.
Risinger, L. D.
Canfield, T. R.
Charest, M. R. J.
Long, A. R.
Morgan, N. R.
机构：
[1] X Computational Physics Division, Los Alamos National Laboratory
[2] Computational and Computer Sciences Division, Los Amos National Laboratory
[3] Formerly of Computational and Computer Sciences Division, Los Alamos National Laboratory
[4] Theoretical Division, Los Amos National Laboratory
[5] Computational Physics Division, Los Amos National Laboratory
来源：
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS | 2015年 / 77卷 / 06期
关键词：
unstructured grids; shock hydrodynamics; many-core architectures; threading; SHOCK HYDRODYNAMICS; SHARED-MEMORY; GRIDS; FLOW; MINIMIZATION; ALGORITHMS; SIMULATION; MACHINES; HARDWARE; SOLVERS;
D O I：
10.1002/fld.3982
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
Several next generation high performance computing platforms are or will be based on the so-called many-core architectures, which represent a significant departure from commodity multi-core architectures. A key issue in transitioning large-scale simulation codes from multi-core to many-core systems is closing the serial performance gap, that is, overcoming the large difference in single-core performance between multi-core and many-core systems. In this paper, we discuss how this problem was addressed for a 3D unstructured mesh hydrodynamics code, describe how Amdahl's law can be used to estimate performance targets and guide optimization efforts, and present timing studies performed on multi-core and many-core platforms. Published 2014. This article is a U.S. Government work and is in the public domain in the USA.
引用
收藏
页码：319 / 333
页数：15
相关论文
共 36 条
  • [1] Amdahl G.M., 1967, Validity of the single processor approach to achieving large scale computing capabilities. Proceedings of the Spring Joint Computer Conference, P483, DOI DOI 10.1145/1465482.1465560
  • [2] [Anonymous], 2007, SC 07 P 2007 ACM IEE
  • [3] [Anonymous], 1993, Similarity and dimensional methods in mechanics
  • [4] On the choice of wavespeeds for the HLLC Riemann solver
    Batten, P
    Clarke, N
    Lambert, C
    Causon, DM
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1997, 18 (06) : 1553 - 1570
  • [5] Chapman B., 2008, Using OpenMP
  • [6] Performance comparison of data-reordering algorithms for sparse matrix-vector multiplication in edge-based unstructured grid computations
    Coutinho, ALGA
    Martins, MAD
    Sydenstricker, RM
    Elias, RN
    [J]. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 2006, 66 (03) : 431 - 460
  • [7] Dong T, 2014, STEP ENERGY EF UNPUB
  • [8] A two-dimensional unstructured cell-centered multi-material ALE scheme using VOF interface reconstruction
    Galera, Stephane
    Maire, Pierre-Henri
    Breil, Jerome
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2010, 229 (16) : 5755 - 5787
  • [9] Hager G., 2010, INTRO HIGH PERFORMAN, DOI [10.1201/EBK1439811924, DOI 10.1201/EBK1439811924]
  • [10] Hemsoth N, 2013, HPC WIRE
1234