DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Abstract

SUMMARY 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.

Authors:
 [1];  [2];  [3];  [4];  [5];  [2];  [5]
  1. X Computational Physics Division Los Alamos National Laboratory USA
  2. Computational and Computer Sciences Division Los Amos National Laboratory USA
  3. Formerly of Computational and Computer Sciences Division Los Alamos National Laboratory USA
  4. Theoretical Division Los Amos National Laboratory USA
  5. Computational Physics Division Los Amos National Laboratory USA
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1400497
Resource Type:
Publisher's Accepted Manuscript
Journal Name:
International Journal for Numerical Methods in Fluids
Additional Journal Information:
Journal Name: International Journal for Numerical Methods in Fluids Journal Volume: 77 Journal Issue: 6; Journal ID: ISSN 0271-2091
Publisher:
Wiley Blackwell (John Wiley & Sons)
Country of Publication:
United Kingdom
Language:
English

Citation Formats

Waltz, J., Wohlbier, J. G., Risinger, L. D., Canfield, T. R., Charest, M. R. J., Long, A. R., and Morgan, N. R. Performance analysis of a 3D unstructured mesh hydrodynamics code on multi‐core and many‐core architectures. United Kingdom: N. p., 2014. Web. doi:10.1002/fld.3982.
Waltz, J., Wohlbier, J. G., Risinger, L. D., Canfield, T. R., Charest, M. R. J., Long, A. R., & Morgan, N. R. Performance analysis of a 3D unstructured mesh hydrodynamics code on multi‐core and many‐core architectures. United Kingdom. https://doi.org/10.1002/fld.3982
Waltz, J., Wohlbier, J. G., Risinger, L. D., Canfield, T. R., Charest, M. R. J., Long, A. R., and Morgan, N. R. Thu . "Performance analysis of a 3D unstructured mesh hydrodynamics code on multi‐core and many‐core architectures". United Kingdom. https://doi.org/10.1002/fld.3982.
@article{osti_1400497,
title = {Performance analysis of a 3D unstructured mesh hydrodynamics code on multi‐core and many‐core architectures},
author = {Waltz, J. and Wohlbier, J. G. and Risinger, L. D. and Canfield, T. R. and Charest, M. R. J. and Long, A. R. and Morgan, N. R.},
abstractNote = {SUMMARY 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.},
doi = {10.1002/fld.3982},
journal = {International Journal for Numerical Methods in Fluids},
number = 6,
volume = 77,
place = {United Kingdom},
year = {Thu Nov 27 00:00:00 EST 2014},
month = {Thu Nov 27 00:00:00 EST 2014}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1002/fld.3982

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Microfluidics simulation using adaptive unstructured grids
journal, January 2004

  • Waltz, Jacob
  • International Journal for Numerical Methods in Fluids, Vol. 46, Issue 9
  • DOI: 10.1002/fld.753

Verification of a three-dimensional unstructured finite element method using analytic and manufactured solutions
journal, July 2013


The Impact of Hardware Gather/Scatter on Sparse Gaussian Elimination
journal, March 1988

  • Lewis, John G.; Simon, Horst D.
  • SIAM Journal on Scientific and Statistical Computing, Vol. 9, Issue 2
  • DOI: 10.1137/0909019

The numerical simulation of two-dimensional fluid flow with strong shocks
journal, April 1984


Restoration of the contact surface in the HLL-Riemann solver
journal, July 1994

  • Toro, E. F.; Spruce, M.; Speares, W.
  • Shock Waves, Vol. 4, Issue 1
  • DOI: 10.1007/BF01414629

Exploring Traditional and Emerging Parallel Programming Models Using a Proxy Application
conference, May 2013

  • Karlin, Ian; Bhatele, Abhinav; Keasler, Jeff
  • 2013 IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2013 IEEE 27th International Symposium on Parallel and Distributed Processing
  • DOI: 10.1109/IPDPS.2013.115

Parallelizing the construction of indirect access arrays for shared-memory machines
journal, August 1998


On the Choice of Wavespeeds for the HLLC Riemann Solver
journal, November 1997


Parallel adaptive refinement for unsteady flow calculations on 3D unstructured grids
journal, August 2004

  • Waltz, Jacob
  • International Journal for Numerical Methods in Fluids, Vol. 46, Issue 1
  • DOI: 10.1002/fld.674

Handling tens of thousands of cores with industrial/legacy codes: Approaches, implementation and timings
journal, October 2013


Renumbering strategies for unstructured-grid solvers operating on shared-memory, cache-based parallel machines
journal, September 1998


Matrix Profile and Wavefront Reduction Based on the Graph Theory and Wavefront Minimization
journal, April 1996


Derived data structure algorithms for unstructured finite element meshes
journal, January 2002

  • Waltz, Jacob
  • International Journal for Numerical Methods in Engineering, Vol. 54, Issue 7
  • DOI: 10.1002/nme.453

A two-dimensional unstructured cell-centered multi-material ALE scheme using VOF interface reconstruction
journal, August 2010

  • Galera, Stéphane; Maire, Pierre-Henri; Breil, Jérôme
  • Journal of Computational Physics, Vol. 229, Issue 16
  • DOI: 10.1016/j.jcp.2010.04.019

Performance comparison of data-reordering algorithms for sparse matrix–vector multiplication in edge-based unstructured grid computations
journal, January 2006

  • Coutinho, Alvaro L. G. A.; Martins, Marcos A. D.; Sydenstricker, Rubens M.
  • International Journal for Numerical Methods in Engineering, Vol. 66, Issue 3
  • DOI: 10.1002/nme.1557

A Step towards Energy Efficient Computing: Redesigning a Hydrodynamic Application on CPU-GPU
conference, May 2014

  • Dong, Tingxing; Dobrev, Veselin; Kolev, Tzanio
  • 2014 IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2014 IEEE 28th International Parallel and Distributed Processing Symposium
  • DOI: 10.1109/IPDPS.2014.103

Minimization of indirect addressing for edge-based field solvers
journal, March 2002

  • Löhner, Rainald; Galle, Martin
  • Communications in Numerical Methods in Engineering, Vol. 18, Issue 5
  • DOI: 10.1002/cnm.494

Validity of the single processor approach to achieving large scale computing capabilities
conference, January 1967

  • Amdahl, Gene M.
  • Proceedings of the April 18-20, 1967, spring joint computer conference on - AFIPS '67 (Spring)
  • DOI: 10.1145/1465482.1465560

A nodal Godunov method for Lagrangian shock hydrodynamics on unstructured tetrahedral grids: A NODAL GODUNOV METHOD FOR LAGRANGIAN HYDRODYNAMICS
journal, June 2014

  • Waltz, J.; Morgan, N. R.; Canfield, T. R.
  • International Journal for Numerical Methods in Fluids, Vol. 76, Issue 3
  • DOI: 10.1002/fld.3928

Efficient gather and scatter operations on graphics processors
conference, January 2007

  • He, Bingsheng; Govindaraju, Naga K.; Luo, Qiong
  • Proceedings of the 2007 ACM/IEEE conference on Supercomputing - SC '07
  • DOI: 10.1145/1362622.1362684