Advertisement

HICFD: Highly Efficient Implementation of CFD Codes for HPC Many-Core Architectures

  • Achim Basermann
  • Hans-Peter Kersken
  • Andreas Schreiber
  • Thomas Gerhold
  • Jens Jägersküpper
  • Norbert Kroll
  • Jan Backhaus
  • Edmund Kügeler
  • Thomas Alrutz
  • Christian Simmendinger
  • Kim Feldhoff
  • Olaf Krzikalla
  • Ralph Müller-Pfefferkorn
  • Mathias Puetz
  • Petra Aumann
  • Olaf Knobloch
  • Jörg Hunger
  • Carsten Zscherp
Conference paper

Abstract

The objective of the German BMBF research project Highly Efficient Implementation of CFD Codes for HPC Many-Core Architectures (HICFD) is to develop new methods and tools for the analysis and optimization of the performance of parallel computational fluid dynamics (CFD) codes on high performance computer systems with many-core processors. In the work packages of the project it is investigated how the performance of parallel CFD codes written in C can be increased by the optimal use of all parallelism levels. On the highest level Message Passing Interface (MPI) is utilized. Furthermore, on the level of the many-core architecture, highly scaling, hybrid OpenMP/MPI methods are implemented. On the level of the processor cores the parallel Single Instruction Multiple Data (SIMD) units provided by modern CPUs are exploited.

Keywords

Computational Fluid Dynamic Message Passing Interface Single Instruction Multiple Data Computational Fluid Dynamic Code Message Passing Interface Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

This work has been supported by the German Federal Ministry of Education and Research (BMBF) under grant 01IH08012 A.

References

  1. 1.
    Alrutz, T., Aumann, P., Basermann, A. et al.: HICFD – Hocheffiziente Implementierung von CFD-Codes für HPC-Many-Core-Architekturen. In: Mitteilungen – Gesellschaft für Informatik e. V., http://www.fg-pars.gi-ev.de/fileadmin/gliederungen/fb-ti/fg-pars/Workshops/PARS/2009/PARS-Mitteilungen_2009.pdf, Parallel-Algorithmen und Rechnerstrukturen, ISSN 0177 - 0454, pp. 27–35 (2009)
  2. 2.
    Alrutz, T., Simmendinger, C., Gerhold, T: Efficiency enhancement of an unstructured CFD-Code on distributed computing systems. In: Parallel Computational Fluid Dynamics, Recent Advances and Future Directions, DEStech Publications, Inc., Lancaster, PA, USA (2010)Google Scholar
  3. 3.
    Basermann, A., Cortial-Goutaudier, F., Jaekel, U., Hachiya, K.: Parallel solution techniques for sparse linear systems in circuit simulation. In: Proceedings of the 4th International Workshop on Scientific Computing in Electrical Engineering, Series: Mathematics in Industry, ISBN 3-540-21372-4, Springer Berlin Heidelberg, Germany (2004)Google Scholar
  4. 4.
    Hohenauer, M., Engel, F., Leupers, R., Ascheid, G., Meyr, H.: A SIMD optimization framework for retargetable compilers. ACM Trans. Archit. Code Optim. 6(1), Article No. 2 (27 pages), (2009) doi: 10.1145/1509864.1509866Google Scholar
  5. 5.
    Karypis, G., Kumar, V.: ParMETIS: Parallel graph partitioning and sparse matrix ordering library. Tech. rep. # 97-060, University of Minnesota (1997)Google Scholar
  6. 6.
    Müller-Pfefferkorn, R., Nagel, W.E., Trenkler, B.: Optimizing Cache Access: A Tool for Source-to-Source Transformations and Real-Life Compiler Tests. In: Danelutto, M., Vanneschi, M., Laforenza, D. (eds.) Lecture Notes in Computer Science 3149, pp. 72–81. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Pokam, G., Bihan, S., Simonnet, J., Bodin, F.: SWARP: a retargetable preprocessor for multimedia instructions. Concurr. Comput.: Pract. Exper. 16(2–3), pp. 303–318, (2004) doi: 10.1002/cpe.v16:2/3Google Scholar
  8. 8.
    Saad,Y., Sosonkina, M.: Distributed Schur complement techniques for general sparse linear systems. SISC 21, 1337–1356 (1999)MathSciNetGoogle Scholar
  9. 9.
    Simmendinger, C., Kügeler, E.: Hybrid Parallelization of a Turbomachinery CFD Code: Performance Enhancements on Multicore Architectures. In: Proceedings of the V European Conference on Computational Fluid Dynamics ECCOMAS CFD 2010, J.C.F. Pereira, A. Sequeira and J.M.C. Pereira (Eds), Lisbon, Portugal, 14–17 June 2010, CD-ROM, ISBN: 978-989-96778-1-4Google Scholar
  10. 10.
    Performance Application Programming Interface: http://icl.cs.utk.edu/papi/.Cited15Dec2010
  11. 11.
    DLR Institute of Aerodynamics and Flow Technology: http://www.dlr.de/as/.Cited15Dec2010
  12. 12.
    DLR Institute of Propulsion Technology, Numerical Methods: http://www.dlr.de/at/desktopdefault.aspx/tabid-1519/2123_read-3615/.Cited15Dec2010
  13. 13.
    Vampir - Performance Optimization: http://www.vampir.eu/.Cited15Dec2010
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Achim Basermann
    • 1
  • Hans-Peter Kersken
    • 3
  • Andreas Schreiber
    • 1
  • Thomas Gerhold
    • 2
  • Jens Jägersküpper
    • 2
  • Norbert Kroll
    • 2
  • Jan Backhaus
    • 3
  • Edmund Kügeler
    • 3
  • Thomas Alrutz
    • 4
  • Christian Simmendinger
    • 4
  • Kim Feldhoff
    • 5
  • Olaf Krzikalla
    • 5
  • Ralph Müller-Pfefferkorn
    • 5
  • Mathias Puetz
    • 6
  • Petra Aumann
    • 7
  • Olaf Knobloch
    • 7
  • Jörg Hunger
    • 8
  • Carsten Zscherp
    • 8
  1. 1.German Aerospace Center e.V. (DLR)Simulation and Software TechnologyCologneGermany
  2. 2.DLRInstitute of Aerodynamics and Flow TechnologyGöttingenGermany
  3. 3.DLRInstitute of Propulsion TechnologyCologneGermany
  4. 4.T-Systems Solutions for Research GmbHGöttingenGermany
  5. 5.Zentrum für Informationsdienste und HochleistungsrechnenTechnische Universität DresdenDresdenGermany
  6. 6.IBM Deutschland GmbHMainzGermany
  7. 7.Airbus Deutschland GmbHAerodynamic Tools and SimulationBremenGermany
  8. 8.MTU Aero Engines GmbHMünchenGermany

Personalised recommendations