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

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Contributors

  • Achim Basermann - , German Aerospace Center (DLR) - Berlin-Adlershof (Author)
  • Hans-Peter Kersken - , German Aerospace Center (DLR) - Berlin-Adlershof (Author)
  • Andreas Schreiber - , German Aerospace Center (DLR) - Berlin-Adlershof (Author)
  • Thomas Gerhold - , German Aerospace Center (DLR) (e.V.) Location Braunschweig (Author)
  • Jens Jägersküpper - , German Aerospace Center (DLR) (e.V.) Location Braunschweig (Author)
  • Norbert Kroll - , German Aerospace Center (DLR) (e.V.) Location Braunschweig (Author)
  • Jan Backhaus - , German Aerospace Center (DLR) - Berlin-Adlershof (Author)
  • Edmund Kügeler - , German Aerospace Center (DLR) - Berlin-Adlershof (Author)
  • Thomas Alrutz - , T-Systems SfR GmbH (Author)
  • Christian Simmendinger - , T-Systems SfR GmbH (Author)
  • Kim Feldhoff - , Center for Information Services and High Performance Computing (ZIH) (Author)
  • Olaf Krzikalla - , Center for Information Services and High Performance Computing (ZIH) (Author)
  • Ralph Müller-Pfefferkorn - , Center for Information Services and High Performance Computing (ZIH) (Author)
  • Mathias Puetz - , IBM Deutschland GmbH (Author)
  • Petra Aumann - , Airbus Group (Author)
  • Olaf Knobloch - , Airbus Group (Author)
  • Jörg Hunger - , MTU Aero Engines GmbH (Author)
  • Carsten Zscherp - , MTU Aero Engines GmbH (Author)

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.

Details

Original languageEnglish
Title of host publicationCompetence in High Performance Computing 2010
PublisherSpringer Verlag
Pages1-13
Number of pages13
ISBN (print)978-3-642-24024-9
Publication statusPublished - 2010
Peer-reviewedYes

Keywords

Keywords

  • Computational Fluid Dynamics, Message Passing Interface, Single Instruction Multiple Data, Computational Fluid Dynamic Code, Message Passing Interface Process