Parallel finite element analysis using the Intel Xeon Phi

Lee Margetts, Jose Arregui-Mena, Terry Hewitt, Luke Mason

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    86 Downloads (Pure)

    Abstract

    This paper describes the porting of the open source engineering software ParaFEM to the Intel Xeon Phi processor. The results of a preliminary performance study are presented for a new open source ParaFEM mini-app written especially for the purpose. The main findings of the study are that: (i) The original MPI-based software scales linearly on up to 56 of the 60 available cores; (ii) A new mixed mode MPI/OpenMP implementation boosts performance by a factor of 4 when using 4 threads per core on 1-16 cores (for the largest problem that fits in the Xeon Phi memory) and (iii) The best Xeon Phi solution time is ~2 times faster than the host; here comprising 2 x 12 core “standard” Intel Xeon processors. It appears that scaling beyond 16 cores and 4 threads per core is limited by the amount of work available to each of the 240 threads. The authors propose a number of strategies that can be explored to reduce the memory footprint of individual finite elements so that a much larger problem can be tackled. With more “parallelizable work” per thread, we expect to be able to further improve the performance of the mixed mode MPI/OpenMP implementation. This work will be of interest to researchers and engineers who may wish to evaluate the Intel Xeon Phi for scientific computing, particularly those using the finite element method.
    Original languageEnglish
    Title of host publicationProceedings of the EMerging Technology (EMiT) Conference 2016
    EditorsB.D. Rogers, D. Topping, F. Mantovani, M.K. Bane
    Number of pages4
    Publication statusAccepted/In press - 2 Jun 2016
    EventEMiT: Emerging Technology Conference 2016 - Barcelona Supercomputing Event, Barcelona, Spain
    Duration: 2 Jun 20163 Jun 2016
    http://emit.tech/

    Conference

    ConferenceEMiT: Emerging Technology Conference 2016
    Abbreviated titleEMiT 2016
    Country/TerritorySpain
    CityBarcelona
    Period2/06/163/06/16
    Internet address

    Keywords

    • HPC
    • Accelerators
    • Finite element method
    • Krylov solvers
    • MPI (Message Passing Interface)
    • OpenMP

    Research Beacons, Institutes and Platforms

    • Energy

    Fingerprint

    Dive into the research topics of 'Parallel finite element analysis using the Intel Xeon Phi'. Together they form a unique fingerprint.
    • STFC Hartree Centre

      Lee Margetts (Visiting researcher)

      27 Jun 20161 Jul 2016

      Activity: External visiting positions or secondmentsVisiting an external academic institutionResearch

    • PRACE Scientific and Industrial Conference 2016

      Lee Margetts (Member of programme committee)

      10 May 201612 May 2016

      Activity: Participating in or organising event(s)Participating in a conference, workshop, exhibition, performance, inquiry, course etcResearch

    Cite this