• DocumentCode
    1917652
  • Title

    Poster: Communication Overlap Techniques for Improved Strong Scaling of Gyrokinetic Eulerian Code beyond 100k Cores on the K-Computer

  • Author

    Idomura, Yasuhiro ; Nakata, Mitsuru ; Yamada, Shigeru ; Machida, M. ; Imamura, Takashi ; Watanabe, Toshio ; Nunami, Masanori ; Inoue, H. ; Tsutsumi, Shinichi ; Miyoshi, Ikuo ; Shida, Naoyuki

  • Author_Institution
    Japan Atomic Energy Agency, Tokai, Japan
  • fYear
    2012
  • fDate
    10-16 Nov. 2012
  • Firstpage
    1375
  • Lastpage
    1376
  • Abstract
    A plasma turbulence research based on 5D gyrokinetic simulations is one of the most critical and demanding issues in fusion science. To pioneer new physics regimes both in problem sizes and in time scales, an improvement of strong scaling is essential. Overlap of computations and communications is a promising approach in improving strong scaling, but it often fails on practical applications with conventional MPI libraries. In this work, this classical issue is revisited, and resolved by communication overlap techniques, which work even on conventional MPI libraries. These techniques dramatically improve the parallel efficiency of a gyrokinetic Eularian code GT5D on the K-computer and the Helios, which are based on dedicated and commodity networks, respectively. On the K-computer, excellent strong scaling is confirmed beyond 100k cores with keeping the peak ratio of ~10% (~307 TFlops using 196,608 cores), and simulations for ITER-size fusion devices are significantly accelerated.
  • Keywords
    message passing; physics computing; plasma simulation; plasma turbulence; GT5D; ITER size fusion device; K-computer; MPI library; communication overlap technique; fusion science; gyrokinetic Eulerian code scaling simulation; parallel efficiency; plasma turbulence; Communication overlap; Eulerian code; Fusion plasma turbulence; Gyrokinetic simulations; Hybrid parallelization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    High Performance Computing, Networking, Storage and Analysis (SCC), 2012 SC Companion:
  • Conference_Location
    Salt Lake City, UT
  • Print_ISBN
    978-1-4673-6218-4
  • Type

    conf

  • DOI
    10.1109/SC.Companion.2012.199
  • Filename
    6495982