• DocumentCode
    1912726
  • Title

    NDM 2012: Second International Workshop on Network-Aware Data Management

  • Author

    Warren, Michael S. ; Bergen, Ben

  • fYear
    2012
  • fDate
    10-16 Nov. 2012
  • Abstract
    We have recently demonstrated our hashed oct-tree N-body code (HOT) scaling to 256k processors on Jaguar at Oak Ridge National Laboratory with a performance of 1.79 Petaflops (single precision) on 2 trillion particles. We have additionally performed preliminary studies with NVIDIA Fermi GPUs, achieving single GPU performance on our hexadecapole inner loop near 1 Tflop (single precision) and application performance speedup of 2x by offloading the most computationally intensive part of the code to the GPU.
  • Keywords
    N-body simulations (astronomical); graphics processing units; octrees; HOT; Jaguar; NVIDIA Fermi GPU; Oak Ridge National Laboratory; Petaflop; hashed oct-tree N-body algorithm; hashed oct-tree N-body code; hexadecapole inner loop;
  • 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.2012.9
  • Filename
    6495788