• DocumentCode
    33871
  • Title

    Lessons Learned from Optimizing Science Kernels for Intel´s "Knights Corner"´ Architecture

  • Author

    Deslippe, Jack ; Austin, Brian ; Daley, Chris ; Woo-Sun Yang

  • Volume
    17
  • Issue
    3
  • fYear
    2015
  • fDate
    May-June 2015
  • Firstpage
    30
  • Lastpage
    42
  • Abstract
    Optimizing the codes and kernels representing the National Energy Research Scientific Computing Center´s workload on the Knights Corner architecture helped pave the path for NERSC´s newest machine. Cori will use the next generation of Intel Xeon Phi processors: Knights Landing.
  • Keywords
    coprocessors; optimising compilers; parallel architectures; Intel Xeon Phi processor; KNL; Knights corner architecture; Knights landing; NERSC; National Energy Research Scientific Computing Center; code optimization; kernel optimization; next generation processor; Computer architecture; Encoding; Kernel; Program processors; Scientific computing; Supercomputers; High-performance computing; Intel; processors; scientific computing; supercomputer;
  • fLanguage
    English
  • Journal_Title
    Computing in Science & Engineering
  • Publisher
    ieee
  • ISSN
    1521-9615
  • Type

    jour

  • DOI
    10.1109/MCSE.2015.28
  • Filename
    7018683