4th International IEEE Conference on Broadband Communications, Networks, Systems

Research Article

Design and implementation of openMP library for λ computing environment

  • @INPROCEEDINGS{10.1109/BROADNETS.2007.4550505,
        author={Keigo Goda and Mai Imoto and Ken-ichi Baba and Noriyuki Fujimoto and Masayuki Murata},
        title={Design and implementation of openMP library for λ computing environment},
        proceedings={4th International IEEE Conference on Broadband Communications, Networks, Systems},
        publisher={IEEE},
        proceedings_a={BROADNETS},
        year={2010},
        month={5},
        keywords={},
        doi={10.1109/BROADNETS.2007.4550505}
    }
    
  • Keigo Goda
    Mai Imoto
    Ken-ichi Baba
    Noriyuki Fujimoto
    Masayuki Murata
    Year: 2010
    Design and implementation of openMP library for λ computing environment
    BROADNETS
    IEEE
    DOI: 10.1109/BROADNETS.2007.4550505
Keigo Goda1,*, Mai Imoto1,*, Ken-ichi Baba2,*, Noriyuki Fujimoto1,*, Masayuki Murata1,*
  • 1: Graduate School of Information Science and Technology, Osaka University
  • 2: Cybermedia Center, Osaka University 1-5 Yamadaoka, Suita, Osaka 565-0871, Japan Telephone: +81-6-6879-4542
*Contact email: k-gouda@ist.osaka-u.ac.jp, m-imoto@ist.osaka-u.ac.jp, baba@cmc.osaka-u.ac.jp, fujimoto@ist.osaka-u.ac.jp, murata@ist.osaka-u.ac.jp

Abstract

Grid technology has been studied and developed by numerous researchers in recent years. Data in conventional grid environments are changed by using TCP/IP. However, as long as the architecture is based on packet switching, highly efficient computing is difficult to achieve. We thus propose a new architecture, the 􀀀 computing environment, where network switches and computing nodes are connected to one another with optical fibers, thereby offering high-performance computing by establishing an optical wavelength path between shared memories on computing nodes. We established the lambda computing environment using the AWG-STAR system, and designed a data-sharing structure for the OpenMP library, which is a parallel-computing programming language utilizing shared memory. Moreover, we evaluated its performance against existing parallel computing in a PC-cluster environment by executing OpenMP applications.