• DocumentCode
    2708404
  • Title

    High performance systems: An agent based application power profiling

  • Author

    Raghu, H.V. ; Kumar, Ajit ; Bindhumadhava, B.S.

  • Author_Institution
    Real Time Syst. & Smart Grid Group, Centre for Dev. of Adv. Comput., Bangalore, India
  • fYear
    2012
  • fDate
    14-16 Dec. 2012
  • Firstpage
    59
  • Lastpage
    65
  • Abstract
    Power measurement and analysis are important aspects for optimizing the power consumption in High Performance Computing (HPC) systems. With the huge increase in the power consumption of HPC systems, it is important to compare systems with metrics based on performance per watt. There are various hardware and software based power measurement techniques available for HPC systems. But, it´s a complex task to accurately measure and analyze the power consumption of entire HPC nodes in real time. Hence, we have used hardware based power measurement technique with Multi-Agent based framework for analyzing power in HPC systems at real time. We clearly demonstrated the power consumed while running the various workloads such as High Performance Linpack (HPL) and NAS Parallel Benchmarks (NPB).
  • Keywords
    multi-agent systems; parallel processing; power aware computing; power consumption; HPC; HPL; NAS parallel benchmarks; NPB; agent based application power profiling; high performance computing systems; high performance linpack; multiagent based framework; power consumption; used hardware based power measurement technique; Benchmark testing; Memory management; Power demand; Power measurement; Servers; Supercomputers; HPC Standard Benchmarks; High Performance Computing; Multi-Agent Framework; Power Measurement;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Computing and Communications (ADCOM), 2012 18th Annual International Conference on
  • Conference_Location
    Bangalore
  • Print_ISBN
    978-1-4799-0802-8
  • Type

    conf

  • DOI
    10.1109/ADCOM.2012.6563585
  • Filename
    6563585