• DocumentCode
    107975
  • Title

    Scaling the Energy Proportionality Wall with KnightShift

  • Author

    Wong, D. ; Annavaram, Murali

  • Volume
    33
  • Issue
    3
  • fYear
    2013
  • fDate
    May-June 2013
  • Firstpage
    28
  • Lastpage
    37
  • Abstract
    Measuring energy proportionality accurately and understanding the reasons for disproportionality are critical first steps in designing future energy-efficient servers. This article presents two metrics-linear deviation and proportionality gap-that let system designers analyze and understand server energy consumption at various utilization levels. An analysis of published SPECpower results shows that energy proportionality improvements are not uniform across various server utilization levels. Even highly energy proportional servers suffer significantly at nonzero but low utilizations. To address the lack of energy proportionality at low utilization, the authors present KnightShift, a server-level heterogeneous server providing an active low-power mode. KnightShift is tightly coupled with a low-power compute node called Knight. Knight responds to low-utilization requests whereas the primary server responds only to high-utilization requests, enabling two energy-efficient operating regions. The authors evaluate KnightShift against a variety of real-world datacenter workloads using a combination of prototyping and simulation.
  • Keywords
    computer centres; power aware computing; KnightShift; active low-power mode; energy proportionality measurement; energy proportionality wall scaling; energy-efficient operating regions; linear deviation; proportionality gap; real-world datacenter workloads; server energy consumption; server utilization levels; server-level heterogeneous server; Computational modeling; Computer architecture; Energy consumption; Energy efficiency; Energy measurement; KnightShift; energy efficiency; energy proportionality; linear deviation; proportionality gap;
  • fLanguage
    English
  • Journal_Title
    Micro, IEEE
  • Publisher
    ieee
  • ISSN
    0272-1732
  • Type

    jour

  • DOI
    10.1109/MM.2013.31
  • Filename
    6487477