• DocumentCode
    3480428
  • Title

    An Efficient Method for Energy Estimation of Application Specific Instruction-Set Processors

  • Author

    Jordans, R. ; Corvino, R. ; Jozwiak, Lech ; Corporaal, Henk

  • Author_Institution
    Dept. of Electr. Eng., Eindhoven Univ. of Technol., Eindhoven, Netherlands
  • fYear
    2013
  • fDate
    4-6 Sept. 2013
  • Firstpage
    471
  • Lastpage
    474
  • Abstract
    Design space exploration for ASIP instruction-set design is a very complex problem, involving a large set of architectural choices. Existing methods are usually handcrafted and time-consuming. In this paper, we propose and investigate a rapid method to estimate the energy consumption of candidate architectures for VLIW ASIP processors. The proposed method avoids the time-consuming simulation of the candidate prototypes, without any loss of accuracy in the predicted energy consumption. We experimentally show the effect of this fast cost evaluation method when used in an automated instruction-set architecture exploration. In our experiments, we compare three different methods for cost estimation and find that we can accurately predict the energy consumption of proposed architectures while avoiding simulation of the complete system.
  • Keywords
    application specific integrated circuits; computer architecture; instruction sets; integrated circuit design; power aware computing; ASIP instruction-set design; VLIW ASIP processors; application specific instruction-set processors; automated instruction-set architecture exploration; cost estimation; cost evaluation method; energy consumption prediction; energy estimation; Computational modeling; Computer architecture; Energy consumption; Estimation; Program processors; Prototypes; VLIW; application specific processor; energy estimation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Digital System Design (DSD), 2013 Euromicro Conference on
  • Conference_Location
    Los Alamitos, CA
  • Type

    conf

  • DOI
    10.1109/DSD.2013.120
  • Filename
    6628315