• DocumentCode
    2283867
  • Title

    A Low Complexity Heuristic for Design of Custom Network-on-Chip Architectures

  • Author

    Srinivasan, Krishnan ; Chatha, Karam S.

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Arizona State Univ., Tempe, AZ
  • Volume
    1
  • fYear
    2006
  • fDate
    6-10 March 2006
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    Network-on-chip (NoC) has been proposed to replace traditional bus based architectures to address the global communication challenges in nanoscale technologies. In future SoC architectures, minimizing power consumption continue to be an important design goal. In this paper, we present a novel heuristic technique consisting of system-level physical design, and interconnection network generation that generates custom low power NoC architectures for application specific SoC. We demonstrate the quality of the solutions produced by our technique by experimentation with many benchmarks. Our technique has a low computational complexity, and consumes only 1.25 times the power consumption, and 0.85 times the number of router resources compared to an optimal MILP based technique whose computational complexity is not bounded
  • Keywords
    computational complexity; integer programming; integrated circuit design; integrated circuit interconnections; linear programming; microprocessor chips; network-on-chip; NoC architectures; application specific SoC; computational complexity; custom network-on-chip architectures; heuristic technique; interconnection network generation; low complexity heuristic; optimal MILP technique; power consumption; system-level physical design; Bandwidth; Computational complexity; Computer architecture; Design optimization; Energy consumption; Global communication; Multiprocessor interconnection networks; Network-on-a-chip; Power generation; Power system interconnection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Design, Automation and Test in Europe, 2006. DATE '06. Proceedings
  • Conference_Location
    Munich
  • Print_ISBN
    3-9810801-1-4
  • Type

    conf

  • DOI
    10.1109/DATE.2006.244034
  • Filename
    1656863