• DocumentCode
    3354707
  • Title

    SmartCell: A power-efficient reconfigurable architecture for data streaming applications

  • Author

    Liang, Cao ; Huang, Xinming

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Worcester Polytech. Inst., Worcester, MA
  • fYear
    2008
  • fDate
    8-10 Oct. 2008
  • Firstpage
    257
  • Lastpage
    262
  • Abstract
    This paper presents SmartCell as a novel power efficient reconfigurable architecture targeted for data streaming applications. We describe the design details of the SmartCell architecture, including processing element, reconfigurable interconnection fabrics, instruction and control process and dynamic configuration scheme. The performance in terms of power efficiency and system throughput is evaluated through a set of benchmark applications, and is compared with ASIC, FPGA and RaPiD reconfigurable architecture. The results show that the SmartCell consumes about 52% and 75% less power than RaPiD and FPGA, respectively. It is demonstrated that SmartCell is a promising reconfigurable, power efficient and scalable computing architecture that can potentially bridge the gap between logic specific ASIC and configurable FPGA for data streaming applications.
  • Keywords
    power aware computing; reconfigurable architectures; signal processing; SmartCell; configurable FPGA; data streaming; dynamic configuration; logic specific ASIC; power efficiency; reconfigurable architecture; reconfigurable interconnection fabrics; Application specific integrated circuits; Bridges; Computer architecture; Fabrics; Field programmable gate arrays; Power system interconnection; Process control; Reconfigurable architectures; Reconfigurable logic; Throughput; ASIC; CGRA; DSP; FPGA; data streaming application; power efficiency; reconfigurability;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Systems, 2008. SiPS 2008. IEEE Workshop on
  • Conference_Location
    Washington, DC
  • ISSN
    1520-6130
  • Print_ISBN
    978-1-4244-2923-3
  • Electronic_ISBN
    1520-6130
  • Type

    conf

  • DOI
    10.1109/SIPS.2008.4671772
  • Filename
    4671772