• DocumentCode
    2415129
  • Title

    A standalone FPGA based emulated-digital CNN-UM system

  • Author

    Vörösházi, Zsolt ; Kiss, András ; Nagy, Zoltán ; Szolgay, Péter

  • Author_Institution
    Dept. of Image Process. & Neurocomputing, Univ. of Pannonia, Veszprem
  • fYear
    2008
  • fDate
    14-16 July 2008
  • Firstpage
    4
  • Lastpage
    4
  • Abstract
    The Falcon emulated-digital CNN-UM (cellular neural/nonlinear networks universal machine) architecture has been extended by an embedded GAPU (global analogic programming unit) using the flexible Xilinx MicroBlaze soft-core processor to take full advantage of the joint computing power of high-speed distributed arithmetics and programmability. The implemented GAPU provides a stand-alone operation, which is capable of controlling complex sophisticated CNN analogic algorithms similar to various visual microprocessors, such as the ACE4k, ACE16k, and Bi-i vision systems. The quality of the embedded GAPU implementation is demonstrated by analogic algorithms, mainly in which sequences of template operations are required.
  • Keywords
    cellular neural nets; field programmable gate arrays; microprocessor chips; neural chips; ACE16k systems; ACE4k systems; Bi-i vision systems; Falcon emulated-digital CNN-UM architecture; cellular neural-nonlinear networks universal machine; complex sophisticated CNN analogic algorithms; flexible Xilinx MicroBlaze soft-core processor; global analogic programming unit; high-speed distributed arithmetics; standalone FPGA; visual microprocessors; Arithmetic; Cellular networks; Cellular neural networks; Computer architecture; Computer networks; Control systems; Distributed computing; Embedded computing; Field programmable gate arrays; Turing machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cellular Neural Networks and Their Applications, 2008. CNNA 2008. 11th International Workshop on
  • Conference_Location
    Santiago de Compostela
  • Print_ISBN
    978-1-4244-2089-6
  • Electronic_ISBN
    978-1-4244-2090-2
  • Type

    conf

  • DOI
    10.1109/CNNA.2008.4588635
  • Filename
    4588635