• DocumentCode
    348216
  • Title

    A processor network without interconnection path

  • Author

    Stefan, Denisa ; Stefan, Gheorghe

  • Author_Institution
    Waferscale Integration Inc., Fremont, CA, USA
  • Volume
    1
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    305
  • Abstract
    In the current silicon technologies the wire connections become more and more important. They will waste time, energy and maybe area more than the gates. Beyond the technological solutions for this problem, architectural solutions are welcome. This paper discusses a solution which completely avoids the interconnections in a 4-processor network. More, the four processors share many structural resources, thus minimizing the size of the entire structure. The pipeline penalties are completely avoided in the proposed structure. The machine we describe is an environment for interleaved multi-threaded executions
  • Keywords
    integrated circuit interconnections; integrated circuit modelling; 4-processor network; architectural solutions; interconnection path; interleaved multi-threaded executions; pipeline penalties; processor network; wire connections; Algorithm design and analysis; Circuit testing; Clocks; Counting circuits; Frequency; Logic testing; Pipelines; Reduced instruction set computing; Registers; Yarn;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Semiconductor Conference, 1999. CAS '99 Proceedings. 1999 International
  • Conference_Location
    Sinaia
  • Print_ISBN
    0-7803-5139-8
  • Type

    conf

  • DOI
    10.1109/SMICND.1999.810524
  • Filename
    810524