• DocumentCode
    2544265
  • Title

    Totally defect-tolerant arrays capable of quick broadcasting

  • Author

    Tsuda, Nobuo ; Ishikawa, Tsutomu ; Nakamura, Yukihiro

  • Author_Institution
    NTT Inf. & Inf. Syst. Labs., Tokyo, Japan
  • fYear
    1995
  • fDate
    13-15 Nov 1995
  • Firstpage
    117
  • Lastpage
    125
  • Abstract
    This paper proposes an advanced spare-connection scheme for k-out-of-n redundancy called “generalized additional bypass linking (ABL)” for total defect-tolerance in large hybrid-WSIs with array structures. The proposed scheme uses bypass links with wired-OR connections to spare processing elements (PEs) without external switches, and can reconfigure complete arrays by tolerating defects in these PEs, links, and external I/O-terminals. The wired-OR connections help to limit the increase in the PE-connections of spare PEs, and these connections are made so that the primary PEs are an inter-PE distance of 3 or more away from each other and are connected to the same bypass link in parallel. The ABL scheme can be used for constructing totally defect-tolerant (TDT) arrays capable of quick broadcasting by using spare circuitries, and it is superior to conventional schemes in terms of extra PE-connections and control of the reconfiguration. This paper describes the basic ABL configurations for series-connected arrays, two-dimensional mesh-connected arrays, and binary trees, and further describes a hierarchical application of the ABL scheme that allows the construction of large arrays using shorter bypass links than the basic ABL configurations
  • Keywords
    VLSI; fault tolerant computing; multichip modules; multiprocessor interconnection networks; parallel processing; redundancy; wafer-scale integration; array structures; binary trees; bypass links; external I/O-terminals; generalized additional bypass linking; hybrid-WSIs; inter-PE distance; k-out-of-n redundancy; processing elements; series-connected arrays; spare circuitries; spare-connection scheme; totally defect-tolerant arrays; two-dimensional mesh-connected arrays; wired-OR connections; Assembly; Broadcasting; Circuit faults; Concurrent computing; Fault tolerance; Joining processes; Laboratories; Large scale integration; Redundancy; Switches;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Defect and Fault Tolerance in VLSI Systems, 1995. Proceedings., 1995 IEEE International Workshop on,
  • Conference_Location
    Lafayette, LA
  • ISSN
    1550-5774
  • Print_ISBN
    0-8186-7107-6
  • Type

    conf

  • DOI
    10.1109/DFTVS.1995.476944
  • Filename
    476944