• DocumentCode
    2726457
  • Title

    Toward a universal mapping algorithm for accessing trees in parallel memory systems

  • Author

    Auletta, Vincenzo ; Das, Sajal K. ; De Vivo, Amelia ; Pinotti, M. Cristina ; Scarano, Vittorio

  • Author_Institution
    Dipt. di Inf. ed Applicazioni, Salerno Univ., Italy
  • fYear
    1998
  • fDate
    30 Mar-3 Apr 1998
  • Firstpage
    447
  • Lastpage
    454
  • Abstract
    The authors study the problem of mapping the N nodes of a complete t-ary tree on M memory modules so that they can be accessed in parallel by templates, i.e. distinct sets of nodes. Typical templates for accessing trees are subtrees, root-to-leaf paths, or levels which are referred to as elementary templates. They first propose a new mapping algorithm for accessing both paths and subtrees of size M with an optimal number of conflicts (i.e., only one conflict) when the number of memory modules is limited to M. They also propose another mapping algorithm for a composite template, say 𝒱 (as versatile), such that its size is not fixed and an instance of 𝒱 is composed of any combination of c instances of elementary templates. The number of conflicts for accessing an S-node instance of template 𝒱 is O(S/√M log M+c) and the memory load is 1+o(1) where load is defined as the ratio between the maximum and minimum number of data items mapped onto each memory module
  • Keywords
    computational complexity; memory architecture; multiprocessing systems; parallel algorithms; tree data structures; complete t-ary tree node mapping; composite template; elementary template; mapped data items; memory load; memory modules; parallel memory systems; root-to-leaf paths; subtrees; templates; tree access; universal mapping algorithm; Concurrent computing; Costs; Data structures; Gold; Information retrieval; Multiprocessor interconnection networks; Network topology; Read-write memory; Vegetation mapping;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Parallel Processing Symposium, 1998. IPPS/SPDP 1998. Proceedings of the First Merged International ... and Symposium on Parallel and Distributed Processing 1998
  • Conference_Location
    Orlando, FL
  • ISSN
    1063-7133
  • Print_ISBN
    0-8186-8404-6
  • Type

    conf

  • DOI
    10.1109/IPPS.1998.669955
  • Filename
    669955