Advertisement

A note on the load balancing problem for coarse grained hypercube dictionary machines

  • Frank Dehne
  • Michel Gastaldo
Load Balancing And The Mapping Problem
Part of the Lecture Notes in Computer Science book series (LNCS, volume 457)

Abstract

The main problem for the design of dictionary machines on coarse grained hypercube multiprocessors, in comparison to the widely studied dictionary problem for fine grained hypercube multiprocessors, is that due to unequal distribution of the inserted and deleted records, the sizes of the sets stored at the individual processors may vary considerably. This problem, which is usually referred to as the load balancing problem, may lead to considerable degradation of the dictionary machine's performance. In this note we show that the load balancing problem for coarse grained hypercube dictionary machines can be solved with provable bounds on the sizes of the data sets, and with only little computational overhead.

Keywords

Computational Overhead Arbitrary Tree Considerable Degradation Load Balance Problem Approximate Counting 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [AK]
    M.J. Atallah and S.R. Kosaraju, "A generalized dictionary machine for VLSI", IEEE Trans. on Computers 34:2, 1985, pp. 151–155.Google Scholar
  2. [BK]
    J.L. Bentley, and H.T. Kung, "A tree machine for searching problems", Proc. 1979 Int. Conf. on Parallel Processing, 1979, May 1981, pp. 257–266.Google Scholar
  3. [C1]
    J.H. Chang, O.H. Ibarra, M.J. Chung, and K.K. Rao, "Systolic tree implementation of data structures", IEEE Trans. on Computers 37:6, 1988, pp. 727–735.CrossRefGoogle Scholar
  4. [DS1]
    F. Dehne, N. Santoro, "Optimal VLSI dictionary machines on meshes", Proc. Int. Conf. on Parallel Processing, 1987, pp. 832–840.Google Scholar
  5. [DS2]
    F. Dehne, N. Santoro, "An optimal VLSI dictionary machine for hypercube architectures", Parallel and Distributed Algorithms, M. Cosnard (ed.), North Holland, 1989, pp. 137–144.Google Scholar
  6. [F]
    A.L. Fisher, "Dictionary machines with small number of processors", Proc. Int. Symp. on Computer Architecture, June 1984, pp. 151–156.Google Scholar
  7. [KRS]
    C.P. Kruskal, L. Rudolph, M. Snir, "The power of parallel profix", Proc. Int. Conf. on Parallel Processing, 1985, pp.180–184.Google Scholar
  8. [L]
    C.E. Leiserson, "Systolic priority queues", Report CMU-CS-79-115, Carnegie-Mellon University, April 1979.Google Scholar
  9. [NS]
    D. Nassimi, S. Sahni, "Brodcasting data in SIMD Computers", IEEE Trans. on Computers 30:2, 1981, pp 101–107.Google Scholar
  10. [OB]
    A.R. Omondi, J. D. Brock, "Implementing a dictionary on hypercube machines", Proc. Int. Conf. on Parallel Processing, 1987, pp.707–709.Google Scholar
  11. [ORS]
    T.A. Ottman, A.L. Rosenberg, and L.J. Stockmeyer, "A dictionary machine for VLSI", IEEE Trans. on Computers 31:9, 1982, pp. 892–897.Google Scholar
  12. [SA]
    A.K. Somani and V.K. Agarwal, "An efficient unsorted VLSI dictionary machine", IEEE Trans. on Computers 34:9, 1985, pp. 841–852.Google Scholar
  13. [SL]
    A.M. Schwartz and M.C. Loui, "Dictionary machines on cube-class networks", IEEE Trans. on Computers 36:1, 1987, pp. 100–105.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Frank Dehne
    • 1
  • Michel Gastaldo
    • 2
  1. 1.Center for Parallel and Distributed Computing School of Computer ScienceCarleton UniversityOttawaCanada
  2. 2.Laboratoire de l'Informatique du Parallelisme — IMAGEcole Normale Superieure de LyonLyon cedex 07France

Personalised recommendations