H-lattice: A geometric model for processor allocation in hypercubes

被引：0
|
作者：
Wu, F
Hsu, CC
机构：
来源：
1996 IEEE SECOND INTERNATIONAL CONFERENCE ON ALGORITHMS & ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP'96, PROCEEDINGS OF | 1996年
关键词：
gray code; hypercube; allocation; first-fit; best-fit; H-lattice;
D O I：
10.1109/ICAPP.1996.562857
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
The H-lattice is a geometric model for describing the construction and occupied configuration of the hypercube multiprocessors. Besides, it can well-model the faulty hypercube in tile presence of faulty processors and/or links. The H-lattice scheme, based on this model, can allocate fault-free subcubes for various allocations, such as first-/best-/worst-/next-fit, and subcube inclusion/exclusion allocations, in a more simple and efficient manner than ever. In this scheme, tile viewpoint of the minimum destroyed degree is introduced to select the best-fit subcube, which is proved to be better than that of other schemes. Mathematical analyses and simulation are also derived to demonstrate the efficiency of the proposed scheme.
引用
收藏
页码：53 / 60
页数：8
相关论文
共 50 条
  • [1] PROCESSOR ALLOCATION FOR HYPERCUBES
    ALBASSAM, S
    ELREWINI, H
    BOSE, B
    LEWIS, TG
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1992, 16 (04) : 394 - 401
  • [2] PROCESSOR ALLOCATION STRATEGIES FOR MODIFIED HYPERCUBES
    ZIAVRAS, SG
    HARAVU, NG
    IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES, 1994, 141 (03): : 196 - 204
  • [3] THE GENERALIZED H-LATTICE FILTER AND ESTIMATION OF THE ARMA MODELS
    YARMANVURAL, F
    WAWRZYNSKI, D
    CETIN, AE
    IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (01): : 147 - 151
  • [4] Sg-lattice: A model for processor allocation for the star graph
    Wu, F
    Hsu, CC
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1999, E82D (03) : 637 - 644
  • [5] Processor allocation in the star graph using Sg-lattice model
    Wu, F
    Hsu, CC
    THIRD INTERNATIONAL SYMPOSIUM ON PARALLEL ARCHITECTURES, ALGORITHMS, AND NETWORKS, PROCEEDINGS (I-SPAN '97), 1997, : 310 - 316
  • [6] A parallel workload model and its implications for processor allocation
    Allen B. Downey
    Cluster Computing, 1998, 1 (1) : 133 - 145
  • [7] A parallel workload model and its implications for processor allocation
    Mathematics and Computer Science, Colby College, Waterville
    ME
    04901, United States
    Cluster Computing, 1998, 1 (01): : 133 - 145
  • [8] ICHU model for processor allocation in distributed operating systems
    Shriram, A.
    Sarangi, A.
    Avinash, S.
    Operating Systems Review (ACM), 2001, 35 (03): : 16 - 21
  • [9] A parallel workload model and its implications for processor allocation
    Downey, AB
    SIXTH IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE DISTRIBUTED COMPUTING, PROCEEDINGS, 1997, : 112 - 123
  • [10] ON THE GEOMETRIC LATTICE APPROXIMATION TO A REALISTIC MODEL OF QCD
    BECHER, P
    JOOS, H
    LETTERE AL NUOVO CIMENTO, 1983, 38 (08): : 293 - 301
12345