Comparative evaluation of hypermesh and multi-stage interconnection networks

被引:14
|
作者
OuldKhaoua, M [1 ]
Mackenzie, LM [1 ]
Sotudeh, R [1 ]
机构
[1] UNIV GLASGOW, DEPT COMP SCI, GLASGOW G12 8QQ, LANARK, SCOTLAND
来源
COMPUTER JOURNAL | 1996年 / 39卷 / 03期
关键词
D O I
10.1093/comjnl/39.3.232
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In a multicomputer network, the channel bandwidth is greatly constrained by implementation technology. Two important constraints have been identified in the literature, each appropriate for a particular technology: wiring density limits dominate in VLSI and pin-out in multiple-chip implementations. Most existing interconnection networks are categorized as either direct or indirect (multi-stage) topologies, the mesh and binary n-cube being examples of the former category, the omega and banyan networks of the latter. This paper argues that direct networks based on hypergraph topologies have characteristics which make them particularly appropriate for use in future high-performance parallel systems. The authors have recently introduced a regular multi-dimensional hypergraph network called the Distributed Crossbar Switch Hypermesh (DCSH), which has: topological properties that permit a relaxation of bandwidth constraints, and which has important topological and performance advantages over direct graph networks, This paper compares the DCSH to multi-stage networks, under both VLSI and multiple-chip technological constraints. The results suggest that in both cases, with a realistic model which includes routing delays through intermediate nodes, the DCSH exhibits superior performance across a wide range of traffic loads.
引用
收藏
页码:232 / 240
页数:9
相关论文
共 50 条
  • [21] Visualization of methods: Computation on multi-stage networks
    Mirenkov, N
    Mirenkova, T
    Sato, M
    INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-III, PROCEEDINGS, 1997, : 1497 - 1504
  • [22] Large switches or blocking multi-stage networks? An evaluation of routing strategies for datacenter fabrics
    Chrysos, N.
    Neeser, F.
    Gusat, M.
    Minkenberg, C.
    Denzel, W.
    Basso, C.
    Rudquist, M.
    Valk, K.
    Vanderpool, B.
    COMPUTER NETWORKS, 2015, 91 : 316 - 328
  • [23] Multi-Stage Elastic Mechanical Modelling and Evaluation of Distribution Networks with Soft Open Point
    Qin Q.
    Han B.
    Li G.
    Luo L.
    Wang K.
    Diangong Jishu Xuebao/Transactions of China Electrotechnical Society, 2021, 36 (21): : 4444 - 4458
  • [24] Multi-Stage Decoding in Dense Distributed Networks for MTC
    Ding, Jie
    Al Homssi, Bassel
    Choi, Jinho
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (09) : 12401 - 12406
  • [25] Convolutional Neural Networks for Multi-Stage Semiconductor Processes
    Wu, Xiaofei
    Chen, Junghui
    Xie, Lei
    Lee, Yishan
    Chen, Chun-, I
    JOURNAL OF CHEMICAL ENGINEERING OF JAPAN, 2021, 54 (08) : 449 - 455
  • [26] Silicon nanowire networks for multi-stage thermoelectric modules
    Norris, Kate J.
    Garrett, Matthew P.
    Zhang, Junce
    Coleman, Elane
    Tompa, Gary S.
    Kobayashi, Nobuhiko P.
    ENERGY CONVERSION AND MANAGEMENT, 2015, 96 : 100 - 104
  • [27] Multi-stage stochastic frontier analysis for simple networks
    Johnes, Geraint
    Tsionas, Mike
    Izzeldin, Marwan
    INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH, 2025, 32 (05) : 2497 - 2522
  • [28] Multi-Stage Process Diagnosis Networks in Semiconductor Manufacturing
    Choi, Jongwon
    Kim, Seoung Bum
    IEEE ACCESS, 2024, 12 : 39495 - 39504
  • [29] Early warnings for multi-stage transitions in dynamics on networks
    MacLaren, Neil G.
    Kundu, Prosenjit
    Masuda, Naoki
    JOURNAL OF THE ROYAL SOCIETY INTERFACE, 2023, 20 (200)
  • [30] Multi-Stage Switching Networks for Waveguide Optical Technology
    Garao, Dario G.
    Maier, Guido
    Pattavina, Achille
    2014 IEEE LATIN-AMERICA CONFERENCE ON COMMUNICATIONS (LATINCOM), 2014,