HTN: A new hierarchical interconnection network for massively parallel computers

被引:0
|
作者
Rahman, MMH
Horiguchi, S
机构
来源
关键词
hierarchical network; network performance; peak number of vertical links; and layout area;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Interconnection networks usually suffer from Little's Law: low cost implies low performance and high performance is obtained high cost. However, hierarchical interconnection networks provide high performance at low cost by exploring the locality that exists in communication patterns of massively parallel computers. In this paper, we propose a new hierarchical interconnection network, called Hierarchical Torus Network (HTN). This network reduces the number of vertical links in 3D stacked implementation while maintaining good network features. This paper addresses the architectural details of the HTN, and explores aspects such as the network diameter, average distance, bisection width, peak number of vertical links, and VLSI layout area of the HTN as well as for several commonly used networks for parallel computers. It is shown that the HTN possesses several attractive features including small diameter, small average distance, small number of wires, a particularly small number of vertical links, and economic layout area.
引用
收藏
页码:1479 / 1486
页数:8
相关论文
共 50 条
  • [31] ON INTERCONNECTION NETWORKS FOR PARALLEL COMPUTERS
    Li, Lei
    Li, Qian
    Yoshioka, Yoshio
    INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, 2008, 11 (06): : 739 - 748
  • [32] Hierarchical interconnection networks based on (3,3)-graphs for massively parallel processors
    Jan, GE
    Hwang, YS
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2004, E87D (07): : 1649 - 1656
  • [33] A spanning bus connected hypercube: A new scalable optical interconnection network for multiprocessors and massively parallel systems
    Louri, A
    Neocleous, C
    JOURNAL OF LIGHTWAVE TECHNOLOGY, 1997, 15 (07) : 1241 - 1252
  • [34] Experimental free-space optical network for massively parallel computers
    NEC Research Inst, Princeton, United States
    Appl Opt, 8 (1269-1281):
  • [35] Experimental free-space optical network for massively parallel computers
    Araki, S
    Kajita, M
    Kasahara, K
    Kubota, K
    Kurihara, K
    Redmond, I
    Schenfeld, E
    Suzaki, T
    APPLIED OPTICS, 1996, 35 (08): : 1269 - 1281
  • [36] Extended Hypercube with Cross-Connection - A New Interconnection Fault Tolerant Network for Parallel Computers
    Ray, B. N. B.
    RanjanTripathy, Alok
    2009 IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE, VOLS 1-3, 2009, : 513 - +
  • [37] Feasibility study of a scalable optical interconnection network for massively parallel processing systems
    Louri, Ahmed
    Furlonge, Stephen
    Applied Optics, 1996, 35 (08): : 1296 - 1308
  • [38] Feasibility study of a scalable optical interconnection network for massively parallel processing systems
    Louri, A
    Furlonge, S
    APPLIED OPTICS, 1996, 35 (08) : 1296 - 1308
  • [40] SCAC-Net: Reconfigurable Interconnection Network in SCAC Massively parallel SoC
    Krichene, Hana
    Baklouti, Mouna
    Abid, Mohamed
    Marquet, Philippe
    Dekeyser, Jean-Luc
    2016 24TH EUROMICRO INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, AND NETWORK-BASED PROCESSING (PDP), 2016, : 759 - 762