Non-blocking Network Architectures for High-speed Switching Networks

高速交换网络的无阻塞网络架构

• 批准号: 14380138
• 负责人: HORIGUCHI Susumu
• 金额: $ 9.79万
• 依托单位: TOHOKU UNIVERSITY (2004)Japan Advanced Institute of Science and Technology (2002-2003)
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2002
• 资助国家: 日本
• 起止时间: 2002 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-14380138/
• 关键词: WDM; Optical Connection; Non-blocking; Multi-stage Interconnection Network; Recursive Structure; Cross-talk Free; 3次元実装方式; 波長多重伝送方式(WDM)

Non-blocking switch networks are useful in designing optical cross-connect to reduce the cell loss probability. For applications that require a high data transmission rate, low error rate and low delay, rearrangement of the states of switching elements in the optical network is not desirable, making non-blocking switching increasingly important for optical networks. In this research, we propose a recursive architecture for non-blocking optical switch networks which is more general than the RN(Nm) network. In this architecture, any M×N non-blocking switch network can be built with building blocks of given size m×n, where M, N, m, n are all powers of integers. We show that the proposed network is self-routing for all N permutations and the propagation delay is O(log_2N). We also show that both RN(N,m) and Spanke's networks are special cases of this network. The proposed approach is a good choice for constructing non-blocking optical switch networks with low signal loss and crosstalk.We a … More lso discuss about new architecture of Banyan networks that are very attractive for serving as the optical switch architectures due to their nice properties of small depth and absolutely signal loss uniformity. Combining the horizontal expansion and vertical stacking of optical banyan networks is a general scheme for constructing banyan-based optical switching networks. The resulting horizontally expanded and vertically stacked optical banyan (HVOB) networks usually take either a high hardware cost or a large network depth to guarantee the non-blocking property. Blocking behavior analysis is an effective approach to studying network performance and finding a graceful compromise among hardware cost, network depth, and blocking probability ; however, little has been done to analyze the blocking behavior of general HVOB networks. In this paper, we study the overall blocking behavior of general HVOB networks, where an upper bound on the blocking probability of a HVOB network is developed with respect to the number of planes (stacked copies) and the number of stages. The upper bound accurately depicts the overall blocking behavior of a HVOB network as verified by an extensive simulation study, and it agrees with the strictly non-blocking condition of the network. The derived upper bound is significant because it reveals the inherent relationship among blocking probability, network depth, and network hardware cost, so that a desirable tradeoff can be made among them. Less

在设计光交叉连接时，非阻塞交换网络可以有效地降低丢包概率。对于要求高数据传输率、低错误率和低时延的应用，光网络中交换元件状态的重新排列是不可取的，这使得无阻塞交换对光网络越来越重要。在本研究中，我们提出了一种比RN（Nm）网络更通用的无阻塞光交换网络递归架构。在该体系结构中，任意M×N无阻塞交换网络都可以用给定大小的构建块m×n构建，其中M、N、M、N都是整数的幂。我们证明了所提出的网络对所有N个排列都是自路由的，传播延迟为O（log_2N）。我们还证明了RN（N,m）和Spanke的网络都是该网络的特殊情况。该方法是构建低信号损耗、低串扰的无阻塞光交换网络的良好选择。我们还讨论了Banyan网络的新架构，它具有小深度和绝对的信号损耗均匀性等优点，非常适合作为光交换架构。将光榕树网络的水平扩展和垂直堆叠相结合是构建榕树光交换网络的一般方案。由此形成的水平扩展和垂直堆叠的光榕树（HVOB）网络通常需要较高的硬件成本或较大的网络深度以保证其不阻塞性。阻塞行为分析是研究网络性能并在硬件成本、网络深度和阻塞概率之间找到一个合理折衷的有效方法；然而，对一般HVOB网络阻塞行为的分析却很少。本文研究了一般HVOB网络的总体阻塞行为，给出了HVOB网络阻塞概率与平面（堆叠副本）数和级数有关的上界。该上界准确地描述了HVOB网络的整体阻塞行为，并经过大量的仿真研究验证，符合网络的严格不阻塞条件。推导出的上限具有重要意义，因为它揭示了阻塞概率、网络深度和网络硬件成本之间的内在关系，从而可以在三者之间进行理想的权衡。少

项目成果

HTN : A New Hierarchical Interconnection Network for Massively Parallel Computers

HTN：大规模并行计算机的新型分层互连网络

• 发表时间: 2003
• 期刊: IEICE Trans.on Information and Systems Vol.E86-D, No.9
• 作者: M.M.H.Rahman;S.Horiguchi
• 通讯作者: S.Horiguchi

An Efficient Self-reconfiguration Algorithm for Degradable Processor or Arrays

可降解处理器或阵列的高效自重构算法

• 发表时间: 2002
• 期刊: Journal of Information Processing Society of Japan Vol.43, No.4
• 作者: M.Fukushi;S.Horiguchi
• 通讯作者: S.Horiguchi

Springer LNCS 3320, ISBN 3-540-24013-6

施普林格 LNCS 3320，ISBN 3-540-24013-6

• 发表时间: 2004
• 作者: K-M.Liew;H.Shen;S.See;P.Fan;S.Horiguchi edited
• 通讯作者: S.Horiguchi edited

Performance of Fast Routing Algorithms in Large Optical Switches Built on the Vertical Stacking of Banyan Structures

• DOI: 10.1023/b:clus.0000028000.94688.a1
• 发表时间: 2004-07
• 期刊: Cluster Computing
• 作者: Md. Mamun-ur-Rashid Khandker;Xiaohong Jiang;P. Ho;S. Horiguchi;Hussein T. Mouftah

NTH : A New Hierarchical Interconnection Network for Massively Parallel Computers

NTH：大规模并行计算机的新型分层互连网络

• 发表时间: 2003
• 期刊: IEICE Trans.on Information and Systems Vol.E86-D, No.9
• 作者: M.M.H.Rahman;S.Horiguchi
• 通讯作者: S.Horiguchi