Unicast-based fault-tolerant multicasting in wormhole-routed hypercubes

A unicast-based fault-tolerant multicasting method is proposed for hypercubes, which can still work well when the system contains enough faults. A multicast message may be unable to reach a destination if Hamming distance between the destination and the multicast source is large enough. A multicast message fails if any one of the destinations is unreachable from the source. An effective destination ordering scheme of the destinations is proposed for one-port systems first, it is extended to all-port systems for unicast-based fault-tolerant multicasting. Unreachable destinations from the source based on the local safety information are forwarded to a reachable destination, where the multicast message can be routed reliably. Destination ordering is completed based on Hamming distance. A multiple round p-cube routing scheme is presented for a deadlock-free fault-tolerant routing for each unicast step in hypercubes, where the same virtual channel is used for each round of p-cube routing. Sufficient simulation results are presented by comparing with the previous methods.     

Maximizing the throughput of parallel jobs on hypercubes

We study a problem of scheduling n independent parallel jobs on hypercubes. A parallel job is required to be scheduled on a subcube of processors. All jobs are available at the beginning, each of which is associated with a due date. The objective is to maximize the total number of early jobs. We provide an optimal polynomial time algorithm for the unit processing time job system.     

A note on path bipancyclicity of hypercubes

In [C.H. Tsai, S.Y. Jiang, Path bipancyclicity of hypercubes, Inform. Process. Lett. 101 (2007) 93–97], the authors showed that any path in an n-cube with length of k, 2k2n−4, lies on a cycle of every even length from 2k to 2ⁿ inclusive. Base on Lemma 5 of that paper, they proved the subcase 2.2.1 of the main theorem of that paper. However, the lemma is false, therefore, we propose a lemma to replace that lemma. Therefore, the main result of [C.H. Tsai, S.Y. Jiang, Path bipancyclicity of hypercubes, Inform. Process. Lett. 101 (2007) 93–97] is still correct.     

Regular connected bipancyclic spanning subgraphs of hypercubes

An n-dimensional hypercube Q_n is a Hamiltonian graph; in other words Q_n (n≥2) contains a spanning subgraph which is 2-regular and 2-connected. In this paper, we explore yet another strong property of hypercubes. We prove that for any integer k with 3≤k≤n, Q_n (n≥3) contains a spanning subgraph which is k-regular, k-connected and bipancyclic. We also obtain the result that every mesh P_m×P_n (m,n≥2) is bipancyclic, which is used to prove the property above.     

Fast multicast on multistage interconnection networks using multi-head worms

1IntroductionMulticastcommunication,whichreferstothedeliveryofamessagefromasinglesourcenodetoanumberofdestinationnodes,isfrequentlyusedindistributed-memoryparallelcomputersystemsandnetworks[1].Efficientimplementationofmulticastcommunicationiscriticaltotheperformanceofmessage-basedscalableparallelcomputersandswitch-basedhighspeednetworks.Switch-basednetworksorindirectnetworks,basedonsomevariationsofmultistageiDterconnectionnetworks(MINs),haveemergedasapromisingnetworkajrchitectureforconstruct…     

Performance comparison of different multicast routing strategies in disruption tolerant networks

Disruption Tolerant Networks (DTNs) technologies are emerging solutions to networks that experience frequent partitions. As a result, multicast design in DTNs is a considerably more difficult problem compared to that in Internet and mobile ad hoc networks. In this paper, we first investigate three basic DTN multicast strategies, including unicast-based multicast (U-Multicast), static-tree-based multicast (ST-Multicast) and dynamic-tree-based multicast (DT-Multicast) strategies. Then we focus on studying two DT-Multicast routing schemes: Dynamic Tree Based Routing (DTBR) and On-demand Situation-aware Multicast (OS-Multicast), which address the challenges of utilizing opportunistic links to conduct dynamic multicast structures in DTNs. Performances of different strategies are then evaluated by simulations, including applying the real-world DTN traces. Our results show that OS-Multicast and DTBR can achieve higher message delivery ratio than that of using U-Multicast and ST-Multicast strategies. Also, to get better performance, we recommend that system designers select OS-Multicast when the source traffic rate is low.     

Efficient communication using message prediction for clusters of multiprocessors

With the increasing uniprocessor and symmetric multiprocessor computational power available today, interprocessor communication has become an important factor that limits the performance of clusters of workstations/multiprocessors. Many factors including communication hardware overhead, communication software overhead, and the user environment overhead (multithreading, multiuser) affect the performance of the communication subsystems in such systems. A significant portion of the software communication overhead belongs to a number of message copying operations. Ideally, it is desirable to have a true zero‐copy protocol where the message is moved directly from the send buffer in its user space to the receive buffer in the destination without any intermediate buffering. However, due to the fact that message‐passing applications at the send side do not know the final receive buffer addresses, early arrival messages have to be buffered at a temporary area. In this paper, we show that there is a message reception communication locality in message‐passing applications. We have utilized this communication locality and devised different message predictors at the receiver sides of communications. In essence, these message predictors can be efficiently used to drain the network and cache the incoming messages even if the corresponding receive calls have not yet been posted. The performance of these predictors, in terms of hit ratio, on some parallel applications are quite promising and suggest that prediction has the potential to eliminate most of the remaining message copies. We also show that the proposed predictors do not have sensitivity to the starting message reception call, and that they perform better than (or at least equal to) our previously proposed predictors. Copyright © 2002 John Wiley & Sons, Ltd.     

Efficient communication primitives on hypercubes

We give practical algorithms, complexity analysis and implementation for one-to-all broadcasting, all-to-all personalized communication and matrix transpose (with two-dimensional partitioning of the matrix) on hypercubes. We assume the following communication characteristics: circuit-switched, e-cube routing and one-port communication model. For one-to-all broadcasting, we give an algorithm that combines the well-known recursive doubling algorithm[1] and the algorithm based on edgedisjoint spanning trees[2]. The measured times of the combined algorithm are always superior to those of the edge-disjoint spanning tree algorithm and outperform the recursive doubling algorithm. For all-to-all personalized communication we propose a hybrid algorithm that combines the well-known recursive doubling algorithm[3,4] and the recently proposed direct-route algorithm[5,6] Our hybrid algorithm balances between data transfer time and start-up time of these two algorithms, and its communication complexity is estimated to be better than the two previous algorithms for a range of machine parameters. For matrix transpose with two-dimensional partitioning of the matrix, we relate a two-phase algorithm to the previous result in Reference 7. The algorithm is predicted to be better than the recursive transpose algorithm[8] by n nearest-neighbor communications[4]. It takes advantage of circuit-switched routing and is congestion-free within each phase. We also suggest a way of storing the matrix such that the transpose operation can be realized in one phase without congestion.     

双向中继协作通信系统的迭代接收机设计

针对双向中继协作系统建立了中继节点多用户接收机因子图模型,通过利用高斯参数化对混合高斯分布进行近似,提出了一种联合信道估计、多用户检测与译码的迭代消息传递算法,在合理的复杂度下有效地提高了中继接收机对于多用户混合信号的检测性能.     

Performance evaluation of multicast communication in packet-switched networks

In this paper we describe the theoretical background and practical application of QNA-MC (queueing network analyser supporting multicast), a tool for the analytical evaluation of multicast protocols. QNA-MC is based on the QNA method, which (approximately) analyses open networks of GI|G|m queues. In contrast to standard QNA, QNA-MC allows for the specification and evaluation of multicast routes. As in real multicast communication, packets leaving a particular node can be copied and deterministically routed to several other nodes. In order to analyse such queueing networks, QNA-MC converts the multicast routes to a suitable input for standard QNA. From the results delivered by QNA, QNA-MC then derives several performance measures for multicast streams in the network. A validation of QNA-MC, via a comparison to simulation results, shows that QNA-MC yields very good results. Finally, we give a detailed application example by evaluating different multicast routing algorithms for a realistic video conferencing scenario in the European MBONE.     

基于JMS规范的消息系统可靠性保障对策

为实现机场管理信息系统（AMIS）中各业务子系统之间互操作和无缝连接,基于JMS规范的消息系统首先需要解决的就是消息可靠性问题,在针对JMS规范的两种消息传递模型,结合机场消息中事件固有的先后顺序关系,提出了一种更高效更适合机场业务的保障消息可靠性的方法,并给予了实现。     

基于多协议标签交换的IP组播技术

多协议标签交换（MPLS）和组播技术的结合可以获得MPLS的高速率、QoS、流量工程、VPN和组播的带宽节省两方面的益处,MPLS和组播是两种互补的技术,这对于带QoS参数的实时的多媒体应用是必须和紧迫的。文章综述了MPLS组播技术在实现机制、组播树的构建等方面的基本原理和研究进展,分析了存在的问题和发展方向。     

一种进程间异步通信模型的研究

该文给出了在分布式系统下一种基于消息传递与排队技术的进程间异步通信模型,并给出了消息队列的管理方法和消息传递模式,最后提出了用局部按名手址方式来解决进程寻址问题。     

Performance analysis of multicast algorithms for mobile satellite communication networks

With the rise of mobile computing and an increasing need for ubiquitous high-speed data connections, Internet-in-the-sky solutions are becoming increasingly viable. To reduce the network overhead of one-to-many transmissions, the multicast protocol has been devised. The implementation of multicast in these low earth orbit (LEO) constellations is a critical component to achieving an omnipresent network environment. This paper examines the system performance associated with two terrestrial-based multicast mobility solutions, distance vector multicast routing protocol (DVMRP) with mobile IP and on demand multicast routing protocol (ODMRP). These protocols are implemented and simulated in a satellite LEO constellation. Results from the simulation trials show the ODMRP protocol provided greater than 99% reliability in packet deliverability, at the cost of more than 8 bits of overhead for every 1 bit of data for multicast groups with multiple sources. In contrast, DVMRP proved robust and scalable, with data-to-overhead ratios increasing logarithmically with membership levels. DVMRP also had less than 70 ms of average end-to-end delay, providing stable transmissions at high loading and membership levels.     

面向消息中间件的设计与实现

首先简要介绍了商务质量消息的基本概念,然后着重对面向消息中间件设计思想和实现方法进行了阐述,并给出了它在中国国家现代化支付系统中的一个应用实例。     

Performance estimations for SUPRENUM systems

A SUPRENUM system consists of many independent processors connected by a hierarchical bus system. Application problems are usually parallelized by decomposition into processes which are mapped onto the processors. Standard multigrid methods for the Poisson equation are considered as a model problem. An abstract model of the SUPRENUM system is developed consisting of five essential components. Their performance is approximated by linear functions. The efficiency and speedup of the considered parallel algorithms are estimated for several system and problem sizes. Parameter studies show the influence of the most important system parameters. The results are extended to some other multigrid algorithms.     

一种基于网络分解的多播通讯路由方法

有效的消息通讯是提高分布存储器并行计算机性能的关键因素．点对点通讯和广播通讯是２种常用的消息通讯方法，而多播通讯（Ｍｕｌｔｉｃａｓｔｉｎｇ）是指从一个源节点同时给任意多个目标节点发送消息，这种通讯比点对点和广播２种方式更具一般性，适用于很多实际应用的需求．本文针对ＰＡＲ９５并行计算机的二维网格结构，提出一种基于网络分解的多播消息通讯方法，并比较了该方法与用多个点对点方法实现多播通讯的性能.     

Shared‐memory communication approaches for an MPI message‐passing library

This paper discusses several approaches to designing and implementing shared‐memory communication protocol modules for the message‐passing interface (MPI) libraries, colloquially called ‘shared‐memory devices’. The authors present a new taxonomy for classifying designs for shared‐memory MPI communication devices and formulate design evaluation criteria. Using these criteria, the authors compare three existing shared‐memory devices for MPICH and choose the best one. The authors also present experimental results that support their choice. The contributions of this paper are three‐fold. First, the authors present the taxonomy for shared‐memory communication devices. Second, they show advantages and potential problems of the devices that belong to different classes of their taxonomy using the formulated design criteria. Third, they analyze communication performance of existing MPICH shared‐memory devices, discuss optimizations of their performance, and show the performance gains that these optimizations yield. MPICH is used for comparison, since it is a widely used MPI implementation. Copyright © 2000 John Wiley & Sons, Ltd.     

High Performance MPI over the Slingshot Interconnect

Journal of Computer Science and Technology - The Slingshot interconnect designed by HPE/Cray is becoming more relevant in high-performance computing with its deployment on the upcoming exascale...     

一种基于总线的多处理器共享内存机制

基于总线的分布式多处理器体系结构是目前常见的高性能路由器硬件体系结构,清华大学计算机系统在研制“863”重大项目“高性能安全路由器”的过程中,在基于CompactPCI总线的PowerPC多处理器平台上实现了一种多处理器共享内存机制,该共享内存机制（SM机制）实现了一系列核心对象,包括SM内存,SM信号量,SM消息队列和SM任务控制块等,本文详细介绍了SM机制的设计与实现并给出了性能测试结果。