By Topic

Algorithms and Architectures for Parallel Processing, 2002. Proceedings. Fifth International Conference on

Date 23-25 Oct. 2002

Filter Results

Displaying Results 1 - 25 of 81
  • Proceedings Fifth International Conference on Algorithms and Architectures for Parallel Processing

    Publication Year: 2002
    Request permission for commercial reuse | PDF file iconPDF (374 KB)
    Freely Available from IEEE
  • Efficient weighted multiselection in parallel architectures

    Publication Year: 2002, Page(s):2 - 8
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (303 KB) | HTML iconHTML

    We study parallel solutions to the problem of weighted multiselection to select r elements on given weighted-ranks from a set S of n weighted elements, where an element is on weighted rank k if it is the smallest element such that the aggregated weight of all elements not greater than it in S is not smaller than k. We propose efficient algorithms on two of the most popular parallel architectures, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary approach for message scheduling in optical Omega networks

    Publication Year: 2002, Page(s):9 - 17
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (390 KB) | HTML iconHTML

    Optimal routing in optical Omega network is an NP-hard problem and traditional heuristics have only limited success in solving small to midsize routing problems. In this paper, we explore the possibility of using genetic algorithm (GA) to optimize a routing solution on optical Omega networks, and determine the impact of various factors, specifically the impact of crossover probability, mutation pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local block factorization and its parallelization to block tridiagonal matrices

    Publication Year: 2002, Page(s):18 - 21
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (270 KB) | HTML iconHTML

    A type of incomplete decomposition preconditioner based on local block factorization is considered, for the matrices derived from discreting 2-D or 3-D elliptic partial differential equations. We prove that the condition numbers of the preconditioned matrices are small, which means that the constructed preconditioners are effective. Further we consider an efficient parallel version of the precondi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parity declustering data layout for tolerating dependent disk failures in network RAID systems

    Publication Year: 2002, Page(s):22 - 25
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB) | HTML iconHTML

    In this paper, we present a new data layout - "string parity declustering data layout". This data layout incorporates advantages of both orthogonal data layout and weighted parity declustering data layout. The simulation results show that, it improves the reliability of RAID systems (especially network RAID systems) greatly. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis of update ordering in a cluster of replicated servers

    Publication Year: 2002, Page(s):28 - 35
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (303 KB) | HTML iconHTML

    This paper analyses update ordering and its impact on the performance of a cluster of replicated servers. We propose a model for update orderings and constraints and develop a number of algorithms for implementing different ordering constraints. A performance study is then carried out to analyse the update ordering model. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TODS: cluster object storage platform designed for scalable services

    Publication Year: 2002, Page(s):36 - 43
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (434 KB) | HTML iconHTML

    In this paper we present the design and implementation of Tsinghua object data store, a cluster object storage system to support the building of scalable services. TODS provides a unified, transparent and object-oriented view of the storage devices of the whole cluster, which greatly simplifies clustered service development. In the meantime, it is designed to be very scalable and efficient. Servic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of dynamic load balancing algorithm on cluster of workstations and PCs

    Publication Year: 2002, Page(s):44 - 47
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (214 KB) | HTML iconHTML

    Heterogeneous parallel systems are becoming increasingly more common, especially with the increasing use of cluster computers, such as PCs and networks of workstations for parallel computing. The main concern of this paper is measuring and evaluating the performance of such parallel systems, based on a dynamic load balancing algorithm for the parallel search algorithm: a depth-first search algorit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TH-CluFS: an open platform cluster file system

    Publication Year: 2002, Page(s):48 - 51
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (318 KB) | HTML iconHTML

    In this paper, we present the design and implementation of a new cluster file system, TH-CluFS, which is based on the standard NFS protocol and is implemented in the user level space completely. This open platform file system is important as the clusters become larger and heterogeneous. To take advantages of the accumulated resources and high-speed network in clusters, TH-CluFS follows a serverles... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Universal parallel numerical computing for 3D convection-diffusion equation with variable coefficients

    Publication Year: 2002, Page(s):54 - 59
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (661 KB) | HTML iconHTML

    A universal parallelized numerical approach for solving the three-dimensional (3D) convection diffusion equation with variable coefficients is proposed by combining the implicit difference method of Crank-Nicolson with alternating bar parallelization, which can be used to solve numerically any variation of the 3D convection diffusion equation. By virtue of bar parallelization and a multistep itera... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient loop partitioning for parallel codes of irregular scientific computations

    Publication Year: 2002, Page(s):60 - 70
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (414 KB) | HTML iconHTML

    In most distributed memory computations, node programs are executed on processors according to the owner computes rule. However, the owner computes rule is not best suited for irregular application codes. In irregular application codes, use of indirection in accessing left hand side array makes it difficult to partition loop iterations, and using indirection in accessing right hand side elements m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A unified theory for Krylov algorithms

    Publication Year: 2002, Page(s):71 - 75
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB) | HTML iconHTML

    Large systems of linear equations arise in many different scientific applications. For example, partial differential equations discretized with the finite difference or finite element method yield a system of equations. Large systems can be solved with either sparse factorization techniques or iterative methods. These two approaches can be combined into a method that uses approximate factorization... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evolutionary algorithm of contracting search space based on partial ordering relation for constrained optimization problems

    Publication Year: 2002, Page(s):76 - 81
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (281 KB) | HTML iconHTML

    A new evolutionary algorithm, which can contract search space based on the partial ordering relation and is designed to solve nonlinear programming (NLP), is proposed in this paper. Firstly, the partial ordering relation is used for evaluating an individual, which ensures that individual competition is more impartial. Secondly, by taking advantage of incomplete evolution, which provides good indiv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed image processing on spiral architecture

    Publication Year: 2002, Page(s):84 - 91
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (339 KB) | HTML iconHTML

    Improving computation efficiency is a key issue in image processing, especially in edge detection, which is very computationally intensive. With the development of real-time applications of image processing, fast processing response is becoming more critical. In this paper, a technique for distributed image processing on a spiral architecture is proposed, which provides a platform for speeding up ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-oriented finite element analysis: a distributed approach to mesh generation

    Publication Year: 2002, Page(s):92 - 99
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (323 KB) | HTML iconHTML

    The object-oriented finite element method (OOFEM) has attracted the attention of many researchers. Compared with the traditional finite element method, OOFEM software has the advantages of maintenance and reuse. Moreover, it is easier to expand the architecture to a distributed one. In this paper, we introduce a distributed architecture of a object-oriented finite element preprocessor. A compariso... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An algorithm for coscheduling tasks on network of heterogeneous workstations

    Publication Year: 2002, Page(s):100 - 104
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (329 KB) | HTML iconHTML

    An algorithm is proposed, which solves cooperative concurrent computing tasks by using the idle cycle of a number of high performance heterogeneous workstations interconnected by a high-speed network. In order to get better parallel computation performance, this paper gives a model and an algorithm of task scheduling among heterogeneous workstations, in which the costs of loading data, computing, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new divide and conquer algorithm for real symmetric band generalized eigenvalue problem

    Publication Year: 2002, Page(s):105 - 108
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (250 KB) | HTML iconHTML

    In this paper we present a new divide and conquer algorithm for solving a real symmetric band generalized eigenvalue problem under a distributed environment. This algorithm computes generalized eigenpairs of a real symmetric band matrix pair using the divide and conquer method combined with multisection and generalized Rayleigh quotient iteration. Theoretical analysis and numerical experiments pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient multicast routing algorithms on mesh networks

    Publication Year: 2002, Page(s):110 - 117
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (285 KB) | HTML iconHTML

    Multicast can provide efficient information dissemination for a subscribed user group on networks. This paper proposes a set of novel efficient fault-tolerant multicast routing algorithms on mesh networks using optimal shared free routing. The algorithms can select an optimal root for constructing the shared tree so as to minimize the average delay for multicast messages. Tree generation is able t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework of using cooperating mobile agents to achieve load sharing in distributed Web server groups

    Publication Year: 2002, Page(s):118 - 125
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (511 KB) | HTML iconHTML

    This paper studies the issues of using mobile agents to achieve load sharing for network services in a wide-area network environment such as the Internet. Traditionally, load sharing algorithms are based on the message-passing paradigm. In this paper, we propose the use of mobile agents as an aid to design fully distributed and dynamic load-sharing mechanisms for wide-area network services, which ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A genetic algorithm for task scheduling in network computing environment

    Publication Year: 2002, Page(s):126 - 129
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (326 KB) | HTML iconHTML

    Huge task can be decomposed into some partially ordered computational sub-tasks, then resolved The general problem of task scheduling is known to be NP-hard, and genetic algorithms have received much attention as a class of robust stochastic search algorithms for task scheduling. While the construction of initial population has some limitations and most of the previous work only considers homogene... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • THMonitor: a new schema of WWW updating monitor

    Publication Year: 2002, Page(s):130 - 133
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (302 KB) | HTML iconHTML

    The World Wide Web is growing rapidly with new and changing Web content. Detecting changes in Web pages from the client side is crucial for Web surfers who want the newest information on the Web site. Instead of pull-based browsing, update monitoring is a promising area of research where the system brings the right information to the right user at the right time. In this paper we present the desig... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unified approach for system-level generative programming

    Publication Year: 2002, Page(s):136 - 142
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (283 KB) | HTML iconHTML

    Today's and future distributed software systems will certainly require combining heterogeneous software components that are geographically dispersed so that its realization not only meets the functional requirements, but also satisfies the nonfunctional criteria such as the desired quality of services (QoS). The unified approach (UA) incorporates the concepts of product line practice (PLP) and gen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Asymmetric VLAN management protocol for distributed architecture

    Publication Year: 2002, Page(s):143 - 147
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB) | HTML iconHTML

    This paper provides an asymmetric VLAN management protocol implemented in switch with distributed architecture, to make an end station available to others in different VLANs without routers in the case end stations are VLAN-unaware, as a supplement to IEEE 802.1Q standard. This paper first introduces the asymmetric VLAN management protocol and gives the protocol properties, then extends the protoc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A distributed dynamic self-immunity security architecture

    Publication Year: 2002, Page(s):148 - 151
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (726 KB) | HTML iconHTML

    Computer network crimes present trends such as the simplification of attack tools, contraposition of attack purposes, and systematization of attack modes. This paper proposes the distributed dynamic self-immunity security architecture (DDSSA) to protect against these new trends. Through a dynamic cycle of detection, collection, decision making, policy distribution, and response, DDSSA can solve th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on network anycast

    Publication Year: 2002, Page(s):154 - 161
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (294 KB) | HTML iconHTML

    Anycast is defined as a service in IPv6, which provides stateless best effort delivery of an anycast datagram to at least one, and preferably only one host. It is a topic of increasing interest. This paper is an attempt to gather and report on the work done on anycast. There are two main categories at present: network-layer anycast and application-layer anycast. Both involve anycast architectures,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.