Parallel Architectures, Algorithms, and Networks, 1999. (I-SPAN '99) Proceedings. Fourth InternationalSymposium on

23-25 June 1999

Filter Results

Displaying Results 1 - 25 of 70
  • Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)

    Publication Year: 1999
    Request permission for commercial reuse | PDF file iconPDF (340 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1999, Page(s):438 - 439
    Request permission for commercial reuse | PDF file iconPDF (8 KB)
    Freely Available from IEEE
  • Models and algorithms for optical and optoelectronic parallel computers

    Publication Year: 1999, Page(s):2 - 7
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (108 KB)

    This paper briefly reviews some of the more popular parallel computer models - pipelined optical bus and OTIS (optical transpose interconnect system) models - that employ optical interconnects. The interconnect topology and some simple algorithms for each model are also described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel architecture for high speed fractal image coding

    Publication Year: 1999, Page(s):88 - 93
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    The main problem of fractal image compression is the long search time of the domain pool. For this reason, the dedicated ASIC architecture for fractal image coding is needed. In this paper, we propose an efficient parallel architecture for fractal image coding which is based on fixed-size full-search algorithm. One of the main features of this architecture is that it uses only local communication ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A VLSI architecture for cellular automata based Reed-Solomon decoder

    Publication Year: 1999, Page(s):158 - 165
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (276 KB)

    The design of cellular automata (CA)-based SbEC-DbED (single-byte error correcting, double-byte error detecting) code, which is analogous to the extended Reed-Solomon (RS) code, was proposed by D.R. Chowdhury et al. (1994). This code has the same restriction on error correction capability as that of the extended RS code. In this paper, a new scheme has been proposed for pipeline implementation of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An optimal embedding of incomplete binary trees onto incomplete hypercubes

    Publication Year: 1999, Page(s):80 - 85
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (116 KB)

    It has been proved that incomplete binary trees can not be embedded onto incomplete hypercubes with both expansion-1 and dilation-1. In this paper we propose an optimal embedding algorithm to embed this issue with expansion-1, dilation-2. Our algorithm is a linear time algorithm, which is optimal in terms of time complexity. Furthermore, the embedding scheme is as desirable to be simple such that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed clustering for ad hoc networks

    Publication Year: 1999, Page(s):310 - 315
    Cited by:  Papers (380)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    A Distributed Clustering Algorithm (DCA) and a Distributed Mobility-Adaptive Clustering (DMAC) algorithm are presented that partition the nodes of a fully mobile network: (ad hoc network) into clusters, this giving the network a hierarchical organization. Nodes are grouped by following a new weight-based criterion that allows the choice of the nodes that coordinate the clustering process based on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MPI backend for an automatic parallelizing compiler

    Publication Year: 1999, Page(s):152 - 157
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB)

    Many naive parallel processing schemes were not as successful as many researchers thought, because of the heavy cost of communication and synchronization resulting from parallelization. In this paper, we identify the reasons for this poor performance and the compiler requirements for performance improvement. We realized that the parallelizing decisions should be derived from the overhead informati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using stochastic intervals to predict application behavior on contended resources

    Publication Year: 1999, Page(s):344 - 349
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (128 KB)

    Current distributed parallel platforms can provide the resources required to execute a scientific application efficiently. However when these platforms are shared by multiple users, performance prediction becomes increasingly difficult due to the dynamic behavior of the system. This paper addresses the use of stochastic values, represented by intervals, to parameterize performance models. We descr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel algorithms for all nearest neighbors of binary images on the BSP model

    Publication Year: 1999, Page(s):394 - 399
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    We present two parallel algorithms for computing the nearest neighbors of an n×n binary image on the Bulk-Synchronous Parallel (BSP) model. The first algorithm is for weighted distance, and the second algorithm is for Lp distance. Both algorithms run in O(n2/p+L) computation time and O(gn/√p+L) communication time using p (1⩽p⩽n) processors and i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A torus assignment for an interconnection network recursive diagonal torus

    Publication Year: 1999, Page(s):74 - 79
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (140 KB)

    Recursive Diagonal Torus (RDT) is a class of interconnection network consisting of recursively overlaid two-dimensional square diagonal tori for massively parallel computers, with up to 216 nodes. Connection structures of the RDT vary according to the assignment of upper rank diagonal tori into a node. Although traditional simple assignment called RDT(2,4,1)/α shows enough performance under ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A convergence algorithm to help enhance the performance of distributed systems on large networks

    Publication Year: 1999, Page(s):302 - 307
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (872 KB)

    The proposed convergence algorithm quickly and accurately predicts the mean message response time and communication channel. From the predicted value the correct window size of the desired percentage of time-out tolerance in message transmission and response can be computed. A correct window size is a necessity for reducing excessive message retransmissions caused by time-outs. The convergence alg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison between PVM on RHODOS and Unix

    Publication Year: 1999, Page(s):144 - 151
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (84 KB)

    Presents the architecture, services and performance results obtained from the implementation of the PVM (Parallel Virtual Machine) parallel processing tool supported by either the Unix operating system or the RHODOS distributed operating system. It is shown that the provision of several advanced services in RHODOS allow the implementation of PVM to be greatly simplified, and significant speed-ups ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using SADTs to support irregular computational problems

    Publication Year: 1999, Page(s):338 - 343
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (116 KB)

    There are well defined methods for supporting regular problems with scalable performance, typified by the HPF language and the BSP model. Less well understood is the solution of more irregular problems, supporting complex shared data structures and task dependencies, and typically requiring dynamic load balancing to sustain high performance. It is demonstrated how the use of Shared Abstract Data T... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel selection algorithms with analysis on clusters

    Publication Year: 1999, Page(s):388 - 393
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    We present three deterministic parallel selection algorithms with analysis on clusters. The first and second algorithms are proposed on the CGM (Coarse Grained Multicomputer) model. The first algorithm achieves optimality with respect to its computation time and runs in O(n/p) computation time and O(min(log p, log log n)) communication rounds if n/p⩾pε for any ε>0, wher... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized hierarchical completely-connected networks

    Publication Year: 1999, Page(s):68 - 73
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (200 KB)

    A novel network structure called generalized Hierarchical Completely-Connected networks (HCC) is proposed, and its properties and features are evaluated. A set of the HCCs constructed by the proposed method includes some conventional hierarchical networks (then it is called generalized). The construction of an HCC is started from a basic block (a level-1 block) which consists of n nodes with a con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complete exchange algorithms in wormhole-routed torus networks : a divide-and-conquer strategy

    Publication Year: 1999, Page(s):296 - 301
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    We present efficient all-to-all personalized communication algorithms for a 2D torus in wormhole-routed networks. Our complete exchange algorithm adopts divide-and-conquer approach to reduce the start-up latency significantly, which is a good metric for network performance in wormhole networks. The first algorithm recursively divides the whole network into 2×2 networks. After specially desig... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the interval routing of chordal rings

    Publication Year: 1999, Page(s):16 - 21
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (116 KB)

    The Shortest-Path Interval Routing Scheme is an efficient strategy to code distributed routing algorithms in a compact way. Characterising networks which admit shortest path Strict Interval Routing Scheme using one interval per edge (1-SIRS) is known to be NP-complete. We study 1-SIRS for a popular class of networks, known as chordal rings. We prove that for any chordal ring of degree 4 with a cho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel efficiency: the dataflow advantage

    Publication Year: 1999, Page(s):356 - 361
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    Dataflow computation models enable simpler and more efficient management of the memory hierarchy - a key barrier to the performance of many parallel programs. This paper enumerates some advantages of using the dataflow model; it argues that the programming model is simple and easily managed by a programmer and demonstrates some of the efficiencies that the dataflow model allows an underlying run-t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Circuit-switched routings for automorphisms of a hypercube

    Publication Year: 1999, Page(s):28 - 33
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    We consider, for d>1, a directed d-dimensional hypercube, Qd=(V,E), where V is a set of 2d nodes, each denoted by a distinct binary string of length , and E is the set of edges (x,y), such that x,yεV differ in exactly one position of their bit strings. Given a permutation of the vertices of Qd, which describes a source-destination mapping, we study the exis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A decoupled scheduled dataflow multithreaded architecture

    Publication Year: 1999, Page(s):138 - 143
    Cited by:  Papers (2)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (80 KB)

    Proposes a new approach to building multithreaded uniprocessors that become building blocks in high-end computing architectures. Our innovativeness stems from a multithreaded architecture with non-blocking threads where all memory accesses are decoupled from the thread execution. Data is pre-loaded into the thread context (registers), and all results are post-stored after the completion of the thr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On mapping complete binary trees into grids and extended grids

    Publication Year: 1999, Page(s):242 - 247
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (132 KB)

    We consider one-to-one, congestion one layouts of complete binary trees into 2-D grids and extended 2-D grids. For such a layout of the complete binary tree Th of height h into the square n×n grid we consider the layout's expansion ratio r=n2/(2h+1 -1). For r the least expansion among layouts of Th into grids, we obtain the bounds 1.122⩽r⩽1... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An extensible framework for coherence in distributed shared data systems

    Publication Year: 1999, Page(s):106 - 111
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (64 KB)

    The choice of sharing model (objects vs. plain shared memory), memory consistency model and coherence protocol are all fundamental aspects of the design of distributed shared data systems. Unfortunately, no single sharing model, memory model or coherence protocol is suitable for all applications. In this paper, we describe the design of an extensible distributed shared data framework, called the E... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Java4P: Java with high-level concurrency constructs

    Publication Year: 1999, Page(s):328 - 333
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (44 KB)

    While Java has provided a mechanism for concurrent programming implemented as language constructs, it is too rudimentary for most programmers and has certain limitations that make programs unnecessarily complex and prevent fine-grained concurrency. We have implemented Java4P, an extension of the Java language, that offers a simpler concurrency model and overcomes Java's limitations. Threads are no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of fault tolerant networks of workstations

    Publication Year: 1999, Page(s):125 - 134
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (72 KB)

    Functional or dataflow models of computation enable a program's run-time system to determine which portions of a computation must be repeated when faults occur. Straightforward modifications to the run-time system of Cilk 2.0 (a threaded extension of C) enable a network-of-workstations parallel processing system to tolerate fail-stop faults of the individual processors or the network. It is shown ... View full abstract»

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