By Topic

Parallel Architectures, Algorithms, and Networks, 1997. (I-SPAN '97) Proceedings., Third International Symposium on

20-20 Dec. 1997

Filter Results

Displaying Results 1 - 25 of 82
  • Proceedings of the 1997 International Symposium on Parallel Architectures, Algorithms and Networks (I-SPAN'97)

    Publication Year: 1997
    Request permission for commercial reuse | PDF file iconPDF (445 KB)
    Freely Available from IEEE
  • Index of authors

    Publication Year: 1997, Page(s):501 - 503
    Request permission for commercial reuse | PDF file iconPDF (91 KB)
    Freely Available from IEEE
  • Design and evaluation of a submesh allocation scheme for two-dimensional mesh-connected parallel computers

    Publication Year: 1997, Page(s):303 - 309
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    This paper presents the design and evaluation of a novel submesh allocation algorithm called the Optimized Buddy System which is derived from conventional binary buddy system. Our scheme is made feasible by using a bit-map to represent the status of the processors. The proposed scheme can be mapped into hardware directly to take the advantage of the speed of a pure combinational-logic implementati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive processor allocation strategy for mesh-connected systems

    Publication Year: 1997, Page(s):296 - 302
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    We propose an adaptive processor allocation strategy based on shape manipulations of required submesh for large mesh-connected systems. When an incoming job requests a rectangular submesh, our strategy first tries to allocate the conventional rectangular submeshes including 90-degree rotation and folding techniques. If it fails, our strategy further tries to allocate more flexible and robust L-sha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CASS: an efficient task management system for distributed memory architectures

    Publication Year: 1997, Page(s):289 - 295
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB)

    The thesis of this research is that the task of exposing the parallelism in a given application should be left to the algorithm designer, who has intimate knowledge of the application characteristics. On the other hand, the task of limiting the parallelism in a chosen parallel algorithm is best handled by the compiler or operating system for the target MPP machine. Toward this end, we have develop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On deciding granularity for optimal speedup for solving data parallel problems with clustered distributed computing

    Publication Year: 1997, Page(s):144 - 149
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    In this paper we show how to obtain optimal speedup in a master-slave model for solving data-parallel problems. Given the number of homogeneous workstations, their computation time for solving a basic sub-task of the problem, network transmission bandwidth and data volume per basic sub-task, the per-distribution number of basic sub-tasks sent to a slave for attaining the optimal speedup can be dec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A built-in self-reconfigurable scheme for 3D mesh arrays

    Publication Year: 1997, Page(s):458 - 464
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    We propose a model for fault tolerant 3D processor arrays using one-and-half track switches. Spare processors are laid on the two opposite surfaces of the 3D array. The fault compensation process is performed by shifting processors on a continuous straight line from a faulty processor to a spare on the surfaces. Two opposite directions are allowed for compensation paths only which they are not in ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evolutionary approach for scheduling in parallel processor systems

    Publication Year: 1997, Page(s):369 - 375
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    Task scheduling is essential for the proper functioning of parallel processor systems. Scheduling of tasks onto networks of parallel processors is an interesting problem that is well-defined and documented in the literature. However, most of the available techniques are based on heuristics that solve certain instances of the scheduling problem very efficiently and in reasonable amounts of time. Th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficiency of remote access caches in future SMP-based CC-NUMA multiprocessors: initial results

    Publication Year: 1997, Page(s):190 - 197
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (752 KB)

    The paper evaluates the benefits of adding a shared remote access cache (RAC) in SMP based CC-NUMA multiprocessors. We consider symmetric multiprocessor (SMP) nodes as the building blocks for a multiprocessor due to its cost effectiveness, which makes SMP nodes an attractive choice for CC-NUMA designers. We base our experimental evaluation of the future architectures on realistic hardware paramete... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RMESH algorithms for parallel string matching

    Publication Year: 1997, Page(s):223 - 226
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    String matching problem received much attention over the years due to its importance in various applications such as text/file comparison, DNA sequencing, search engines, and spelling correction. Especially with the introduction of search engines dealing with tremendous amount of textual information presented on the world wide web and the research on DNA sequencing, this problem deserves special a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech support in wireless, multihop networks

    Publication Year: 1997, Page(s):282 - 288
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    In this paper we address the evaluation of speech quality through a wireless network as perceived by the user. User perceived evaluation (in addition to the usual network metrics including delay, throughput, packet loss statistics etc.) is critical in the design of wireless multimedia networks where speech and video play a key role and are affected by several factors, such as network performance a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fiber-ribbon pipeline ring network for high-performance distributed computing systems

    Publication Year: 1997, Page(s):138 - 143
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (636 KB)

    In this paper, we propose a high-bandwidth ring network built up with fiber-ribbon point-to-point links. The network has support for both packet switched and circuit switched traffic. Very high throughputs can be achieved in the network due to pipelining, i.e., several packets can be traveling through the network simultaneously but in different segments of the ring. The network can be built today ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new general purpose parallel database system

    Publication Year: 1997, Page(s):2 - 8
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    This paper is concerned with the transparent parallelisation of declarative database queries, based on theoretical principles. We have designed an entire database architecture suitable for use on any general-purpose parallel machine. This architecture addresses the shortcomings in flexibility and scalability of commercial parallel databases. A substantial benefit is that the mathematical principle... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hamiltonian-laceability of star graphs

    Publication Year: 1997, Page(s):112 - 117
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    Suppose G is a bipartite graph with two partite sets of equal size. G is said to be strongly hamiltonian-laceable if there is a hamiltonian path between every two vertices that belong to different partite sets, and there is a path of (maximal) length N-2 between every two vertices that belong to the same partite set, where N is the order of G. The star graph is known to be bipartite. In this paper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis for dynamic tree embedding in k-partite networks by random walk

    Publication Year: 1997, Page(s):451 - 457
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    We study the problem of dynamic tree embedding in k-partite networks Gk and analyze the performance on inter-partition load distribution of the embedding. We show that, for ring-connected G k, if the embedding proceeds by taking uni-directional random walk at length randomly chosen from [0, Δ-1], where a is a multiple of k, the best-case performance is achievable at pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modular design of a large sorting network

    Publication Year: 1997, Page(s):362 - 368
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    Batcher sorting networks have been extensively used in the design of ATM switches based on Batcher-banyan interconnection network. Batcher sorting networks require large number of stages of sorting elements especially for large network sizes. This results in high delay, difficulty in partition into IC, and difficulty in maintaining synchronization across rite entire structure. In this paper, we pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color optimal self-stabilizing depth-first token circulation

    Publication Year: 1997, Page(s):317 - 323
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (652 KB)

    The notion of self-stabilization was first introduced by Dijkstra: it is the property for a system to eventually recover itself a legitimate state after any perturbation modifying the memory state. This paper proposes a self-stabilizing depth-first token circulation protocol for uniform rooted networks. Such an algorithm is very convenient to obtain the mutual exclusion or to construct a spanning ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hardware synchronization of massively parallel processes in distributed systems

    Publication Year: 1997, Page(s):157 - 164
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB)

    In this paper a new method is proposed to synchronize massively parallel processes in distributed multiprocessor systems. The method is an extension of that used in arbitration systems like Futurebus+. It also uses three global synchronization lines and a distributed synchronizer, and can be applied without changes to the existing hardware. The method allows to carry out two alternative synchroniz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pleiades: a prototype of inter-processor network generation system

    Publication Year: 1997, Page(s):202 - 206
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    A method that generates a static network for a dedicated parallel computer from an application program is proposed. The article describes the heuristic code scheduling algorithm that becomes necessary for the generation of the network. Furthermore, it describes the method of dependency analysis that becomes necessary for the insertion of the data transfer instruction and network generation. A netw... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A polynomial time algorithm for reconfiguring the 1 1/2 track-switch model with PE and bus faults

    Publication Year: 1997, Page(s):16 - 22
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    As VLSI technology has developed, the interest in implementing an entire or significant part of a parallel computer system using wafer scale integration is growing. The major problem for the case is the possibility of drastically low yield and/or reliability of the system if there is no strategy for coping with such situations. Various strategies to restructure the faulty physical system into the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the power of the mesh with hybrid buses

    Publication Year: 1997, Page(s):172 - 178
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    The main contribution of this work is to fathom the power and flexibility of the Mesh with Hybrid Buses via simulation. We propose two algorithms that perform an O(1) time stepwise simulation of an N-processor dynamic Priority CRCW-PRAM endowed with M memory cells. Our first algorithm uses a Mesh with Hybrid Buses of size max{N, MNε/2}×MNε/2 for some fixed con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Processor allocation in k-ary n-cube multiprocessors

    Publication Year: 1997, Page(s):211 - 214
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    Composed of various topologies, the k-ary n-cube system is desirable for accepting and executing topologically different tasks. We propose a new allocation strategy to utilize the large amount of processor resources in the k-ary n-cubes. Our strategy is an extension of the TC strategy on hypercubes and is able to recognize all subcubes with different topologies. Simulation results show that with s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • UHC-a massively parallel and distributed realisation of hierarchical classifier networks

    Publication Year: 1997, Page(s):186 - 189
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    In an earlier work on the design of fine-grain, scalable classifiers for massively parallel computers, the technique of unifying cascaded networks has been demonstrated. This paper further examines the method adopted using a highly parallel processing architecture, entitled Unified Hierarchical Classifiers (UHC), based on the principles of Generalised Regression Neural Networks (GRNN). As with the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel algorithm with embedded load balancing for autocorrelation matrix computation

    Publication Year: 1997, Page(s):219 - 222
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (288 KB)

    The computation of autocorrelation matrix is used heavily in several areas including signal and image processing, where parallel and application-specific architectures are also being increasingly used. Therefore, an efficient scheme to compute autocorrelation matrix on parallel architectures has tremendous benefits. In this paper, a parallel algorithm for the computation of autocorrelation matrix ... View full abstract»

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

    Publication Year: 1997, Page(s):275 - 281
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (668 KB)

    Cluster of Workstations is becoming an important kind of parallel computing platform. Two issues are essential for promoting the popularization of COW: high-performance communication mechanism and powerful programming environment. In this paper we present our research work on COW, which aims at giving a practical solution to the above issues. In order to build a high performance communication syst... View full abstract»

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