Proceedings.Seventh IEEE Symposium on Parallel and Distributed Processing

25-28 Oct. 1995

Filter Results

Displaying Results 1 - 25 of 98
  • Proceedings of Seventh IEEE Symposium on Parallel and Distributed Processing

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (469 KB)
    Freely Available from IEEE
  • Data parallel logic programming in &ACE

    Publication Year: 1995, Page(s):424 - 431
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (818 KB)

    &ACE is a high performance parallel Prolog system developed at the Laboratory for Logic, Databases, and Advanced Programming that exploits and-parallelism from Prolog programs. &ACE was developed to exploit MIMD parallelism. However, SPMD parallelism also arises naturally in many Prolog programs. In this paper we develop runtime techniques that allow systems that have primarily been designed to ex... View full abstract»

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

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (123 KB)
    Freely Available from IEEE
  • Bandwidth-based upper bounds on the scalability of micro-grained network machines

    Publication Year: 1995, Page(s):579 - 586
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    This paper presents a method to bound the scalability of algorithms executing on micro-grained network machines based on communication bandwidth, β. The scalability is reported as the rate at which effective work is expended by the machine as a function of problem size. The method yields an upper bound on the effective work-rate of an algorithm A containing work W on host machine H as R=O(&be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The cyclic banyan network: a fault tolerant multistage interconnection network with the fully-adaptive self-routing

    Publication Year: 1995, Page(s):702 - 710
    Cited by:  Papers (10)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (840 KB)

    In this paper, we introduce a fault tolerant fully-adaptive self-routing scheme for a class of augmented banyan network. It can provide more multiple paths than the related previous networks between an input/output pair of a network by adding extra links between switching elements in the same stage and extending the self-routing scheme of the banyan network using the topological properties of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-level partitioning and scheduling under local memory constraint

    Publication Year: 1995, Page(s):612 - 619
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (840 KB)

    Massive uniform nested loops are broadly used in scientific and DSP applications. Due to the large amount of data handled by such applications the optimization of data accesses by fully utilizing the local memory and minimizing communication overhead is important in order to improve the overall system performance. Most of the traditional partition strategies do not consider the effect of data acce... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling and characterizing parallel computing performance on heterogeneous networks of workstations

    Publication Year: 1995, Page(s):25 - 34
    Cited by:  Papers (27)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (828 KB)

    A heterogeneous network of workstations (NOW) introduces a new performance factor into distributed computing: a large variation of the computing power of the different workstations. This unique factor makes traditional performance models/metrics for homogeneous computing measurement and evaluation not suitable for heterogeneous computing. We present models which quantify the heterogeneity of netwo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A structural theory of recursively decomposable parallel processor-networks

    Publication Year: 1995, Page(s):570 - 578
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    A `recursively decomposable' network G can be partitioned into a fixed number of subnetworks each of which is recursively decomposable and `a smaller version' of G. Several notions of such networks emerge depending on the collection of parameters chosen to model a subnetwork as `a smaller version' of another. Examples of such parameters are permutation time, bandwidth latency, topology, wires, deg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Asynchronous failure location algorithm for fiber-optic networks

    Publication Year: 1995, Page(s):690 - 693
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    All current research on fiber-optic networks assume that the underlying fiber-optic network delivers the messages correctly to their intended destination. To satisfy the assumption of correct delivery of messages, we present an algorithm that locates possible stuck-at faults in the switching subsystems of the nodes of general asynchronous fiber-optic networks and provides the nodes of such a netwo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal load sharing in dynamically heterogeneous systems

    Publication Year: 1995, Page(s):346 - 353
    Cited by:  Papers (3)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (588 KB)

    Heterogeneity of processor speed and time availability is introduced to the paradigm of load sharing among a number of autonomous and independently scheduled heterogeneous computers that communicate via message-passing interconnection system. A divisible job originating at one of the system sites is to be partitioned and executed concurrently on a suite of selected processors, to the extent of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance evaluation of load distribution strategies in parallel branch and bound computations

    Publication Year: 1995, Page(s):402 - 405
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    Load distribution is essential for efficient use of available processors in a parallel branch-and-bound computation because the computation generates and consumes non-uniform subproblems at runtime. This paper presents six decentralized load distribution strategies. They are incorporated in a runtime support system, and evaluated in the solution of set partitioning problems on two parallel compute... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sender-based message logging for reducing rollback propagation

    Publication Year: 1995, Page(s):602 - 609
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB)

    We present a sender-based message logging protocol for supporting fault tolerance with checkpointing and rollback recovery in distributed systems. Our scheme achieves the benefits of both optimistic and pessimistic message logging. Experimental results show that the maximum rollback induced by our protocol, and the number of messages logged, can be less than in optimistic receiver-based protocols,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global predicates in rough real time

    Publication Year: 1995, Page(s):17 - 24
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (596 KB)

    Evaluation of predicates on the state of a distributed system is complicated by the lack of either a common clock or common memory. In these systems, message passing is often used to order local events globally. This leads to a partial, causal ordering of system events. Predicate evaluation algorithms based on this causal ordering generally cannot determine if an unstable predicate was true at som... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards developing universal dynamic mapping algorithms

    Publication Year: 1995, Page(s):456 - 459
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    We investigate the problem of mapping dynamically generated tasks onto the processors of an MIMD-system. Our main concern is to construct an algorithm which can be integrated in distributed runtime systems like PVM or MPI. Existing methods are often not adjustable to different architecture- and application-demands. Even if they are, the adjustment has to be done manually via time-consuming experim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scalable 2d convex hull and triangulation algorithms for coarse grained multicomputers

    Publication Year: 1995, Page(s):561 - 568
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB)

    In this paper we describe scalable parallel algorithms for building the Convex Hull and a Triangulation of a given point set in R 2. These algorithms are designed for the coarse grained multicomputer model: p processors with O(n/p)≫O(1) local memory each, connected to some arbitrary interconnection network (e.g. mesh, hypercube, omega). They require time O(Tsequential/p+T<... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient deadlock-free wormhole routing in shuffle based networks

    Publication Year: 1995, Page(s):92 - 99
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    To provide deadlock-free wormhole routing in simple regular networks, virtual channels have recently been introduced. This paper presents a deadlock-free routing scheme for a class of shuffle-based directed and undirected networks. First, the network graph is partitioned into a predetermined number of subdigraphs such that there are no cycles in each subdigraph. This enables not only a deadlock-fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A lower bound for the QRQW PRAM

    Publication Year: 1995, Page(s):231 - 237
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    The queue-read, queue-write (QRQW) parallel random access machine (PRAM) model is a shared memory model which allows concurrent reading and writing with a time cost proportional to the contention. This is designed to model currently available parallel machines more accurately than either the CRCW PRAM or EREW PRAM models. Many algorithmic results have been developed for the QRQW PRAM. However, the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bisection widths of transposition graphs

    Publication Year: 1995, Page(s):681 - 688
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    We prove lower and upper bounds on bisection widths of the transposition graphs. This class of graphs contains several frequently studied interconnection networks including star graphs and hypercubes. In particular, we prove that the bisection width of the complete transposition graph is of order Θ(n.n!!) which solves the open problem (R) 3.356 of F.T. Leighton (1992) and determine nearly ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Demand-based document dissemination to reduce traffic and balance load in distributed information systems

    Publication Year: 1995, Page(s):338 - 345
    Cited by:  Papers (28)  |  Patents (37)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    Research on replication techniques to reduce traffic and minimize the latency of information retrieval in a distributed system has concentrated on client-based caching, whereby recently/frequently accessed information is cached at a client (or at a proxy thereof) in anticipation of future accesses. We believe that such myopic solutions-focussing exclusively on a particular client or set of clients... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generalized utility for parallel branch and bound algorithms

    Publication Year: 1995, Page(s):392 - 401
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (784 KB)

    Branch and bound algorithms are general methods applied to various combinatorial optimization problems. Recently, parallelizations of these algorithms have been proposed. In spite of the generality of these methods, many of the parallelizations have been set up for a specific problem and a specific parallel computer. A generalized utility PUBB (Parallelization Utility for Branch and Bound algorith... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and analysis of a systolic sorting architecture

    Publication Year: 1995, Page(s):652 - 659
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (668 KB)

    We present a new parallel sorting algorithm that uses a fixed-size sorter iteratively to sort inputs of arbitrary size. A parallel sorting architecture based on this algorithm is proposed. This architecture consists of three components, linear arrays that support constant-time operations, a multilevel sorting network, and a termination detection tree, cell operating concurrently in systolic proces... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • All-to-all broadcast in torus with wormhole-like routing

    Publication Year: 1995, Page(s):130 - 137
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    This paper deals with collective communications on distributed-memory parallel machines. We are interested in the design of efficient all-to-all broadcast algorithms on square torus of processing nodes using wormhole-like routing mechanism. The execution time is influenced by three factors, namely, the number of steps, the transmission rate and the maximum distance to cross. We first compute the l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Designing a distributed queue

    Publication Year: 1995, Page(s):304 - 311
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (668 KB)

    A common paradigm for distributed computing is the producer-consumer model. One set of processes produce objects (data, resources, or tasks) that are consumed by another set of processes. We present a simple algorithm for implementing a distributed queue. This algorithm has several parameters that need to be tuned, such as the number of probes to find an object, the amount of buffering, and the co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Restart services for highly available systems

    Publication Year: 1995, Page(s):596 - 601
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB)

    This paper proposes a design methodology for building highly available systems. In addition, we describe a set of operating system services that can be used to achieve this goal. The techniques described are intended for a parallel environment and can be generalized for any distributed system. We describe a methodology for providing basic services for high availability, specific services for resta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving hard satisfiability problems with synchronous simulated annealing on the AP1000 multiprocessor

    Publication Year: 1995, Page(s):719 - 722
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    Solving the hard satisfiability problem is difficult and time-consuming for even modest sized problem instances. This paper presents a parallel synchronous simulated annealing method for solving the Random L-Sat problem on a large scale distributed-memory multiprocessor. In particular, we use a parallel synchronous simulated annealing method called generalized speculative computation, which guaran... View full abstract»

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