[1993] Proceedings Seventh International Parallel Processing Symposium

13-16 April 1993

Filter Results

Displaying Results 1 - 25 of 130
  • C parallelizing compiler on local-network-based computer environment

    Publication Year: 1993, Page(s):849 - 853
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (446 KB)

    The local-network-based computer system, in which some workstations are connected is coming into practical use. Software development is, however, very difficult for end-users because the system has complicated problems such as load balancing, communication among processes on different workstations and so on. The authors propose a C-specific parallelizing compiler to solve these problems. The compi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • OCCAM prototyping of massively parallel applications from colored Petri-nets

    Publication Year: 1993, Page(s):842 - 848
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    The authors present a technique to build a massively parallel application from a formal description. They use the colored Petri-net formalism to model applications. This formalism allows them to concisely describe parallel applications. Theoretical results on this formalism contribute to proving the correctness of the description before implementation. Furthermore, they use some linear invariants ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance characteristics of the iPSC/860 and CM-2 I/O systems

    Publication Year: 1993, Page(s):837 - 841
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (370 KB)

    Typical scientific applications require vast amounts of processing power coupled with significant I/O capacity. Highly parallel computer systems can provide processing power at low cost, but have historically lacked I/O capacity. By evaluating the performance and scalability of the Intel iPSC/860 Concurrent File System and the Connection Machine DataVault, one can get an idea of the current state ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic parallelization of LINPACK routines on distributed memory parallel processors

    Publication Year: 1993, Page(s):830 - 836
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (689 KB)

    Distributed memory parallel processors (DMPPs) have no hardware support for a global address space. However, conventional programs written in a sequential imperative language such as Fortran typically manipulate few, large arrays. The Oxygen compiler, developed as part of the K2 project, accepts conventional Fortran code, augmented with code and data distribution directives. These directives suppo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transformation of Doacross loops on distributed memory systems

    Publication Year: 1993, Page(s):824 - 829
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (718 KB)

    Doacross loops are generally used to exploit the parallelism in loops with cross-iteration dependences. On shared memory machines, Doacross execution usually achieves useful speedup. This is not the case with distributed memory systems (multicomputers) where communication overhead can outweigh the benefits of parallelism. The authors present compile time transformation of Doacross loops with unifo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient atomic multicast protocol for client-server models

    Publication Year: 1993, Page(s):816 - 823
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (886 KB)

    Distributed applications which are replicated to achieve fault tolerance usually are faced with the problem of maintaining consistent states. To eliminate potential divergence of replica states caused by unreliable communication primitives, an atomic multicast protocol is required which guarantees delivery of messages at all receivers in the same order. The authors propose a new efficient protocol... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new horizon for sorting on mesh architectures

    Publication Year: 1993, Page(s):810 - 814
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    The author introduces the use of data duplication in massively parallel architectures as a tool for improving the running time of the basic data movement operations. He demonstrates its use by presenting two algorithms for sorting N items on mesh architectures of square root N* square root N processors. The first algorithm has an O(N/sup 1/3/ log N) running time and requires the use of O(N/sup 2/3... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mapping of uniform dependence algorithm onto fixed size processor arrays

    Publication Year: 1993, Page(s):804 - 809
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (518 KB)

    The paper addresses the problem of mapping uniform dependence algorithms onto fixed size processor arrays. The optimal computation time of executing uniform dependence algorithm on a fixed size processor array is first discussed. A mapping and partitioning method for 2-dimensional algorithms (algorithms with doubly nested loops) which can achieve near optimal computation time is proposed. Necessar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel A* algorithms and their performance on hypercube multiprocessors

    Publication Year: 1993, Page(s):797 - 803
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (813 KB)

    The authors develop parallel A* algorithms suitable for distributed-memory machines. In parallel A* algorithms, inefficiencies grow with the number of processors P used, causing performance to drop significantly at lower and intermediate work densities (the ratio of the problem size to P). To alleviate this effect, they propose a novel parallel startup phase and efficient dynamic work distribution... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards understanding block partitioning for sparse Cholesky factorization

    Publication Year: 1993, Page(s):792 - 796
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (409 KB)

    The authors examine the effect of two partitioning parameters on the performance of block-based distributed sparse Cholesky factorization. They present result to show the trends in the effect of these parameters on the computation speeds, communication costs, extent of processor idling because of load imbalances, and bookkeeping overheads. These results provide a better understanding in selecting ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Managing the bottlenecks of a parallel Gauss-Seidel algorithm for power flow analysis

    Publication Year: 1993, Page(s):787 - 791
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (539 KB)

    The parallelization and implementations of Gauss-Seidel (G-S) algorithms for power flow analysis have been investigated on a Sequent Balance shared memory (SM) machine. In this paper, the authors generalize the idea to more general computer architectures and demonstrate how to effectively increase the speedup upper bounds of G-S algorithms by properly managing the bottlenecks.<<ETX>> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel execution of real-time rule-based systems

    Publication Year: 1993, Page(s):779 - 786
    Cited by:  Papers (13)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (758 KB)

    When rule-based expert systems are used to monitor and control real-time systems, the ability of these expert systems to met stringent response time constraints is as important as their ability to produce correct results to react to input. This paper explores parallel execution as an approach to achieve higher execution speed in rule-based systems in domains requiring high performance and real-tim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new model for the performance evaluation of synchronous circuit switched multistage interconnection networks

    Publication Year: 1993, Page(s):773 - 777
    Cited by:  Papers (3)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (465 KB)

    Patel (1981) proposed a probabilistic approach to analyze the performance of multiprocessor systems using synchronous multistage interconnection networks (MINs) based on a uniform reference model and the assumption of independent requests. Through extensive simulation, the authors have found that, in many cases, their model will result in rather significant inaccuracy. the factors which cause inac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low crosstalk address encodings for optical message switching systems

    Publication Year: 1993, Page(s):768 - 772
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    An optical message switching system delivers messages from N sources to N destinations using beams of light. The redirection of the beams involves vector-matrix multiplication and a threshold operation. The authors consider the design of addresses which are both short (so that the number of threshold devices is reduced) and have low crosstalk (so that the sensitivity gap may grow). They show that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of buffered multistage interconnection networks in non uniform traffic environment

    Publication Year: 1993, Page(s):762 - 767
    Cited by:  Papers (13)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (534 KB)

    Multistage interconnection networks (MIN) are used to connect processors to memories in shared memory multiprocessor systems. A generalized Markov chain model for the performance evaluation of a single-buffered Omega network, in the presence of a hot spot, is proposed. The proposed model produces better results than existing models.<<ETX>> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamic multiple copy approach for message passing in a virtual cut-through environment

    Publication Year: 1993, Page(s):757 - 761
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (481 KB)

    The paper proposes a scheme where nodes adaptively send multiple copies of time-critical messages to increase the probability of their timely delivery. A message is replicated only when the time remaining to its deadline is below a pre-computed threshold. An off-line algorithm for computing the number of copies and the deadline thresholds is presented. Simulation results indicate that the reductio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel implementation issues of the textured algorithm for optimal routing in data networks

    Publication Year: 1993, Page(s):752 - 756
    Cited by:  Papers (8)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (544 KB)

    Parallel implementation issues of the textured algorithm to solve the optimal routing problem (ORP) in data networks is investigated. The textured model decomposes a large data network into a multi-level structure, each level contains a few subnetworks and each subnetwork is controlled by a local processor (e.g. an internet gateway). Subnetworks of the same level are not overlapped with each other... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On simulations of linear arrays, rings and 2D meshes on Fibonacci cube networks

    Publication Year: 1993, Page(s):748 - 751
    Cited by:  Papers (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (307 KB)

    The Fibonacci cube was proposed recently as an interconnection network. It has been shown that this new network topology possesses many interesting properties that are important in network design and applications. This paper addresses the following network simulation problem: Given a linear array, a ring or a two-dimensional mesh, how can be assign its nodes to the Fibonacci cube nodes so as to ke... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous parallel heuristic combinatorial search

    Publication Year: 1993, Page(s):741 - 746
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (630 KB)

    Heuristic search is the process of searching a state space under the guidance of an evaluation function. Most research on parallelizing heuristic search algorithms has emphasized system problems such as load balancing and reduction in memory use. A theoretical analysis of a new autonomous parallel heuristic search algorithm is introduced. Rather than simply dividing the search space among the proc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VMPP: a virtual machine for parallel processing

    Publication Year: 1993, Page(s):735 - 740
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (549 KB)

    In the field of parallel processing, there is a great diversity of languages and architectures which become obsolete at a rapid pace. In this environment, portability is an important issue. Unfortunately, most parallel languages are not portable. This portability problem can be solved using a virtual machine approach. In this approach, front-end translators translate various parallel source langua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Class and user based parallelism in Raven

    Publication Year: 1993, Page(s):728 - 734
    Cited by:  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (631 KB)

    This paper presents the concurrency features found in Raven, an object-oriented parallel programming system. Raven supports coarse-grained parallelism via class based and user based parallelism. Class based parallelism is provided by the implementor of the class, while user based parallelism is provided by the user, or client of objects. Raven also supports object properties which are determined a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The CM-2 data transposition problem

    Publication Year: 1993, Page(s):722 - 727
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (467 KB)

    The CM-2's natural data layout is not conducive to exchanging data with other machines. Before CM-2 data is sent to a remote machine, a bitwise transpose must be performed on the data. Each bit in an n bit value must be transmitted to a different processor, requiring n send operations through the CM-2's global router network. The time required to transpose the data limits the effective throughput ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speedup, communication complexity and blocking-a La Recherche du Temps Perdu

    Publication Year: 1993, Page(s):712 - 721
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (939 KB)

    The paper investigates the time lost in a parallel computation due to sequential and duplicated work, communication and control, and blocking. It introduces the concept of relative speedup and proposes characterizations of parallel algorithms based upon the communication complexity and the blocking model. The paper discusses the impact of the processor's architecture upon the measured speedup. It ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global semigroup operations in faulty SIMD hypercubes

    Publication Year: 1993, Page(s):706 - 711
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (537 KB)

    The authors consider the problem of computing a global semigroup operation (such as addition and multiplication) on a faulty hypercube. In particular, they study the problem of performing such an operation in an n-dimensional SIMD hypercube Q/sub n/, with upto n-1 node and/or link faults. In an SIMD hypercube, during a communication step, nodes can exchange information with their neighbors only ac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VLSI architectures for depth estimation using intensity gradient analysis

    Publication Year: 1993, Page(s):700 - 704
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (487 KB)

    Depth recovery from grey-scale images is an important topic in the field of computer and robot vision. Intensity gradient analysis (IGA) is a robust technique for inferring depth information from a sequence of images acquired by a sensor undergoing translational motion. IGA obviates the need for explicitly solving the correspondence problem and hence is an efficient technique for range estimation.... View full abstract»

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