Proceedings of 4th Euromicro Workshop on Parallel and Distributed Processing

24-26 Jan. 1996

Filter Results

Displaying Results 1 - 25 of 71
  • Author index

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (123 KB)
    Freely Available from IEEE
  • Computing the singular values of the product of two matrices in distributed memory multiprocessors

    Publication Year: 1996, Page(s):15 - 21
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    A parallel algorithm for computing the singular values of the product of two matrices A and B has been developed. The algorithm is based on the Kogbetliantz (1955) method. We use a simple and efficient data distribution, adequate for multicomputers. The application of the rotations is done in a simple order that shows the same convergence rate as the sequential and the odd-even orderings. Also, th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symbolic executions of symmetrical parallel programs

    Publication Year: 1996, Page(s):327 - 334
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    We propose an algorithm to execute symbolically parallel programs with an unknown number of processes. Usually one instantiates the programs before their execution, i.e., one fixes the number of processes. We exploit the symmetrical behaviors of the processes to execute simultaneously all the instantiated programs. We define symbolic states that represent sets of states of an infinite number of in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Load balancing with internode precedence relations: a new method for static allocation of DAGs into parallel systems

    Publication Year: 1996, Page(s):252 - 257
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    In order to execute a parallel program Pp on a parallel machine PM, we must determine an allocation function which assigns Pp operations to PM processors, such that the execution time of Pp is minimum. As this problem is known to be NP-complete, a lot of alternative approaches have been proposed in the literature. We refer to load balancing (LB) approaches, ie. to mapping algorithms which determin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A small parallel C simulator

    Publication Year: 1996, Page(s):123 - 129
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (548 KB)

    The C language is an interesting choice for parallel programming with the transputer. We present a module built in C that allows a program written in INMOS Parallel C to be run in any computer with minor changes, using a sequential compiler. Only the language is simulated, not the architecture, providing fast execution and reasonably accurate timing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel simulation of a multi-dimensional computational fluid dynamics problem

    Publication Year: 1996, Page(s):11 - 14
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (412 KB)

    The simulation of computational fluid dynamics problems in two and more dimensions involves computations of multiple degrees of freedom, such as the components of velocity, which are an obvious source of parallelism. Further to our previous investigation in this area we report on our current experiences in extracting such parallelism on a distributed network platform. A finite element method for s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulating asynchronous architectures on transputer networks

    Publication Year: 1996, Page(s):274 - 281
    Cited by:  Patents (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB)

    Recently, there has been a resurgence of interest in asynchronous design techniques due to the potential of asynchronous logic for higher performance, power efficiency and immunity from clock related timing problems. Occam, a CSP based parallel language provides for the rapid development of asynchronous architectural simulation models which may then be executed on a transputer network to achieve h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TransCom: a communication microkernel for transputers

    Publication Year: 1996, Page(s):147 - 153
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    If parallel computers have to become general purpose tools, it is necessary to develop services that make transparent its internal characteristics and make parallel programming easier. Trying to fulfil this goal and to have a platform for the test and evaluation of mechanisms for a parallel architecture, a microkernel called TransCom has been designed for a distributed-memory multiprocessor. The m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed simulation of ECATNets: a conservative approach

    Publication Year: 1996, Page(s):518 - 525
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (724 KB)

    ECATNets (Extended Concurrent Algebraic Term Nets) are a kind of high-level algebraic net used for specifying various aspects of distributed and parallel systems. We address the problem of developing parallel simulation techniques to analyze ECAT-Nets. Distributed discrete event simulation (DDES) is used to develop a simulation framework for studying their behaviour. The ECATNet model to be simula... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cyclo-dynamic dataflow

    Publication Year: 1996, Page(s):319 - 326
    Cited by:  Papers (12)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    We present cyclo dynamic data flow (CDDF), a new data flow model for real time digital signal processing (DSP) applications. CDDF is an extension of cyclo static dataflow (CSDF) (G. Bilsen et al.; M. Engels et al., 1994) that keeps the interesting properties like analyzability and efficient compile time scheduling, while introducing data dependent control flow to improve the expressivity. The sema... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • InHouse-a user-oriented monitoring approach

    Publication Year: 1996, Page(s):478 - 485
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1112 KB)

    We present a new approach for monitoring and visualization of parallel processing systems. Instead of measuring the system and presenting to the user a variety of performance figures and visualization displays afterwards, in this user oriented approach the events and features of interest may be selected before instrumentation and measurements. Different techniques for this a priori filtering of ev... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Behaviour equation as solution of inheritance anomaly in concurrent object-oriented programming languages

    Publication Year: 1996, Page(s):360 - 366
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    In this paper, we propose a new model called Behaviour Description Equation which solves the problem of inheritance anomaly found in concurrent object-oriented programming languages and provides a means for the reuse of synchronisation code. The fundamental reason why inheritance anomaly occurs is that for a concurrent object, when synchronisation code is not properly separated from the method cod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Trace analysis with a relational database system

    Publication Year: 1996, Page(s):243 - 250
    Cited by:  Papers (3)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    One of the main problems dealing with trace based analysis of parallel systems is the management of the vast amounts of data produced by monitors. This paper describes the experiences made with a database approach for the management of trace data. The system is configurable in terms of trace formats and of metrics defined on this trace format. Performance measurements of the system conclude the pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-oriented model of parallel programs

    Publication Year: 1996, Page(s):80 - 86
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    The aim of this paper is to investigate an object oriented model of parallel programs in a distributed memory environment that is structural and yet has reduced complexity in dealing with parallel software. The presented model enables integration of well-known methods based on the common concept of a program control flow. A parallel program is described by a multi-flow graph, being an extension of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel processing system for simulations of vortex blob interactions

    Publication Year: 1996, Page(s):115 - 122
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (872 KB)

    The vortex method in the simulation of 2D incompressible flows with complex interacting circulations is very attractive if compared with other nowadays widespread methods. However, the vortex method is computationally very expensive and suggests the adoption of suitably powerful computing units. Our group analysed some parallelisation techniques of the algorithm, in order to obtain the best perfor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Programming shared virtual memory multiprocessors

    Publication Year: 1996, Page(s):2 - 9
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (776 KB)

    Highly parallel machines needed to solve compute intensive scientific applications are based on the distribution of physical memory across the compute nodes. The drawback of such systems is the difficult message passing programming model. Therefore, a lot of research in simplifying the programming model is going on. This article investigates the combination of a task parallel programming model imp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation of chaotic iterative processes in speed-independent computing networks

    Publication Year: 1996, Page(s):27 - 32
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    Mathematical simulation of self organizing chaotic processes in networks with speed independent processes by means of the asynchronous method of chaotic relaxations with delay using the Monte-Carlo method is considered. This method allows to imitate effectively the fulfilment of chaotic computing processes depending on the spread of time parameters of speed independent processors. Every speed inde... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Achieving good performance for dictionary machines; a scalable distributed data balancing technique

    Publication Year: 1996, Page(s):266 - 272
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB)

    We address the problem of how to process utility commands in database applications while the system remains operational and the data remains available for concurrent accesses. In particular, we focus on the online reorganization of a dictionary, a database reduced to its simplest instance, showing its implementation on a multicomputer. As is the case with implementations of dynamic structures on d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Liveness conditions for a safe distributed deadlock resolution algorithm

    Publication Year: 1996, Page(s):139 - 146
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    Although the problem of deadlock detection and resolution in distributed systems has been studied in detail during the last years, it is still an open and difficult problem for all but the simplest models. One of the main difficulties in finding adequate solutions in the Multiple-Request model resides in the need to avoid false deadlock resolutions. In this paper we show a distributed solution wit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Overlapping computations and communications in torus networks

    Publication Year: 1996, Page(s):162 - 169
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    A fundamental aspect in the design of parallel applications consists in minimizing communications: reducing the number of messages, or overlapping computations and communications. The objective of this paper is the design of parallel algorithms that use processors and expensive resources such as communications efficiently. We present a partial embedding of computation and communication graphs that... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using ITL and Tempura for large-scale specification and simulation

    Publication Year: 1996, Page(s):493 - 500
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (636 KB)

    ITL and Tempura are used for respectively the formal specification and simulation of a large scale system, namely the general purpose multi threaded dataflow processor EP/3. The paper shows that this processor can be specified concisely within ITL and simulated with Tempura. But it also discusses some problems encountered during the specification and simulation, and indicates what should be added ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deblocking event algorithm: a new approach to conservative parallel discrete event simulation

    Publication Year: 1996, Page(s):510 - 517
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    Presents a new approach to perform distributed event driven simulation that we have named the `deblocking event algorithm'. This algorithm adopts the conservative paradigm, but takes into account the structural properties of the simulation network to reduce the overhead that any distributed simulation scheme inherently has. At the same time, the algorithm keeps a high degree of activity in the net... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application-dependent performability evaluation of fault-tolerant multiprocessors

    Publication Year: 1996, Page(s):310 - 318
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (856 KB)

    A case study of performance and dependability evaluation of fault tolerant multiprocessors is presented. Two specific architectures are analyzed taking into account system functionality, actual workloads, failures of system components as well as the inter component dependencies. Since the evaluation of such complex systems has to be performed already during the design phase, simulation models are ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interconnection network design: a statistical analysis of interactions between factors

    Publication Year: 1996, Page(s):211 - 218
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    Interconnection network performance depends on several parameters, including network design parameters, network size, message traffic and message length. Simulation is the methodology usually followed in evaluation studies, because the model can more faithfully represent hardware implementation, taking into account more details. Nevertheless, the number of parameter combinations is often high, and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel processing environment for speech signal processing applications

    Publication Year: 1996, Page(s):470 - 477
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB)

    The paper describes a software tool that has been developed for production of speech signal processing systems, but may be easily expanded to include any 1 dimensional signal processing problem with multiple inputs and outputs. The tool allows the user to define an arbitrary set of interconnected signal processing functions that are interlinked by vectors of signal data, this kind of problem is th... View full abstract»

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