By Topic

Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 1995. MASCOTS '95., Proceedings of the Third International Workshop on

18-20 Jan. 1995

Filter Results

Displaying Results 1 - 25 of 76
  • Multiple times in systems: a perspective

    Publication Year: 1995
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (39 KB)

    Summary form only given. Time plays a fundamental role in real-time computer controlled systems, in which the system dynamics depend on the temporal behavior of controlling tasks. The temporal behavior of the tasks, in turn, is determined through the system level policies which are designed to execute the tasks in a timely manner by preserving the time constraints on their execution. We show that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MASCOTS '95. Proceedings of the Third International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (14 KB)
    Freely Available from IEEE
  • An eclectic survey of bounding methods for Markov chain models

    Publication Year: 1995, Page(s):184 - 188
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    Markov models are often used for performance modeling. However most models do not have closed form solutions, and numerical solutions are often not feasible due to the large (or even infinite) state space of models of practical interest. One can sometimes take advantage of special structures such as nearly completely decomposable models or models with matrix analytic solutions. This paper presents... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scheduling of random task graphs on parallel processors

    Publication Year: 1995, Page(s):143 - 147
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    Task graphs are one of the most used models for representing parallel computations. The structures of these graphs are sometimes obtained when compiling the parallel programs. In many other cases, however, they can be determined only at run time. In this paper, we study the scheduling of parallel computations whose task graphs are generated at run time. We obtain a simple optimal scheduling policy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Product form in discrete-time queueing networks: new issues

    Publication Year: 1995, Page(s):148 - 153
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (436 KB)

    This paper presents product form equilibrium distributions for different types of discrete-time queueing systems, in which group transitions are allowed both for arrival and service processes. Only the late arrival case is considered. When the system is open the product form is valid when we assume a geometric arrival process and a truncated geometric service time distribution. Then, we develop so... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An experimental assessment of Express parallel programming environment

    Publication Year: 1995, Page(s):200 - 204
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    This paper describes a performance evaluation study of Express programming environment on the iPSC/860 hypercube computer. Express allows parallel programs to be developed in a completely portable fashion and is available on most commercially available parallel computers as well as networks of workstations. We have developed a set of benchmarks to make a comprehensive performance assessment of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spare capacity assignment in telecom networks using path restoration

    Publication Year: 1995, Page(s):370 - 374
    Cited by:  Papers (3)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    Path restoration scheme can be used in augmenting existing telecommunication networks with adequate spare capacity to achieve a desired level of protection against link failures. Path restoration planning corresponds to the multi-commodity flow problem, which is computationally hard. In this paper, we present the details of an approximation scheme for the path based restoration planning problem an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation model for analysis of synchronous digital hierarchy network payload jitter

    Publication Year: 1995, Page(s):275 - 279
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    Since pointer processing in SONET/SDH networks is a complex non-linear process, computer simulation is required to accurately characterize the network jitter induced in the underlying PDH payloads. While previous behavioral network models provide accurate results for normal synchronous operation, they do not model the periodic pointer sequences which occur during holdover mode. This paper's method... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Approximate MVA for client-server systems with nonpreemptive priority

    Publication Year: 1995, Page(s):155 - 162
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    A new approximate algorithm for the Stochastic Rendezvous Network (SRVN) model with nonpreemptive priority scheduling is introduced in this paper. SRVN is a performance model for client-server systems with synchronous communication which is different from Queueing Network models in two ways: it allows for nested services, and offers two phases of service (the first executed while the client is blo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A robust heuristic for minimizing cell loss in ATM networks

    Publication Year: 1995, Page(s):48 - 52
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    Limited buffers in ATM network elements will inevitably result in cell loss. We model an ATM network as a tandem network with finite buffers and investigate the performance of a cell-level control policy (the HILO heuristic) that is designed to minimize cell loss rates. The HILO heuristic is based on limited feedback about the cells awaiting transmission in adjacent network nodes. We demonstrate v... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extensible parallel program performance visualization

    Publication Year: 1995, Page(s):205 - 211
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (636 KB)

    Performance bugs have classically been difficult to identify in high performance programs. The problem arises because there is a broad spectrum of causes of performance degradation, and because it may be necessary to apply specialized diagnostics to search the performance space. The prototype tuning environment we are developing enables one to explore the performance space of a program using custo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time and performance evaluation extensions of specification language LOTOS

    Publication Year: 1995, Page(s):382 - 386
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    The paper contains extensions of specification language LOTOS in three directions: actions with durations, real-time and performance evaluation constructions. We have introduced a time-out as a specific action. An expressive power of this action has been discussed. We have defined such a performance evaluation extension of LOTOS that can be used as a modelling language for performance evaluation o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the performance evaluation of asynchronous processor architectures

    Publication Year: 1995, Page(s):100 - 104
    Cited by:  Papers (2)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    This paper evaluates and analyses the influence of an asynchronous control paradigm on the performance of processor architectures. The idea of a micronet is introduced which models the datapath as a network of concurrent functional units which communicate with each other asynchronously. This allows the efficient exploitation of fine-grained instruction-level parallelism (ILP). A macronet-based asy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Q2: a new performance analysis tool exploiting numerical transform inversion

    Publication Year: 1995, Page(s):411 - 415
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    We describe a tool that we are developing to help analyze the performance of emerging telecommunication systems. These emerging systems include ATM, broadband, intelligent and wireless networks, each of which will support a wide variety of services and media. The tool is distinguished from previous tools by exploiting numerical transform inversion. We describe three modules in the tool. These modu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance space of a GI/G/1 queueing system under a percentile goal criterion

    Publication Year: 1995, Page(s):53 - 57
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The delay performance of a GT/G/1 queueing system with a single server and multiple classes is studied under a new criterion, namely the percentile goal criterion. We assume independent and identically distributed general interarrival times and general service times for each class of packets. The percentile goal criterion is characterized by a prespecified waiting time objective and the goal is to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • XNeuroGene: a system for evolving artificial neural networks

    Publication Year: 1995, Page(s):436 - 439
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    Artificial nervous systems (ANS) controlling action coordination tasks are in general very difficult to design. This is partly due to the great number of parameters that can be optimized: neural net connectivity, neuron functionality, weight settings etc. Another problem is posed by the need to automatically construct neuron clusters (modules) which can subsequently be used as building blocks. We ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discrete event simulation modelling of concurrent access in ATM-based computer networks

    Publication Year: 1995, Page(s):365 - 369
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    The problem of sharing resources in telecommunications networks has benefited from a rich theoretical development in the area of statistical multiplexing. Integrating data and other very bursty traffic on these networks changes the way of managing the concurrent access to network resources. Discrete event simulation is used in the paper for the quantitative analysis of the trade-off involved in gi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modelling of client-server systems

    Publication Year: 1995, Page(s):340 - 344
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    The paper examines client-server systems and shows the kind of measurements that can be obtained by analyzing the structural and performance models and a combined study of dependability and performance. More specifically, performability measures are presented which combine the effects of violation of deadlines and those relating to component fault/repair phenomena View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A heuristic algorithm for admission control in ATM networks

    Publication Year: 1995, Page(s):280 - 286
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    We present a real time front-end admission control scheme for ATM networks which dynamically shapes the traffic. The call management scheme uses the burstiness associated with traffic sources in a heterogeneous ATM environment to effect dynamic assignment of bandwidth. Call acceptance is based on an on-line evaluation of the upper bound on cell loss probability. The negotiated grade of service wil... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A short theory of multiprogramming

    Publication Year: 1995, Page(s):2 - 7
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    Pressures to use virtual memory are growing. Newer versions of application programs are growing explosively; for example, Microsoft Word, around 400K bytes in Version 3, is 25 megabytes in Version 6. Servers such as those running Windows NT use multiprogramming to share memory among jobs. We may see soon a revival of interest in the theory of multiprogramming as server administrators discover and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Approximate performance models of real-time software systems

    Publication Year: 1995, Page(s):163 - 167
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    Design of real-time systems needs to take into account their performance behaviour before their implementation. This goal can be attained by means of queueing network modelling. To process this kind of models normally simulation is used with its inherent costs of debugging and running times. This paper presents the analysis and comparison of several kinds of performance models of a basic software ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient algorithm to compute the synchronized product

    Publication Year: 1995, Page(s):77 - 81
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    Computing all the reachable states of synchronized automata is important in the mechanical verification of concurrent programs. It is however a hard task because this set of states typically grows exponentially in the number of automata involved. We present a new approach that yields interesting experimental results, both an memory requirements and computation times. It uses a new data structure, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Program modelling via inter-reference gaps and applications

    Publication Year: 1995, Page(s):212 - 216
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    Locality of reference in program behavior has been studied and modelled extensively because of its application to CPU, cache and virtual memory design, code optimization, multiprogramming etc. In this paper we propose a scheme based on Markov chains for modelling the time interval between successive references to the same address in a program execution. Using this technique and trace driven simula... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A tool for optimizing large scale parallel applications

    Publication Year: 1995, Page(s):293 - 296
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    Developments in the field of supercomputing during the last couple of years showed that new classes of applications (The Grand Challenges) gain in importance that demand for new dimensions in computing power. The development of efficient parallel programs has to be supported in all phases of the program design and coding. This paper introduces a tool that supports the optimization of programs on m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A two-queue polling model with a threshold service policy

    Publication Year: 1995, Page(s):84 - 88
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (288 KB)

    We consider a model of two M/M/1 queues, served by a single server. The service policy for this polling model is of threshold type: the server serves queue 1 exhaustively, and does not remain at an empty queue if the other one is non-empty. It switches from queue 2 to queue 1 when the size of the latter queue reaches some level T. All switches are instantaneous. We determine the joint queue length... View full abstract»

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