Proceedings of Third Workshop on Parallel and Distributed Real-Time Systems

25-25 April 1995

Filter Results

Displaying Results 1 - 25 of 35
  • Proceedings of Third Workshop on Parallel and Distributed Real-Time Systems

    Publication Year: 1995
    Request permission for commercial reuse | |PDF file iconPDF (126 KB)
    Freely Available from IEEE
  • A study of network routers for real-time parallel computers

    Publication Year: 1995, Page(s):202 - 203
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (156 KB)

    A candidate network function is accurately defined for real-time parallel computers. A concise, time-driven, flit-based, priority-driven, wormhole-routed, network simulator has been designed. Experimentation is performed by monitoring the latency and the throughput with variations in different network parameters. Initially the destination address, message length and message priority are generated ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The peer tasking design method

    Publication Year: 1995, Page(s):20 - 29
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (972 KB)

    This paper is a preliminary report of an ARPA sponsored study. It focuses on designing real-time command and control or battle management systems for parallel and distributed architectures. Due to delays in other ARPA programs, the targeted architectures were not available during the time frame of the study. The results of the study were, however, tested on more conventional sequential and paralle... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Timing insensitive binary-to-binary migration across multiprocessor architectures

    Publication Year: 1995, Page(s):193 - 194
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (188 KB)

    TIBBIT is a method of performing a binary to binary translation of an application from one architecture (source) to another (target) while maintaining the timing behavior of the code, even when it depends upon the speed (e.g. clock rate) of the host processor. Translated applications are scheduled under a real-time operating system on the target system such that processor-speed dependent behavior ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the modeling of distributed real-time systems

    Publication Year: 1995, Page(s):4 - 5
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (188 KB)

    This paper discusses the requirements for the modeling of distributed real-time systems, both from an engineering and a reengineering point of view. A suitable extension of the object-oriented paradigm with execution graphs, modeled as partial orders, is briefly described. The objects and execution graphs are attended with annotations suitable for the description of non-fictional system properties... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Runtime reallocation of divisible load under processor execution deadlines

    Publication Year: 1995, Page(s):30 - 31
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (168 KB)

    We examine the problem of optimizing the reallocation and execution of divisible load originating in different amounts at the sites of an interconnected set of heterogeneous processors characterized by their load computing speeds and I/O speeds. Each processor imposes, a priori, a hard deadline on its allocated task completion. The objective of load retasking and redistribution, which is implement... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scheduling tasks in real-time systems using evolutionary strategies

    Publication Year: 1995, Page(s):195 - 196
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (160 KB)

    Finding feasible schedules for tasks running in hard, real-time distributed computing systems is generally NP-hard. This paper describes a heuristic algorithm using evolutionary strategies. Our results indicate that the evolutionary strategies can find feasible schedules (assuming they exist) in very short periods of time View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time multimedia network system using VLIW hardware stack processor

    Publication Year: 1995, Page(s):84 - 89
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (336 KB)

    We propose a multimedia network system using VLIW hardware stack processors, which supports mainly the presentation layer of OSI protocol and fits various real-time applications including intelligent processing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predictability of program execution times on superscalar pipelined architectures

    Publication Year: 1995, Page(s):104 - 112
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (728 KB)

    Predicting the execution time of straight line code sequences is essential for reliable real-time systems. Traditional timing techniques suck as table lookup method, instruction counting and averaging are inadequate to predict a tight execution time on reduced instruction set processors since they do not account for the low-level parallelism that exists in these processors. This paper presents a s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed real-time computing

    Publication Year: 1995, Page(s):6 - 7
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (172 KB)

    This paper outlines the key areas of research in distributed real-time systems that are being investigated within the Spring Project at the University of Massachusetts. This includes reflective, multiprocessor operating systems, dynamic guarantees, adaptive flow, control filters, adaptive fault tolerance, architecture support, and active real-time databases View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Partitioning Ada programs for distributed platforms

    Publication Year: 1995, Page(s):33 - 34
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (140 KB)

    Few work has been done in the past which has dealt with programming for loosely coupled distributed systems. However, distributed execution is becoming increasingly important for real time systems, since most of them are implemented with distributed processors. Programming multiprocessors through a single program approach offers many advantages from a software engineering point of view like, abstr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SATURNE: a reactive-anytime programming model for intelligent embedded real-time systems

    Publication Year: 1995, Page(s):134 - 135
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (196 KB)

    One of the major challenge of next embedded systems is to involve intelligence while preserving the classical real-time properties: (a) reactivity, i.e. the capability to react continuously towards asynchronous inputs, and (b) predictability. Furthermore, one of the main property which is requested in this kind of systems operating in a highly non-deterministic outside environment, is adaptability... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Avoiding deadline decay under transient overloads

    Publication Year: 1995, Page(s):198 - 200
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (252 KB)

    Deadline scheduling policies based on stochastic computation times perform well in average but fail in presence of transient overloads, causing already scheduled tasks to miss their deadline. This paper presents an approach using medium-term scheduling policies to cope with the problem of transient overload in dynamic real-time systems. The proposed approach has been implemented in a Real-Time Dis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On building distributed soft real-time systems

    Publication Year: 1995, Page(s):13 - 19
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (488 KB)

    When building a distributed real-time system, one can either build the whole system from scratch, or from pre-existing standard components. Although the former allows better scheduling design, it may not be economical in terms of the cost and time of development. This paper studies the performance of distributed soft real-time systems that use standard components with various scheduling algorithms... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Verification of schedulability of real-time systems with extended time Petri nets

    Publication Year: 1995, Page(s):185 - 192
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (528 KB)

    Most verification algorithms for schedulability of real-time systems are based on an approximate computation which only considers worst cases. Although they always find correct schedulings, in which any task never violates its deadline, those schedulings are sometimes too strict. In this paper, in order to verify schedulability more precisely we propose a verification method based on the state spa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based system development

    Publication Year: 1995, Page(s):2 - 3
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (168 KB)

    Reactive systems, i.e. systems reacting to events in their environment, base their operation on models of the objects of interest in the environment. In the current practice these models are implemented as algorithms ultimately relating observations to actions. This approach results in systems that are rather inflexible and sometimes difficult to maintain. In addition, the different uses made of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time networking over HIPPI

    Publication Year: 1995, Page(s):76 - 83
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (540 KB)

    HIPPI provides a very-high-speed communication medium, which is very well suited for a large number of bandwidth-demanding distributed applications. Unfortunately, its circuit-switched nature makes it very difficult to provide real-time guarantees when connections contend for network resources. We present a time-division-multiplex access scheme designed to give timing guarantees to high-speed conn... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fault-tolerant scheduling algorithm for distributed real-time systems

    Publication Year: 1995, Page(s):99 - 103
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (340 KB)

    In a distributed real-time system, tolerance to faults on processing nodes in the system is achieved by means of redundant nodes and a fault-tolerant scheduling algorithm. Since redundant nodes increase total failure rate of the system, the number of such redundant nodes should be small. This paper proposes a procedure for fault-tolerant scheduling, which realizes fault-tolerance via a small numbe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimized priority assignment for tasks and messages in distributed hard real-time systems

    Publication Year: 1995, Page(s):124 - 132
    Cited by:  Papers (42)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (548 KB)

    Recent advances in the analysis of distributed realtime systems have made it possible to predict if hard realtime requirements will be met. However, it is still difficult to find a feasible priority assignment when the utilization levels of the CPUs and communication networks are pushed near to their limits. This paper presents a new heuristic algorithm for optimizing the assignment of priorities ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ada 95 eliminates race conditions

    Publication Year: 1995, Page(s):10 - 11
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (144 KB)

    This brief paper raises the issue of whether Ada 95 gives full control of queuing when required. Ada 83 prevented the programmer from having detailed control and inadvertently introduced nasty race conditions. The only solution in Ada 83 was to abandon Ada tasking and use low level primitives such as semaphores. Ada 95 includes a number of new features such as the requeue statement, explicit prior... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Atomic broadcast: a case study in locative temporal logic

    Publication Year: 1995, Page(s):175 - 183
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (576 KB)

    Locative temporal logic (LTL) has been developed for the specification and verification of distributed real time systems. It is a two-sorted modal logic in the sense that linear time temporal logic has been extended by a locative sort modelling communication networks. In its intended application area, LTL is more intuitive and adequate than other observer-based approaches because it is moulded aft... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Testing Ada Annex E-distributed systems

    Publication Year: 1995, Page(s):72 - 73
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (100 KB)

    With the addition of special needs annexes to Ada 95, the traditional reliance on Ada Compiler Validation Capability style testing may not suffice. This paper explores some alternatives for testing a portion of the Distributed Systems Annex that deals with the method used to communicate between multi-processors in a real-time Ada system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bounding the end-to-end response time in multiprocessor real-time systems

    Publication Year: 1995, Page(s):91 - 98
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (420 KB)

    In a multiprocessor real-time system, a task may execute in turn on several processors before it completes. The task may have different priorities on different processors and may execute on some processors more than once. Existing techniques for bounding the response times of such tasks are not effective. In this paper, we present a method to compute tighter upper bounds on their response times View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Drawing execution graphs by parsing

    Publication Year: 1995, Page(s):113 - 122
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (668 KB)

    We present an algorithm for drawing execution graphs. Such graphs represent the control flow in a program. The fact that a program is constructed according to a grammar is reflected in the corresponding execution graph. Therefore, we introduce graph production rules that are based on generally used programming language constructs. Each rule is applied to a certain class of topologies of the graph.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time computing cornerstones: a system engineer's view

    Publication Year: 1995, Page(s):8 - 9
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (184 KB)

    Common attributes are found in both military and commercial real-time systems. The existence of these common threads suggests that there may be key quantitative system design considerations that undergird large scale, real-time system design. Identifying and quantifying these key aspects early in a program is important in insuring the success of a design. This paper suggests a candidate list of su... View full abstract»

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