scispace - formally typeset
Search or ask a question

Showing papers on "Heterogeneous network published in 1992"


Journal ArticleDOI
TL;DR: Experiences with and enhancements to PVM (Parallel Virtual Machine), a software package that allows the utilization of a heterogeneous network of parallel and serial computers as a single computational resource, are described.
Abstract: Concurrent computing environments based on loosely coupled networks have proven effective as resources for multiprocessing. Experiences with and enhancements to PVM (Parallel Virtual Machine) are described in this paper. PVM is a software package that allows the utilization of a heterogeneous network of parallel and serial computers as a single computational resource. This report also describes an interactive graphical interface to PVM, and porting and performance results from production applications. 23 refs., 5 figs., 5 tabs.

274 citations


Patent
30 Jan 1992
TL;DR: In this paper, a heterogeneous configuration management tool (17) enables building of a software system in a heterogenous network of computers (13, 15) of which a reference to a version indicator (25) is passed to the foreign computer (13) to provide an indication of user-specified version of the component being translated by the foreign Computer (13).
Abstract: A heterogeneous configuration management tool (17) enables building of a software system in a heterogeneous network (11) of computers (13, 15). In building a desired software system, the tool (17) enables at least one component of the system to be translated by a foreign computer (13) of the network (11) and other components of the system to be translated by other computers (15) of the network (11). A reference to a version indicator (25) is passed to the foreign computer (13) to provide the foreign computer (13) an indication of user-specified version of the component being translated by the foreign computer (13). The reference is expanded during processing on the foreign computer (13). Pathname transformation files (21) are employed to provide transformation of a pathname in one computer of the network (11) to a corresponding pathname in another computer of a network (11). Binaries (30) resulting from component translations are stored in split pools (35). In turn, split releases of the built software system are enabled.

224 citations


Journal ArticleDOI
TL;DR: An explanation of the widely different technological approaches and technologies being proposed for different interpretations of wireless personal communications services (PCS) is presented.
Abstract: An explanation of the widely different technological approaches and technologies being proposed for different interpretations of wireless personal communications services (PCS) is presented. Different wireless communications applications and issues surrounding the applications are discussed. Descriptions of the compromises that have been made in developing specific technologies optimized to serve the cordless telephone and the vehicular mobile radio applications are presented. Characteristics of a technology that is aimed at the widespread pedestrian PCS application and environment are outlined. Different wireless technologies that have been aimed at different applications and environments are compared. >

202 citations


Book
02 Jan 1992
TL;DR: The DARPA experimental internet system consisting of satellite, terrestrial, radio, and local networks, all interconnected through a system of gateways and a set of common protocols, supports an architecture consisting of multiple packet switched networks interconnected by gateways.
Abstract: THE MILITARY requirement for computer communications between heterogeneous computers on heterogeneous networks has driven the development of a standard suite of protocols to permit such communications to take place in a robust and flexible manner. These protocols support an architecture consisting of multiple packet switched networks interconnected by gateways. The DARPA experimental internet system consists of satellite, terrestrial, radio, and local networks, all interconnected through a system of gateways and a set of common protocols.

116 citations


Journal ArticleDOI
TL;DR: The results of an analysis of switch performance as measured by capacity and the distribution of functionality are presented and several open issues regarding the capability of the CPS to deliver telephone service to wireless terminals, including privacy and security issues are discussed.
Abstract: Existing wireless network architectures and the increasing demand for cellular services are reviewed. Wireless network control tasks and the structure of a cellular packet switch (CPS) based on an optical fiber metropolitan area network (MAN) are described. Protocols for moving information through the MAN focusing on handoff, a crucial function of wireless networks, are discussed. The results of an analysis of switch performance as measured by capacity and the distribution of functionality are presented. Several open issues regarding the capability of the CPS to deliver telephone service to wireless terminals, including privacy and security issues, are discussed. >

68 citations


Proceedings ArticleDOI
26 Apr 1992
TL;DR: The purpose and use of the HeNCE software is described, which provides a graphical interface for creating, compiling, executing, and debugging parallel programs, as well as configuring a distributed virtual computer (using PVM).
Abstract: HeNCE (heterogeneous network computing environment) is an X Window based graphical parallel programming environment that was created to assist scientists and engineers with the development of parallel programs. HeNCE provides a graphical interface for creating, compiling, executing, and debugging parallel programs, as well as configuring a distributed virtual computer (using PVM). HeNCE programs can be run on a single Unix workstation or over a network of heterogeneous machines. The paper describes the purpose and use of the HeNCE software. >

45 citations


Proceedings ArticleDOI
14 Jun 1992
TL;DR: In this article, the authors propose an alternative approach, in which the source encodes its signal hierarchically, and the network delivers subsets of the signal layers in accordance with individual destinations' bandwidth constraints.
Abstract: Multicast of real-time data in a heterogeneous network environment, in which links and recipients differ in their bandwidth, is considered. Traditional schemes are designed to deliver the source's complete data to all recipients, thereby restricting the source's handling of heterogeneity to either overcompressing to the bandwidth accessible by the least capable user, or excluding those destinations which cannot receive the full signal. The author presents an alternative approach, in which the source encodes its signal hierarchically, and the network delivers subsets of the signal layers in accordance with individual destinations' bandwidth constraints. This approach allows each user to trade off reception bandwidth for signal quality independently of other users' selections. In support of such a service, efficient routes that carry the desired bandwidth to all destinations must be computed. Routing algorithms that compute such paths are presented, and their merits are compared. >

36 citations


Book
03 Jan 1992
TL;DR: In this paper, the evolution of routing mechanisms in IBM's Systems Network Architecture (SNA) since its inception in 1974 to the present is discussed, and possible evolutionary paths that may be taken in the future to address the problems of large heterogeneous networks.
Abstract: This paper reviews the evolution of routing mechanisms in IBM's Systems Network Architecture (SNA) since its inception in 1974 to the present. Routing mechanisms are related to changes in the application and communications environment. Also discussed are possible evolutionary paths that may be taken in the future to address the problems of large heterogeneous networks.

21 citations


Proceedings ArticleDOI
01 Dec 1992
TL;DR: Results on sheer performance, price performance, and toolkit-based parallelization by monitoring the same computations on a CRAY Y-MP and making detailed comparisons show the excellent price-performance ratios given by the heterogeneous computing environment.
Abstract: The authors present the results of an experiment on massively parallel stochastic simulation of polymer chains for measuring scale-invariant phenomena at critical temperatures. The parallelization is achieved through the EcliPSe toolkit and conducted on a flexible, tree-structured virtual machine made up of arbitrary and heterogeneous computing nodes dispersed across the country. These nodes cooperate to perform the simulation and pool results together in real time at a central node which initiates the parallel simulation. The advantage of the tree-structure is that it allows for a fault-resilient, flexible environment for long-running parallel simulations. The authors present results on sheer performance, price performance, and toolkit-based parallelization by monitoring the same computations on a CRAY Y-MP and making detailed comparisons. Most significant are the excellent price-performance ratios given by the heterogeneous computing environment. >

17 citations


Patent
31 Mar 1992
TL;DR: In this article, the authors describe a communication network consisting of at least two general purpose computers, each of which has a processor, a memory, and an input/output bus.
Abstract: The present inventions pertains to a communication network. The communication network comprises an ATM network. The communication network also comprises at least two general purpose computers. Each computer has a processor, a memory in communication with the processor, and an input/output bus in communication with the processor, memory and the ATM network. The N computers communicate with each other through the ATM network and operate instructions for applications other than communications between the other computers.

17 citations


01 Feb 1992
TL;DR: The installation and use of the HeNCE software is described, which provides an easy to use interface for creating, compiling, executing, and debugging parallel programs.
Abstract: HeNCE, Heterogeneous Network Computing Environment, is a graphical parallel programming environment. HeNCE provides an easy to use interface for creating, compiling, executing, and debugging parallel programs. HeNCE programs can be run on a single Unix workstation or over a network of heterogeneous machines, possibly including supercomputers. This report describes the installation and use of the HeNCE software.

Journal ArticleDOI
TL;DR: The key software technology underlying Hetero Helix is the use of a ‘compiler’ which analyzes the date structures in shared memory and automatically generates code which translated data representations from the format native to each machine into a format understood by all machines, and vice versa.

Proceedings ArticleDOI
01 Jul 1992
TL;DR: The proposed system for the Madigan Army Medical Center was modeled in detail, as part of the Medical Diagnostic Imaging Support System (MDIS) proposal, and issues addressed with the models, the modeling techniques used and the performance results from the simulations are described.
Abstract: Siemens and Loral Western Development Labs have designed a Picture Archiving and Communication System capable of supporting a large, fully digital hospital. Its functions include the management, storage and retrieval of medical images. The system may be modeled as a heterogeneous network of processing elements, transfer devices and storage units. Several discrete event simulation models have been designed to investigate different levels of the design. These models include the System Model, focusing on the flow of image traffic throughout the system, the Workstation Models, focusing on the internal processing in the different types of workstations, and the Communication Network Model, focusing on the control communication and host computer processing. The first two of these models are addressed here, with reference being made to a separate paper regarding the Communication Network Model. This paper describes some of the issues addressed with the models, the modeling techniques used and the performance results from the simulations. Important parameters of interest include: time to retrieve images from different possible storage locations and the utilization levels of the transfer devices and other key hardware components. To understand system performance under fully loaded conditions, the proposed system for the Madigan Army Medical Center was modeled in detail, as part of the Medical Diagnostic Imaging Support System (MDIS) proposal.

Proceedings ArticleDOI
06 Dec 1992
TL;DR: The architecture and functionalities of a system that permit updating management information, represented by managed objects within the management information base (MIB), are presented and a prototype integrator has been developed.
Abstract: The architecture and functionalities of a system that permit updating management information, represented by managed objects within the management information base (MIB), are presented. These managed objects are an abstract representation of the managed resources of the network. The system interacts with the heterogeneous underlaying networks through a module called the integrator. Its role is to hide the complexity and the heterogeneity of access to the heterogeneous underlaying resources. A prototype integrator has been developed. >

Journal ArticleDOI
TL;DR: The state of the art in heterogeneous network computing is surveyed, beginning with a description of representative systems and applications, and the most pressing needs as well as the foreseeable obstacles are identified.

Journal ArticleDOI
A. Wolisz1, Radu Popescu-Zeletin1
TL;DR: A novel, top down modelling approach is developed, for which a proper protocol stack assuring reliable end-to-end communication between application processes residing in space labs and ground-based application processes has to be chosen, which represents any type of subnetwork by a specific set of networl quality of service characteristics.

Proceedings ArticleDOI
02 Feb 1992
TL;DR: In the 1980s, personal computers and personal entertainment such as UCRS, Camcorders, Walkman, have revolutionized the way people relate to business information and entertainment.
Abstract: In the 1980s, personal computers and personal entertainment such as UCRS, Camcorders, Walkman, have revolutionized the way people relate to business information and entertainment. With cellular and cordless telephones in the vanguard, the 1990s will initiate an era of personal communications. Early systems owe their character to the means of radio transmission. There is a growing appreciation that the fixed infrastructure will play a critical role determining costs and capabilities. Optical communications systems will be key infrastructure components of wireless personal communication networks of the future.

Proceedings ArticleDOI
Nakanishi1, Rego1, Sunderam
16 Nov 1992
TL;DR: In this article, the authors present the results of an experiment on massively parallel stochastic simulation of polymer chains for measuring scale-invariant phenomena at critical temperatures, achieved through the EcliPSe toolkit and conducted on a flexible, tree-structured virtual machine.
Abstract: The authors present the results of an experiment on massively parallel stochastic simulation of polymer chains for measuring scale-invariant phenomena at critical temperatures. The parallelization is achieved through the EcliPSe toolkit and conducted on a flexible, tree-structured virtual machine made up of arbitrary and heterogeneous computing nodes dispersed across the country. These nodes cooperate to perform the simulation and pool results together in real time at a central node which initiates the parallel simulation. The advantage of the tree-structure is that it allows for a fault-resilient, flexible environment for long-running parallel simulations. The authors present results on sheer performance, price performance, and toolkit-based parallelization by monitoring the same computations on a CRAY Y-MP and making detailed comparisons. Most significant are the excellent price-performance ratios given by the heterogeneous computing environment.

Journal ArticleDOI
TL;DR: The chief advantage of a LAN is that it permits computer resources and data to be shared among users while retaining the bcncfits of personal computing-a situation that managcmcnts have long tried to foster.

Journal ArticleDOI
TL;DR: A performance methodology for estimating user perceived delay and buffer overflow in heterogeneous data networks is developed based on well-known two-moment approximation schemes and is applied to several LAN-MAN andLAN-WAN network examples.
Abstract: A heterogeneous data network consists of Local Area Networks (LANs) interconnected with either leased lines, packet-switched networks, Metropolitan Area Networks (MANs), or combinations thereof. Heterogeneous networks are characterized by bursty traffic, nested segmentation and reassembly of packets, window flow control and round-robin channel access. We develop a performance methodology for estimating user perceived delay and buffer overflow in heterogeneous data networks. The methodology is based on well-known two-moment approximation schemes. Modifications of these schemes are proposed in order to model the bandwidth allocation policies of the MANs and to capture the burstiness of the traffic. The methodology is applied to several LAN-MAN and LAN-MAN-WAN network examples.

Journal ArticleDOI
TL;DR: A general purpose method and a set of algorithms are presented for correctly decomposing multilingual update requests on a network of distributed heterogeneous databases.
Abstract: New problems of updating views involving inter-entity relationships or joins are identified, beyond those reported previously in the literature. A general purpose method and a set of algorithms are presented for correctly decomposing multilingual update requests on a network of distributed heterogeneous databases. The method and algorithm also apply to both homogeneous nondistributed and distributed database environments. The method, called prototype views and update rules, applies to individual relationships in an entity relationship (ER) view of the network database and gives a floorplan for update decomposition. The network database view represents a unified conceptual view of all the individual databases in the heterogeneous network (i.e. of the objects shared across the network). The update request is decomposed into a sequence of intermediate control language steps to subsequently guide the particular updates to each of the underlying databases in the network. Individual database updates are performed by each particular database management system (DBMS). >

Journal ArticleDOI
03 Aug 1992
TL;DR: The transformation of a finite-element program into a distributed application, allowing its users to handle the remote computational power available on a heterogeneous network of computers, is presented and it is shown that one can improve the performances of such an application by use of distributed computing.
Abstract: The transformation of a finite-element program into a distributed application, allowing its users to handle the remote computational power available on a heterogeneous network of computers, is presented. Tools are designed to facilitate the client/server decomposition and implementation for a finite-element package like FLUX3D, and it is shown that one can improve the performances of such an application by use of distributed computing. Many difficulties are discussed, such as the localization of resources, the replicated database management, the cost of network communications, and parallel distributed computing. The model in which a single remote server running on a powerful host is used to perform coarse grained computations seems to give the best performances. Because of communication times, parallel distributed computing is less efficient. Moreover, it requires a real programming effort (leading to little transparency) when being implemented in a steady-state finite-element package. >

Book
01 Jan 1992
TL;DR: The present work presents an Object-Oriented Architecture for Distributed Systems that supports Dynamic Configuration of Distributed, Mixed-Language Applications and an ISO/OSI Based Approach for Modeling Heterogeneous Networks.
Abstract: Open Distributed Systems. An Object-Oriented Architecture for Distributed Systems (R.M. Soley). Trader Interaction Models and Infrastructure Implications (K. Geihs). An Architecture Supporting Dynamic Configuration of Distributed, Mixed-Language Applications (J. Becher). Implementation of Access Control in an X.500 Environment (X. Zhang et al.). High Speed Networking. . Myths about Congestion Management in High Speed Networks (R. Jain). Distributed Multimedia Applications and Wireless and High-Speed Networking in MultiG (B. Pehrson). ISDN and B-ISDN: From Basic Technology to Applications (A.T. Kundig). High Speed Protocols: State of the Art in Multimedia Applications (W. Tawbi et al.). Some Aspects of the Adaption of Services to an ATM Network (A.J. Casaca, M.S. Nunes). Protocol Engineering. A Protocol Development Environment Based on Estelle (R. Fodisch et al.). Performance Characteristics of Portable ISO/OSI Protocol Implementations (M. Lahti, J. Malka). Test Case Generation for Transport Protocols (S.V. Raghavan et al.). Advanced Software Technology for Protocol Engineering (G. Csopaki). Object-Oriented Implementation of Telecommunication Software Using the OTSO Environment (J. Koivisto et al.). Simulation Support for the OTSO Environment (J. Harju et al.). Communications Systems Technology. Current Trends in Mobile Communication (H. Ahava). Computer Networking in the Baltic States and in the Soviet Union (A. Work). Networking Applications. Library Networking in the Finnish Academic Libraries (J. Hakala). NORDUNET, University Network in the Nordic Countries (L. Backstrom). Distribution Networks in the Travel Industry (H. Alvgren). A Redefinition of the Telecommunications Enterprise (H. Palsson). TeleGuide: A New Electronic Marketing and Distribution Channel in Sweden (V. Gjerstad). TELMO: Open Telematic Services Network in Finland (R. Nevalainen). Techniques for Distributed Systems. A Graphical User Interface for a Value Added Network (M. Hallivuori et al.). Migration, Caching and Replication in Distributed Object-Oriented Systems: An Integrated Framework (A. Schill). A Tutorial on Intelligent and Integrated Management of an Electronic Messaging Network (R. Ananthanpillai). Providing Low Cost Read Access to Replicated Data with Multi-Level Voting (B. Freisleben et al.). An ISO/OSI Based Approach for Modeling Heterogeneous Networks (B. Schott et al.). Analysis of Network Protocols. Sensitivity Analysis of the Load on an Ethernet Network (J. van Oorschot, A. Dekkers). Optimisation of Transport Protocols for High-Speed (T. Wahl, M. Salmony). Protocol Architectures and Migration Strategies: Concepts, Example and Implementation (E. Mannie, B. Sales). FDDI Performance: Measurements and Experiences of the FDDI Network at Technical University Aachen (P. Davids et al.). Networking Strategies. Security Arrangements in a Large Banking Network (K. Oksanen). Information Security in Open Systems (A. Karila).

Proceedings ArticleDOI
01 Jul 1992
TL;DR: The detailed description of the Communication Network model which is one of three models used for the Medical Diagnostic Imaging Support System (MDIS) design analysis will be presented and future issues in the modeling of MDIS and other large heterogeneous networks of computers and workstations are concluded.
Abstract: Due to the expense and time required to configure and evaluate large scale PACS rapid modeling and simulation of system configurations is critical. The results of the analysis can be used to drive the design of both hardware and software. System designers can use the models to help them during the actual system integration. This paper will show how the LANNET 11. 5 and NE1''WORK 11. 5 modeling tools can be used hierarchically to model and simulate large PACS. The detailed description of the Communication Network model which is one of three models used for the Medical Diagnostic Imaging Support System (MDIS) design analysis will be presented. The paper will conclude with future issues in the modeling of MDIS and other large heterogeneous networks of computers and workstations. The way that the models might be used throughout the system life cycle to reduce the operation and maintenance costs of the system is explained.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Journal ArticleDOI
TL;DR: The object-oriented conception and language is used to permit the use of dynamic control of each protocol and the evaluation of the evolution of the QOS for the interworking units for the administration aspect of a heterogeneous network.
Abstract: This paper describes the implementation of a functional simulator for the interconnection of heterogeneous high-speed data networks. After trying several approaches, we use the object-oriented conception and language to permit the use of dynamic control of each protocol (FDDI, DQDB, ATM). We studied the most interesting QOS parameters for our context. For the administration aspect of a heterogeneous network, the simulator permits the evaluation of the evolution of the QOS for the interworking units.

Proceedings ArticleDOI
09 Aug 1992
TL;DR: The comparison shows that the heterogeneous network has the unique feature of very fast early stage learning and converges much faster for a suitable range of the slope of the learning activation function.
Abstract: A three-layer heterogeneous network consisting of linear output layer units and sigmoid hidden layer units is considered. Compared with a conventional homogeneous network of all sigmoid units, this network can be implemented much more economically, and for analog mapping this network is more suitable. The minimal hidden size needed for convergence in a three-layer heterogeneous network for a given task is derived and a performance comparison between the two types of networks in terms of convergence behavior and generalization ability is also presented. The comparison shows that the heterogeneous network has the unique feature of very fast early stage learning and converges much faster for a suitable range of the slope of the learning activation function. Both have comparable generalization abilities. >

Journal ArticleDOI
TL;DR: The requirements for subsystems are stated and DESys is implemented under Microsoft-Windows on IBM-compatible PCs and can be used as a comprehensive tool to build up efficient and robust distributed FMS in a transparent way.

DOI
01 Sep 1992
TL;DR: This talk will review the status of existing tools to address management for networks and draws on experience from both within and outside the HEP community.
Abstract: It has been said that the ``network is the system``. This implies providing levels of service, reliability, predictability and availability that are commensurate with or better than those that individual computers provide today. To provide this requires integrated network management for interconnected networks of heterogeneous devices covering both the local campus and across the world and spanning many administrative domains. This talk will review the status of existing tools to address management for networks. It draws on experience from both within and outside the HEP community.

Proceedings ArticleDOI
11 Nov 1992
TL;DR: The strategies in developing heterogeneous networks to support computer communications through connectionless services and telecommunications through connection oriented (CO) services are proposed and a performance evaluation of the interworking unit (IWU) is presented.
Abstract: The evolution of broadband networks through heterogeneous networking among the set of broadband networks that are being developed, i.e., broadband ISDN, (B-ISDN), fiber distributed data interface (FDDI) LAN, MAN, and distributed queue dual bus (DQDB), is considered. The evolution scenario based on business customer needs is stressed. The interworking requirements are outlined, and the strategies in developing heterogeneous networks to support computer communications through connectionless services and telecommunications through connection oriented (CO) services are proposed. A performance evaluation of the interworking unit (IWU) is presented. The delay characteristics of CO and connectionless (CL) services are presented. >