Showing papers on "Reference architecture published in 1983"

An overview of meta-level architecture

Abstract: One of the biggest problems in AT programming is the difficulty of specifying control. Meta-level architecture is a knowledge engineering approach to coping with this difficulty. The key feature of the architecture is a declarative control language that allows one to write partial specifications of program behavior. This flexibility facilitates incremental system development and the integration of disparate architectures like demons, object-oriented programming, and controlled deduction. This paper presents the language, describes an appropriate, and discusses the issues of compiling. It illustrates the architecture with a variety of examples and reports some experience in using the architecture in building expert systems.

Elements of Architecture

Abstract: (1) MR. STATHAM objects to Perrot and Chipiez' work, on primitive Greece being cited for proof of the derivation of the Greek entablature from a wooden origin.

Dynamic activity-creating data-driven computer architecture

Abstract: A computer architecture wherein data inputs causes the dynamic creation of appropriate activities employing stored functions as necessary to accomplish the desired end result for the data. The architecture employs a large scale multi-processing environment for parallel computation. A fast forward propagating queue structure and improved interfacing crossbar are employed.

Developing a long-range information architecture

Abstract: A methodology is presented for eliciting enterprise information requirements and developing a long-range information architecture. The methodology is based on a combination of business system planning, critical success factors, and ends/means analysis. The methodology is independent of organizational structure, personnel, and hardware and software; and it has been successfully implemented in a variety of organizational settings.

System/370 extended architecture: the channel subsystem

Abstract: The 370-XA channel subsystem architecture represents a significant extension of the corresponding System/370 architecture. This paper examines the need for these extensions, discusses the important features and facilities of the new architecture, and provides comparisons with its predecessor, the System/370 channel architecture. It also describes, from an operational viewpoint, how these new concepts affect I/O processing and how they relate to the current trend toward using multiple CPUs, increasing CPU execution speed, and increasing the number of I/O attachments.

Pipe: a high performance VLSI architecture

Abstract: The pipe architecture (parallel instructions and pipelined execution) is proposed as a research vehicle for studying high performance VLSI architectures and organizations. Principal features are: 1) it is pipelined, 2) it is capable of a decoupled mode of operation where two processors cooperate in executing the same task and communicate via hardware queues, 3) it has an instruction cache, and 4) it has a memory interface that allows overlap of memory transactions. This paper describes the proposed architecture and its planned implementation. Included are a discussion of design considerations for a pipelined VLSI architecture, and a description of the particular architecture we have chosen to study. 18 references.

Technologies for network architecture and implementation

Abstract: Systems Network Architecture (SNA) provides a framework or constructing networks of distributed processors and terminals. This paper discusses some of the fundamental properties of network architectures such as SNA, and the evolution of formal descriptive methods that provide precise, complete definitions of the architecture. This has culminated in the development of a programming language, Format and Protocol Language (FAPL), tailored for programming a reference model or meta-implementation of an SNA node. In this form, the architecture specification is itself machine-executable. This property has led to new software technologies that improve quality and productivity in the processes for developing a network architecture and the product implementations derived from it. Automated protocol validation provides the tool necessary to ensure a correct and internally consistent definition of the architecture. This definition can then be used as a standard for testing products to determine compliance with the architecture. Direct implementation of network software by compiling the meta-implementation program is another emerging technology. This paper reviews the current state of work in these areas.

A fault-tolerant system architecture for navy applications

Abstract: This paper describes the architecture of a computer system, being designed and built for the U.S. Navy, that is expected to be the standard Navy shipboard computer for the next twenty years or so. It has a requirement for very high system reliability, which is addressed by a multiprocessor system configuration that can recover dynamically from hardware faults and support on-line repair of failed hardware elements. Successfully accomplishing this requires various types of redundant hardware elements and special system architecture features, as well as intelligent fault-recovery software. This also requires that the application programs be designed to participate fully in the recovery and reconfiguration process. This paper presents the overall system architecture and discusses a number of significant new features designed to support fault-tolerant operation, including a duplex control bus, a computer interconnection system, a technique for remote diagnostics, a single-button maintenance procedure, and special fault-handling software.

Task-oriented architectures

Abstract: Recent advances in system design provide increasing opportunities for rapid experimentation with task-oriented architectures, i.e., architectures designed to perform extremely well for a given application. Problems encountered in one such experiment indicate that, contrary to initial expectations, only a small fraction of the effort is required for hardware development. Most of the effort was devoted to algorithm analysis and restructuring, architecture design, systems programming, software and hardware debugging, and performance analysis. This paper presents a case study in task-oriented architecture, using the Harpy connected speech recognition system as the problem domain. This study highlights the limitations of current methods and presents a number of tools and techniques that are useful for experimentation with task-oriented architectures.

On the verification of computer architectures using an architecture description language

Abstract: In a previous paper [8], we had presented the notion of a family of languages for the multilevel design and description of computer architectures Details of a particular language family, currently under development, was also described One of the constituent members of this family is S

Messages and multiprocessing in the ELXSI system 6400

Abstract: The ELXSI operating system consists of processes which communicate only via messages. Hardware, architecture and software decisions which facilitate and exploit the message approach are described. Multiprocessing, caching and I/O architecture aspects of the minicomputer system are given particular attention. 3 references.

The system architecture of EAS-E: an integrated programming and data base language

Abstract: EAS-E is an application development system based on an entity-attribute-set view of system description. It consists of a procedural language for manipulating data base and main storage entities, and direct (nonprocedural) facilities for interrogating and updating data base entities. The EAS-E software itself was implemented with the entity-attribute-set view. This paper reviews some of the EAS-E features and considers some of its implementation details. This paper is both an introduction to the EAS-E software architecture and an example of the usefulness of the entity-attribute-set view.

Towards the Design and Implementation of Object Oriented Architecture

Abstract: Object oriented programming languages and the computer architecture to support the reliable and efficient execution of programs written in these languages are important issues for providing better programming environment. The main purpose of this paper is to establish the foundation for the design and implementation of object oriented programming languages and object oriented architecture. First, various definitions for object in existing languages and systems are surveyed. Then a new model of object and computation on objects is introduced to establish the foundation. A new object oriented language is used both to rationalize the model and to exemplify how the model is applied to object oriented languages. Finally, issues in the design and implementation of an object oriented architecture which directly reflects this model is described.

Modular architectures for adaptive multichannel lattice algorithms

Abstract: A modular architecture for adaptive multi-channel lattice algorithms is presented. This architecture requires no matrix computations and has a regular structure which significantly simplifies its implementation in comparison with the multichannel (matrix) version of the same algorithms. Because the suggested architecture exhibits a high degree of parallelism and local communication, it is well suited for parallel hardware (VLSI) implementation. The derivation of this modular architecture demonstrates a powerful principle which may become a basic tool for analysis and design of structured processing architectures such as systolic arrays and wavefront array processors.

System/370 extended architecture: A program view of the channel subsystem

Abstract: The 370-XA channel-subsystem architecture represents an evolutionary and significant extension of the System/370 channel architecture. This paper examines the programming-machine interface of the 370-XA channel subsystem and how it was designed to meet the requirements called for by the evolution of IBM's large-scale systems. In particular, emphasis has been placed upon meeting the needs of multiprocessing, maintaining availability, and supporting large I/O configurations while at the same time preserving compatibility for running System/370 channel programs.

Architecture of Distributed Systems

Abstract: Distributed systems are usually very complex In addition to the system part which deals with the application proper, a large part of the system is concerned with the communication between the distributed components, exchanging data over great distances, and controlling the synchronization and consistency of the operations performed at different locations This section deals in particular with this communications aspect of a distributed system

Network Data Management System General Architecture and Implementation Principles

Abstract: The general presentation of the Network Data Management System is provided. The objectives and the application background of NDMS is discussed and the influence of these factors on the NDMS architecture and implementation approach is illustrated. Finally, the distributed transaction processing control and the query processor facilities are presented.

On the design of Always Compatible Instruction Set Architecture(ACISA)

Abstract: This note suggests a concept of a new kind of interrupt called GAP to be used in filling gaps in the Architecture of a computing system.

Systems building in architecture

Abstract: This work is an inquiry into the interventions of the systems design in the whole building process. At the beginning, three approaches which represent different points of view of interventions in production and use are exposed and compared to each other, and one of them serves as the theoretical background of this thesis. It is accepted that interventions in both production and use aspects of the whole building process might be capable of producing valuable solutions, as this notion is determined in the first chapter. Interventions in the production aspect are looked upon as influencing the relations among physical elements and as depending on the process of production which is followed. Here the interest (i.e., producer, designer, client or user), which determines the process of building production, is of importance. The process of production certainly affects the performance of the building product after the building is occupied, and all factors influencing the building performance constitute the use aspect of the whole building process. Changes in the building process produce changes in the use aspect. Systems, which change the building process according to the needs of both the production and use, are considered as intervening in both the production and the use aspect of the whole building process. Finally, traditional, self-evolving methods and principles of building production are looked upon as constituting systems, which are not designed by anybody and serve the needs of both production and use, but substantially differ from the designed building systems. Such differences will be exposed in the last part of my thesis. Thesis Supervisor: Dr. Eric Dluhosch Associate Professor of Building Technology Title:

Processor-per-Domain Guard Architecture

Abstract: The motlvatlon, conception and design of a data filter operating In the security class.lflcatlon domain are described The filter architecture features dlstlnct dcmalns with a separate mlcrOprOcessor In each Isolatlon of the domains 1s accomplished exculslvely by hardware Sharing between the domains 1s con– trolled by trusted software This architecture facilitates verlflcatlon and prov]des flexlblllty, economy, and high throughput A prototgpe of the filter has been Implemented and applled to guarding channels connecting a multicompartmented database to lower level networks The protot~pe ’s operation is fully automatic It uses secret key dlg~tal signatures associated with each database record to authenticate classlflcatlon markings and data A filter security pollcy has been modelled and the prototype design and implementation have been shown Informally to comply. Future directions zn architecture, engineering, application and verification are discussed I20 CH1882-O/83/~/OIN$Ol.M@1983 IEEE

Design issues in parallel architectures for artificial intelligence. Memorandum report

Abstract: Development of highly intelligent computers requires a conceptual foundation that will overcome the limitations of the von Neumann architecture Architectures for such a foundation should meet the following design goals: Address the fundamental organizational issues of large-scale parallelism and sharing in a fully integrated way This means attention to organizational principles, as well as hardware and software Serve as an experimental apparatus for testing large-scale artificial intelligence systems Explore the feasibility of an architecture based on abstractions, which serve as natural computational primitives for parallel processing Such abstractions should be logically independent of their software and hardware host implementations In this paper we lay out some of the fundamental design issues in parallel architecture for Artificial Intelligence, delineate limitations of previous parallel architectures, and outline a new approach that we are pursuing

Software Architecture for the Implementation of a Computer-Aided Engineering System

Abstract: This paper will focus on the implementation of a software architecture and set of related procedures that allow the designer of a design automation tool to easily modify the control of the program and the interface to the tool's user. In addition, this target user can modify the interface as well to provide a personal, more 'friendly' work environment. The procedures to be discussed are a file driven control procedure, procedures called "dialog handlers", and procedures to control graphics displays. Text files used to drive and configure these software modules will also be discussed.