The goal of this project Is to plan and develop a computing system that will provide interactive computing services with a high degree of reliability, a variety of language systems, incremental expansion capability, competitive costs, a respect for human factors considerations; and the project will require only a modest amount of system programming resources.
The Distributed Computer System (DCS) is a distributed timesharing system developed at the University of California Irvine. The system consists of multiple minicomputers coupled by a ring communications system. The present system has been used as a vehicle for research and development of distributed computer systems, and to support a limited amount of class programming.
The design objectives of the system are coherence, high availability through failsoft behavior, and low cost. Enhanced system availability is achieved through the distribution of hardware, software, and control. The distribution discipline of DCS also makes changes in system configuration natural. The failure of a redundant hardware or software network component is isolated; the remaining components continue to function. Mechanisms for the detection and the restart of the failed components allow the construction of fault tolerant services This paper describes the message functions and techniques that are used in the DCS and points out some possible evolutionary trends in message based distributed systems.
HOUGH has proposed a procedure for detecting lines in pictures. DUDA-HART extended the method for a more general curve fitting. This paper shows how this method can be used to detect any given curve. The procedure presented here can be easily implemented and is more efficient in a parallel machine.
This paper describes the design parameters and the approaches used in the construction of a Network Access Arrangement (NAA). The NAA connects a network node (host) to the communications medium. The details of the design and implementation are presented, along with some rationale for the design choices. The design is biased towards implementation in Large Scale Integration (LSI) , and allows variation in message format and transmission protocol.
This freedom is explored in regard to building both ring networks, such as the Distributed Computer System (DCS) [1], and contention nets, such as Ethernet [2]. The NAA will initially be used to implement access to a ring network, similar to the DCS at the University of California, Irvine. This application is examined in detail.
Cookie SettingseScholarship uses cookies to ensure you have the best experience on our website. You can manage which cookies you want us to use.Our Privacy Statement includes more details on the cookies we use and how we protect your privacy.