Fehlertolerierende Rechensysteme

In the last decade of Computer Science development, we can observe a growing interest in fault-tolerant computing. This interest is the result of a rising number of appl'ications where reliable operation of computing systems is an essential requirement. Besides basic research in the field of fault-tolerant computing, there is an increasing num ber of systems especially designed to achieve fault-tolerance. It is the objective of this conference to offer a survey of present research and development activities in these areas. The second GI/NTG/GM~ Conference on Fault-Tolerant Computing Systems has had a preparatory time of about two years. In March 1982, the first GI conference concerning fault-tolerant computing systems was held in Munich. One of the results of the conference was to bring an organiza tional framework to the FTC community in Germany. This led to the founding of the common interest group "Fault-Tolerant Computing Systems" of the Gesellschaft fur Informatik (GI), the Nachrichtentechnische Gesellschaft (NTG), and the Gesellschaft fur MeB- und Regelungstechnik (VDI/VDE-GMR) in November 1982. At that time, it was also decided to schedule a biannual conference on fault-tolerant computing systems. One of the goals of this second conference is to strengthen the relations with the international FTC community; thus, the call for papers was extended not only to German-speaking countries, but to other countries as well.

Contenu
/ Table of Contents.- Verteilte Systeme I / Distributed systems I.- The architecture and the fault-treatment of MuTEAM.- Anwenderwerkzeuge für das fehlertolerante Multimikrocomputersystem FUTURE.- Implementing fault-tolerance in a distributed system architecture.- Extending resilient objects efficiently.- Fehlertolerante Betriebssysteme / Fault-tolerant operating systems.- Ein fehlertolerantes UNIX(TM)Prozeßsystem auf der Basis von Zuverlässigkeitsklassen.- Entwurf und Struktur einer Betriebssystemschicht zur Implementierung von Fehlertoleranz.- The introduction of fault-tolerance in a hierarchical operating system.- Verifikations- und Laufzeitvalidationsmethoden / Verification and run-time validation techniques.- Effiziente Verfahren zur 'online'-Fehlererkennung in Baumstrukturen von Datenbanksystemen.- CADAS: A tool for designing reliable embedded software and supporting testing 'in the large'.- Automatische Verifikation logischer Entwürfe.- Allgemeine Modelle / General models.- Modelling and validating broadcasting-free concurrent systems.- Eine Theorie der Analyse und Konstruktion fehlertolerierender Systeme.- An uniform approach to the Operating System in fault-tolerant distributed computer systems.- Fehlertolerante Hardwarekomponenten / Fault-tolerant hardware components.- Modular design of totally self-checking checkers for 1-out-of-n codes.- Systematic t-error correcting all unidirectional error detecting codes.- Concurrent error-detection /-correction of logical operations.- Zuverlässigkeitsmodelle / Reliability models.- Dependability modelling and evaluation of software and hardware systems.- Eingeladener Vortrag / Invited talk.- Quantitative Bewertung der Zuverlässigkeit von Echtzeitprogrammsystemen.- Issues in reliability modeling offault-tolerant computers.- Einzelfehler tolerierende Kommunikationsnetze.- Verteilte Systeme II / Distributed systems II.- Implementation of a fault-tolerant file management system.- Ein fehlertolerantes lokales Netz mit Schleifenstruktur auf Lichtwellenleiter-Basis.- Synchronization tools and a restart method in the fault-tolerant distributed automation system FIPS.- Diagnose auf Systemebene / Diagnosis at system level.- Distributed self-diagnosis and fault-tolerant communication in parallel multiprocessor networks.- System level fault-diagnosis in distributed systems.- Selbstdiagnoseverfahren auf der Grundlage der mathematischen Logik.- Tests with fault-localizing capabilities improve system level diagnosis.- Protokolle / Protocols.- Bestimmung der Protokoll-Menge für verteilte Fehlermaskierungs-Systeme.- Modeling and verification of a checkpoint-restart-protocol.- Hardware-Testmethoden I / Hardware testing methods I.- VLSI functional testing using critical path traces at a hardware description language level.- Random testing of LSI self-checking circuits.- Functional testing vs. structural testing of RAMs.- Hardware Testmethoden II / Hardware testing methods II.- Compression of multiple-valued data serial streams by means of parallel LFSR signature analyzer.- The detection of small size multiple faults by single fault test sets in programmable logic arrays.