An architecture for constructing fault- tolerant transputer systems
نویسنده
چکیده
The paper describes the structure of an experimental fault-tolerant transputer architecture (EFTA) based on industry standard transputer modules. The architecture represents one possible implementation of a reliable processing element defined by the Reconfiguration and Fault-Tolerance (RaFT) project. The paper presents an overview of fault protection mechanisms specified within the RaFT project, together with a description of the hardware and software components of the EFTA node. In particular the status interface unit is described. This is used to pass the status information generated by the hardware voting units to a control or application process. Finally, a number of possible network topologies that may be constructed using the EFTA node are given.
منابع مشابه
The RaFT Simulation Environment
This paper describes the RaFT simulation environment, a software tool for use in the development of hardware-based fault-tolerant systems using transputers. The concepts behind the RaFT project are presented, together with an overview of previous work into the design of a fault-tolerant transputer node. The simulation environment described seeks to emulate the hardware techniques and to provide...
متن کاملDesign and Structuring of a Multiprocessor System based on Transputers
In this paper the Authors present the design of a high performance transputer based fault-tolerant multiprocessor system for critical applications such as aircraft control, nuclear power station control, satellite applications etc. Fault-tolerant building blocks designed with potential for real time processing. The systematic architecture, regularity and recursiveness enables the system to be m...
متن کاملEvacuation: A software strategy to support fault-tolerant transputer systems
This paper introduces the concept of process evacuation, a technique for moving processes between processing elements in the presence of faults. The technique forms part of the RaFT support environment, a framework for building fault-tolerant applications on transputers. The paper describes the layered structure of the support environment and how process evacuation fits into this structure. Fin...
متن کاملFault-Tolerant Dynamic Task Scheduling Based on Dataflow Graphs
This paper describes a distributed algorithm for scheduling parallel programs represented by (macro-) dataflow graphs on multicomputer systems such that they are executed in a fault-tolerant way. Fault tolerance is based on dynamic redundancy comprising checkpointing, self-diagnosis and rollback recovery. The schedule is computed dynamically during the runtime of the process system. It works in...
متن کاملConsul: a communication substrate for fault-tolerant distributed programs
Replicating important services on multiple processors in a distributed architecture is a common technique for constructing dependable computing systems. This paper describes a communication substrate, called Consul, that facilitates the development of such systems by providing a collection of fundamental abstractions for constructing fault-tolerant programs based on replicated processing. These...
متن کامل