Software implemented fault-tolernace on distributed-memory MIMD architectures /

architecture for a software-implemented fault-tolerance

Bibliographic Details
Main Author: Holland, Gavin D. (Gavin Douglas)
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1995.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:architecture for a software-implemented fault-tolerance
cause the computations to fail. This thesis presents a novel
computing systems. The objective of this research is to
coverage measurements of a minimal implementation of the
develop the conceptual framework for a purely software-based,
distributed computations performed on these systems. As the
distributed, multi-tiered layer envelopes user applications,
efficient and effective.
enables dynamic run-time selection of the most appropriate
enabling it to perform fault-tolerance related actions apart
fault-tolerant algorithm, and is, therefore, not restricted
from, and transparent to the application. Its modular design
grows, so does the probability that a hardware failure will
Large multicomputer systems are inherently unreliable because
layer, designed for the purpose of enhancing the reliability
of distributed computations performed on large multicomputer
of their enormous complexity. This has a direct impact on
proposed layer are presented, and indicate that user-level
recovery in a parallel environment. The symmetrically
size and execution time of these distributed computations
software-implemented fault-tolerance can be reasonably
systems, such as massively parallel computers and distributed
to one particular fault-tolerant method. Performance and
user-level solution for fault detection, reconfiguration, and
Item Description:"Major subject: Computer Science".
Vita.
Physical Description:viii, 69 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references.