Files in this item

FilesDescriptionFormat

application/pdf

application/pdf8409830.pdf (3MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Transient Error Recovery Techniques for Pipelines and Memory Systems
Author(s):Saleh, Abdallah Medhat
Department / Program:Electrical Engineering
Discipline:Electrical Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Engineering, Electronics and Electrical
Abstract:This thesis presents fundamental results related to the problem of system recovery from transient errors. Scrubbing methods are suggested for memory systems and retry techniques are discussed for pipelines. A probabilistic model for the activity of faulty periods is introduced, and a fault analysis is carried out to decide the optimum length of the retry period, T. Distribution functions are derived to represent the case of false alert, where a transient fault is flagged as permanent, and the case of a miss, where too many errors coexist, thus overcoming the checker's capability to detect them. These derivations are compared with the results of a simulation program representing the model used.
Different retry techniques are devised to recover from transient errors in pipelined systems. The criteria for these techniques are the speed of recovery, the reliability, and the amount of extra hardware required for their implementation. Error-detecting checkers are used between the different segments of the pipe. An optimum distribution of checkers between the segments is obtained, along with an analysis of the checkers' effectiveness in detecting transient errors.
For transient error recovery in memory systems, two scrubbing techniques are analyzed. These techniques are based on single-error correction and double-error detection (SEC-DED) codes. One technique has an exponentially distributed scrubbing interval and the other has a deterministic scrubbing interval. The results of this analysis are compared to results obtained for memory systems without scrubbing and for memory systems without redundancies. Reliability plots and mean time to failure (MTTF) equations are obtained to justify the need for redundancies and scrubbing techniques.
Issue Date:1984
Type:Text
Description:130 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1984.
URI:http://hdl.handle.net/2142/69269
Other Identifier(s):(UMI)AAI8409830
Date Available in IDEALS:2014-12-15
Date Deposited:1984


This item appears in the following Collection(s)

Item Statistics