Transient Error Recovery Techniques for Pipelines and Memory Systems
Saleh, Abdallah Medhat
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/69269
Description
Title
Transient Error Recovery Techniques for Pipelines and Memory Systems
Author(s)
Saleh, Abdallah Medhat
Issue Date
1984
Department of Study
Electrical Engineering
Discipline
Electrical Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(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.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
