Access Restriction

Author Saha, Goutam Kumar
Source ACM Digital Library
Content type Text
Publisher Association for Computing Machinery (ACM)
File Format PDF
Language English
Subject Keyword Fault tolerance ♦ Burst errors ♦ Multiple byte-errors ♦ Single-version software
Abstract This paper describes how to design a software-based fault tolerant application using microprocessor (MP), in order to tolerate the burst errors in memory. This approach may be called a single -- version scheme (SVS). The SVS relies on a single version application program which is enhanced with self-checking code redundancy to tolerate memory burst errors that are difficult to correct during the run-time of an application. Conventionally, the other software based approaches can detect a few bit errors (in memory) only towards fail-stop kind of fault tolerance against transient bit errors. Reed Solomon codes are mainly effective for burst errors in coding of audio Compact Disks at offline only. The proposed online technique does not need multiple versions of software and multiple machines. This approach employs only two copies of the application software running on one machine only. Two copies of the enhanced version version of an application are used here for online error detection and tolerance thereof as well. This is an effective low-cost online tool for hardening a microprocessor-based industrial computing system or for on-chip DRAM applications using an affordable code and time redundancy against the burst errors in processor memory. The SVS aims to provide a non-fail-stop kind of fault tolerance against burst errors. This approach supplements the Error Correcting Codes (ECC) in memory system also, against both the transient and permanent bit errors in memory.
Description Affiliation: Kolkata, India (Saha, Goutam Kumar)
Age Range 18 to 22 years ♦ above 22 year
Educational Use Research
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2015-06-29
Publisher Place New York
Journal Ubiquity (UBIQ)
Volume Number 2005
Issue Number November
Page Count 1
Starting Page 1
Ending Page 1

Open content in new tab

   Open content in new tab
Source: ACM Digital Library