Cover Image

A framework for system dependability validation under the influence of intrinsic parameters fluctuation

This paper presents a framework to analyze and evaluate effects of cell failures induced by impact of intrinsic parameters fluctuation (IPF) on system dependability. The method of evaluation is based on generating the actual cell failures model and the realistic conditions of hardware-software inter...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed, Rabah Abood, Samsudin, Khairulmizam, Rokhani, Fakhrul Zaman
Format: Article
Language:English
Published: Science & Engineering Research Support soCiety 2014
Online Access:http://psasir.upm.edu.my/id/eprint/36161/1/A%20framework%20for%20system%20dependability%20validation%20under%20the%20influence%20of%20intrinsic%20parameters%20fluctuation.pdf
http://psasir.upm.edu.my/id/eprint/36161/
http://www.sersc.org/journals/IJSEIA/vol8_no3_2014.php
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.36161
record_format eprints
spelling my.upm.eprints.361612019-06-13T02:32:37Z http://psasir.upm.edu.my/id/eprint/36161/ A framework for system dependability validation under the influence of intrinsic parameters fluctuation Ahmed, Rabah Abood Samsudin, Khairulmizam Rokhani, Fakhrul Zaman This paper presents a framework to analyze and evaluate effects of cell failures induced by impact of intrinsic parameters fluctuation (IPF) on system dependability. The method of evaluation is based on generating the actual cell failures model and the realistic conditions of hardware-software interactions, where the actual error pattern can be captured. The case study of this paper is the impact of cell failures in L1 data cache of a general-purpose microprocessor. The failure modules are generated corresponding to the individual and combined impact of IPF sources in nanometer scale Ultra Thin Body – Silicon on Isolator (UTB-SOI) transistor on 6T-SRAM cell stability. A novel fault injection mechanism has been introduced to propagate errors, through modifying data of cache transactions according to error(s) incurred, dynamically at system-level. By applying a representative system workload using a well-selected suit of real benchmark programs, this study demonstrates that the framework: 1) provides an accurate user visible description for the implications of cell failures at the higher levels of abstraction induced by IPF sources at the lower levels of abstraction, 2) links individual and combined impact of IPF sources with the corresponding implications at system-level which offers a tool to systems designer to involve IPF impacts within the design plan, 3) allows for a detailed simulation process of a system-level environment in the presence of cell failures induced by IPF within an accepted period of time using the look-up file technique and thus offers a foundation to system dependability studies that require vast statistical models, 4) offers high credible evaluation results because the framework is based on the actual error pattern incurred in the system, and 5) improves system reliability where it offers valuable perceptions for an optimal fault tolerance technique in L1 cache with a high failures rate. Science & Engineering Research Support soCiety 2014 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/36161/1/A%20framework%20for%20system%20dependability%20validation%20under%20the%20influence%20of%20intrinsic%20parameters%20fluctuation.pdf Ahmed, Rabah Abood and Samsudin, Khairulmizam and Rokhani, Fakhrul Zaman (2014) A framework for system dependability validation under the influence of intrinsic parameters fluctuation. International Journal of Software Engineering and Its Applications, 8 (3). pp. 233-250. ISSN 1738-9984 http://www.sersc.org/journals/IJSEIA/vol8_no3_2014.php 10.14257/ijseia.2014.8.3.22
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description This paper presents a framework to analyze and evaluate effects of cell failures induced by impact of intrinsic parameters fluctuation (IPF) on system dependability. The method of evaluation is based on generating the actual cell failures model and the realistic conditions of hardware-software interactions, where the actual error pattern can be captured. The case study of this paper is the impact of cell failures in L1 data cache of a general-purpose microprocessor. The failure modules are generated corresponding to the individual and combined impact of IPF sources in nanometer scale Ultra Thin Body – Silicon on Isolator (UTB-SOI) transistor on 6T-SRAM cell stability. A novel fault injection mechanism has been introduced to propagate errors, through modifying data of cache transactions according to error(s) incurred, dynamically at system-level. By applying a representative system workload using a well-selected suit of real benchmark programs, this study demonstrates that the framework: 1) provides an accurate user visible description for the implications of cell failures at the higher levels of abstraction induced by IPF sources at the lower levels of abstraction, 2) links individual and combined impact of IPF sources with the corresponding implications at system-level which offers a tool to systems designer to involve IPF impacts within the design plan, 3) allows for a detailed simulation process of a system-level environment in the presence of cell failures induced by IPF within an accepted period of time using the look-up file technique and thus offers a foundation to system dependability studies that require vast statistical models, 4) offers high credible evaluation results because the framework is based on the actual error pattern incurred in the system, and 5) improves system reliability where it offers valuable perceptions for an optimal fault tolerance technique in L1 cache with a high failures rate.
format Article
author Ahmed, Rabah Abood
Samsudin, Khairulmizam
Rokhani, Fakhrul Zaman
spellingShingle Ahmed, Rabah Abood
Samsudin, Khairulmizam
Rokhani, Fakhrul Zaman
A framework for system dependability validation under the influence of intrinsic parameters fluctuation
author_facet Ahmed, Rabah Abood
Samsudin, Khairulmizam
Rokhani, Fakhrul Zaman
author_sort Ahmed, Rabah Abood
title A framework for system dependability validation under the influence of intrinsic parameters fluctuation
title_short A framework for system dependability validation under the influence of intrinsic parameters fluctuation
title_full A framework for system dependability validation under the influence of intrinsic parameters fluctuation
title_fullStr A framework for system dependability validation under the influence of intrinsic parameters fluctuation
title_full_unstemmed A framework for system dependability validation under the influence of intrinsic parameters fluctuation
title_sort framework for system dependability validation under the influence of intrinsic parameters fluctuation
publisher Science & Engineering Research Support soCiety
publishDate 2014
url http://psasir.upm.edu.my/id/eprint/36161/1/A%20framework%20for%20system%20dependability%20validation%20under%20the%20influence%20of%20intrinsic%20parameters%20fluctuation.pdf
http://psasir.upm.edu.my/id/eprint/36161/
http://www.sersc.org/journals/IJSEIA/vol8_no3_2014.php
_version_ 1643831666832048128
score 13.211869

Similar Items