Towards understanding the effects of intermittent hardware faults on programs

Rashid, Layali; Pattabiraman, Karthik; Gopalakrishnan, Sathish

doi:10.1109/dsnw.2010.5542613

Cited by 16 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The faults induced by IES are typically partitioned as PFs, Ifs, and transient faults (TFs) according to their durations. Since TFs cannot be traced to a defect in a particular part of the system and, normally, their adverse effects disappear rapidly, [11][12][13] they are ignored in this paper, and TFs diagnosis can be found in Ref. 14 .…”

Section: Reference Stress Events Divisionmentioning

confidence: 99%

Environmental stress level evaluation approach based on physical model and interval grey association degree

Deng

Qiu

Liu

et al. 2013

Chinese Journal of Aeronautics

View full text Add to dashboard Cite

Associating environmental stresses (ESs) with built-in test (BIT) output is an important means to help diagnose intermittent faults (IFs). Aiming at low efficiency in association of traditional time stress measurement device (TSMD), an association model is built. Thereafter, a novel approach is given to evaluate the integrated environmental stress (IES) level. Firstly, the selection principle and approach of main environmental stresses (MESs) and key characteristic parameters (KCPs) are presented based on fault mode, mechanism, and ESs analysis (FMMEA). Secondly, reference stress events (RSEs) are constructed by dividing IES into three stress levels according to its impact on faults; and then the association model between integrated environmental stress event (IESE) and BIT output is built. Thirdly, an interval grey association approach to evaluate IES level is proposed due to the interval number of IES value. Consequently, the association output can be obtained as well. Finally, a case study is presented to demonstrate the proposed approach. Results show the proposed model and approach are effective and feasible. This approach can be used to guide ESs measure, record, and association. It is well suited for on-line assistant diagnosis of faults, especially IFs.

show abstract

Section: Reference Stress Events Divisionmentioning

confidence: 99%

Environmental stress level evaluation approach based on physical model and interval grey association degree

Deng

Qiu

Liu

et al. 2013

Chinese Journal of Aeronautics

View full text Add to dashboard Cite

show abstract

“…These errors can damage the correct software execution by producing erroneous results if the computation is completed, or by preventing the execution of the application by causing exceptions, interrupts, abnormal terminations or applications hang-up. Nevertheless, the software stack can also play an important role in masking errors, introducing a further error masking effect (Software Vulnerability Factor -SVF), which may further improve the system reliability [39][40][41][42][43][44][45][46].…”

Section: A Cross-layer Approach For System Reliability Evaluationmentioning

confidence: 99%

Cross-layer reliability evaluation, moving from the hardware architecture to the system level: A CLERECO EU project overview

Vallero

Tselonis

Foutris

et al. 2015

Microprocessors and Microsystems

View full text Add to dashboard Cite

International audienceAdvanced computing systems realized in forthcoming technologies hold the promise of a significant increase of computational capabilities. However, the same path that is leading technologies toward these remarkable achievements is also making electronic devices increasingly unreliable. Developing new methods to evaluate the reliability of these systems in an early design stage has the potential to save costs, produce optimized designs and have a positive impact on the product time-to-market

show abstract

“…An intermittent fault occurs repeatedly at the same location, it tends to occur in bursts for a period of time when the fault is activated while replacement of the offending circuit removes the intermittent fault [6], [28]. It has been suggested that intermittent faults have the potential to impact program execution to a greater extent when compared with transient faults [19]. Moreover, it is hard to diagnose by post facto using hardware/software tests because intermittent faults do not persist and the conditions that caused the fault are hard to regenerate.…”

Section: Intermittent Faultsmentioning

confidence: 99%

“…Layali Rashid [19] injected intermittent faults in software level to understand their affects on the software. However, they made their experiments only on two applications (matrix multiply and insertion sort).…”

Section: Related Workmentioning

confidence: 99%

FIMSIM: A fault injection infrastructure for microarchitectural simulators

Yalcin

Unsal

Cristal

et al. 2011

2011 IEEE 29th International Conference on Computer Design (ICCD)

View full text Add to dashboard Cite

Abstract-Fault injection is a widely used approach for experiment-based dependability evaluation in which faults can be injected to the hardware, to the simulator or to the software. Simulation based fault injection is more appealing for researchers, since it can be utilized at the early design stage of the processor. As such, it enables a preliminary analysis of the correlation between the criticality of circuit level faults and their impact on applications. However, the lack of publicly available fault injectors for microarchitecture level simulators brings extra burden of designing and implementing fault injectors to the researchers who evaluate microarchitecture dependability. In this study, we present FIMSIM, to the best of our knowledge, the first publicly available fault injection simulator at the microarchitecture level. FIMSIM is a compact tool which is capable of injecting transient, permanent, intermittent and multi-bit faults. Therefore, FIMSIM provides the opportunity to comprehensively evaluate the vulnerability of different microarchitectural structures against different fault models.

show abstract

Towards understanding the effects of intermittent hardware faults on programs

Abstract: Abstract

Cited by 16 publications

References 20 publications

Environmental stress level evaluation approach based on physical model and interval grey association degree

Environmental stress level evaluation approach based on physical model and interval grey association degree

Cross-layer reliability evaluation, moving from the hardware architecture to the system level: A CLERECO EU project overview

FIMSIM: A fault injection infrastructure for microarchitectural simulators

Contact Info

Product

Resources

About