WearMon: Reliability monitoring using adaptive critical path testing

Zandian, Bardia; Dweik, Waleed; Kang, Suk Hun; Punihaole, Thomas; Annavaram, Murali

doi:10.1109/dsn.2010.5544916

Cited by 9 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first requirement can be accommodated by our BLINC algorithm: as shown in the previous section, it can provide emergency routes with minimal overhead. The latter requirement has been solved in the context of microprocessor designs [19,23] but, to date, no solution of this kind has been developed for NoCs. Because of BLINC's fast and localized reconfiguration, it is possible to select each link in turn, take it offline, test it in a harsh operating environment to mimic circuit aging (such as lowered supply voltage [19]), and then bring it back online.…”

Section: B Uninterrupted Availability With Blincmentioning

confidence: 99%

See 1 more Smart Citation

Brisk and limited-impact NoC routing reconfiguration

Lee

Parikh

Bertacco

2014

Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE), 2014

View full text Add to dashboard Cite

Abstract-The expected low reliability of the silicon substrate at upcoming technology nodes presents a key challenge for digital system designers. Networks-on-chip (NoCs) are especially concerning because they are often the only communication infrastructure for the chips in which they are deployed. Recently, routing reconfiguration solutions have been proposed to address this problem. However, they come at a high silicon cost, and often require suspending the normal network activity while executing a centralized, resource-hungry reconfiguration algorithm. This paper proposes a novel, fast and minimalistic routing reconfiguration algorithm, called BLINC. BLINC utilizes precomputed routing metadata to quickly evaluate localized detours upon each fault manifestation. We showcase the efficacy of our algorithm by deploying it in a novel NoC fault detection and reconfiguration solution, where BLINC enables uninterrupted NoC operation during aggressive online testing. If a fault seems likely to occur, we circumvent it in advance with the aid of our BLINC reconfiguration algorithm. Experimental results show an 80% reduction in the average number of routers affected by a reconfiguration event, compared to state-of-the-art techniques. BLINC enables negligible performance degradation in our detection and reconfiguration solution, while solutions based on current techniques suffer a 17-fold latency increase.

show abstract

Section: B Uninterrupted Availability With Blincmentioning

confidence: 99%

“…under a range of testing rates and test durations. Viable testing rates and durations were derived from [9,11,23]. For instance, the rightmost data point in our plot corresponds to one complete test period every 112,000 cycles.…”

Section: B Uninterrupted Availability With Blincmentioning

confidence: 99%

Brisk and limited-impact NoC routing reconfiguration

Lee

Parikh

Bertacco

2014

Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE), 2014

View full text Add to dashboard Cite

show abstract

“…In known approaches to wear-out monitoring [9], [10], [16], [11], [12], [13], [14], some consider electromigration [9], some consider NBTI (Negative Bias Temperature Instability) [11], [12], [14], some gate oxide breakdown [9], [13] or some other or unspecified wear-out mechanism [16], [17]. Several of the known wear-out mechanisms have in common that they affect the signal propagation delay through a circuit.…”

Section: Previous Work On Electromigration Wear-out Monitoringmentioning

confidence: 99%

“…• One type of wear-out monitors are based on regularly performed speed tests [10]. Reduction in system-wide slack indicates impending failure due to wear-out.…”

Section: Previous Work On Electromigration Wear-out Monitoringmentioning

confidence: 99%

See 1 more Smart Citation

Measurement point selection for in-operation wear-out monitoring

Ingelsson

Chang

Larsson

2011

14th IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems

View full text Add to dashboard Cite

-In recent IC designs, the risk of early failure due to electromigration wear-out has increased due to reduced feature dimensions. To give a warning of impending failure, wearout monitoring approaches have included delay measurement circuitry on-chip. Due to the high cost of delay measurement circuitry this paper presents a method to reduce the number of necessary measurement points. The proposed method is based on identification of wear-out sensitive interconnects and selects a small number of measurement points that can be used to observe the state of all the wear-out sensitive interconnects. The method is demonstrated on ISCAS85 benchmark ICs with encouraging results.

show abstract

Low overhead online periodic testing for GPGPUs

Abdel-Majeed

Dweik

2018

Integration

View full text Add to dashboard Cite

WearMon: Reliability monitoring using adaptive critical path testing

Cited by 9 publications

References 20 publications

Brisk and limited-impact NoC routing reconfiguration

Brisk and limited-impact NoC routing reconfiguration

Measurement point selection for in-operation wear-out monitoring

Low overhead online periodic testing for GPGPUs

Contact Info

Product

Resources

About