Probabilistic Networks and Expert Systems
Probabilistic Networks and Expert Systems
Approximating MAP using Local Search
UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
VLSID '04 Proceedings of the 17th International Conference on VLSI Design
A Probabilistic-Based Design Methodology for Nanoscale Computation
Proceedings of the 2003 IEEE/ACM international conference on Computer-aided design
Accurate Reliability Evaluation and Enhancement via Probabilistic Transfer Matrices
Proceedings of the conference on Design, Automation and Test in Europe - Volume 1
Toward Hardware-Redundant, Fault-Tolerant Logic for Nanoelectronics
IEEE Design & Test
Test set enrichment using a probabilistic fault model and the theory of output deviations
Proceedings of the conference on Design, automation and test in Europe: Proceedings
Solving MAP exactly using systematic search
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Majority multiplexing-economical redundant fault-tolerant designs for nanoarchitectures
IEEE Transactions on Nanotechnology
On the maximum tolerable noise for reliable computation by formulas
IEEE Transactions on Information Theory
| Hi-index | 0.00 |
Reliability modeling and evaluation is expected to be one of the major issues in emerging nano-devices and beyond 22nm CMOS. Such devices would have inherent propensity for gate failures due to the underlying device variabilities. Many of these failures would be transient in nature, necessitating the need for probabilistic logic base danalysis. Current research in this area is concerned with computing error bounds, but they do not account for circuits structures or are usually derived for specific logic gate types. In addition, the usual focus is on computing the average error behavior. In this work, we propose an exact probabilistic error model to compute the maximum error in a circuit-specific manner and can handle various types of logical components in the same circuit. We model the error estimation problem as a maximum a posteriori estimate (MAP) over the joint error probability function of the entire circuit. Using this model, we can not only compute the maximum error, but can also identify the input vector that cause the maximum output error. We demonstrate this model using MCNC and ISCAS circuits. We observe that for some circuits, maximum error probabilities are significantly larger than the average likelihood error, thus making acase for the consideration of maximum error metric as an essential design guideline rather than just average-case estimates. We also find that the error estimates depend on the specific circuit structure. Lastly, we observe that the maximum error probabilities are sensitive to the individual gate failure probabilities.