English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The pivotal issue of reliability is one of colossal concern for circuitdesigners. The driving force is transistor aging, dependent on operatingvoltage and workload. At the design time, it is difficult to estimateclose-to-the-edge guardbands that keep aging effects during the lifetime atbay. This is because the foundry does not share its calibrated physics-basedmodels, comprised of highly confidential technology and material parameters.However, the unmonitored yet necessary overestimation of degradation amounts toa performance decline, which could be preventable. Furthermore, thesephysics-based models are exceptionally computationally complex. The costs ofmodeling millions of individual transistors at design time can be evidentlyexorbitant. We propose the revolutionizing prospect of a machine learning modeltrained to replicate the physics-based model, such that no confidentialparameters are disclosed. This effectual workaround is fully accessible tocircuit designers for the purposes of design optimization. We demonstrate themodels' ability to generalize by training on data from one circuit and applyingit successfully to a benchmark circuit. The mean relative error is as low as1.7%, with a speedup of up to 20X. Circuit designers, for the first time ever,will have ease of access to a high-precision aging model, which is paramountfor efficient designs. This work is a promising step in the direction ofbridging the wide gulf between the foundry and circuit designers.

Modeling and Predicting Transistor Aging under Workload Dependency using Machine Learning