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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The electromigration (EM)-induced reliability issues in very large scaleintegration (VLSI) circuits have attracted increased attention due to thecontinuous technology scaling. Traditional EM models often lead to overlypessimistic prediction incompatible with the shrinking design margin in futuretechnology nodes. Motivated by the latest success of neural networks in solvingdifferential equations in physical problems, we propose a novel mesh-free modelto compute EM-induced stress evolution in VLSI circuits. The model utilizes aspecifically crafted space-time physics-informed neural network (STPINN) as thesolver for EM analysis. By coupling the physics-based EM analysis with dynamictemperature incorporating Joule heating and via effect, we can observe stressevolution along multi-segment interconnect trees under constant, time-dependentand space-time-dependent temperature during the void nucleation phase. Theproposed STPINN method obviates the time discretization and meshing required inconventional numerical stress evolution analysis and offers significantcomputational savings. Numerical comparison with competing schemes demonstratesa 2x ~ 52x speedup with a satisfactory accuracy.

A Space-Time Neural Network for Analysis of Stress Evolution under DC Current Stressing