A Physics-Guided Transformer Framework for Electromigration Analysis in Multi-Segment Interconnects

2026-10-05

AI Summary

This study addresses the high computational cost and limited scalability of conventional electromigration stress analysis for advanced-technology interconnects by proposing a physics-guided Transformer framework. The method encodes interconnects into segment tokens that integrate geometric and DC-aware information, leveraging attention mechanisms to capture contextual dependencies. A lightweight decoder then rapidly predicts transient stress distributions, while physics-constrained losses enforcing continuity and terminal flux conditions balance accuracy with efficiency. Evaluated on IBM benchmarks, the proposed framework achieves relative errors below 8% and delivers up to a 2459.68× speedup over traditional matrix exponential solvers, demonstrating its potential for fast and reliable electromigration assessment in modern integrated circuit design.

Abstract

As technology scales to smaller nodes, increasing current densities make electromigration (EM) one of the dominant reliability challenges in on-chip interconnects. Accurate transient stress analysis is needed to identify wires susceptible to EM degradation, but applying physics-based solvers across many interconnects remains computationally expensive. This paper proposes a physics-guided transformer framework for fast EM stress prediction in multi-segment interconnect lines. The framework converts each line into geometry- and DC-aware segment tokens and uses transformer attention to capture line-level context. A lightweight query decoder then predicts stress at selected locations and time instants. The model is trained with an objective that combines normalized supervised regression, linewise relative-$L_2$ loss, and physics-guided continuity and terminal-flux terms. Experiments on IBM power grid benchmarks show that the proposed model achieves relative-$L_2$ error below 8\% and reaches up to 2459.68$\times$ speedup compared with the matrix exponential~solver.

Problem

• Electromigration
• Transient stress analysis
• Multi-segment interconnects
• Reliability
• Computational cost

Innovation

• Physics-Guided Transformer
• Electromigration Analysis
• Multi-Segment Interconnects
• Transient Stress Prediction
• Physics-Informed Loss