发表机构
University of Thessaly; University of Amsterdam; Trinity College Dublin（色萨利大学; 阿姆斯特丹大学; 都柏林圣三一大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出物理引导变压器框架，用于多段互连电迁移应力快速预测，在IBM基准上相对L2误差低于8%，速度提升达2459.68倍。
AI 中文摘要
随着技术向更小节点扩展，电流密度的增加使得电迁移（EM）成为片上互连中主要的可靠性挑战之一。准确的瞬态应力分析对于识别易受电迁移退化影响的导线至关重要，但将基于物理的求解器应用于众多互连在计算上仍然昂贵。本文提出了一种物理引导的变压器框架，用于多段互连线中的快速电迁移应力预测。该框架将每条线转换为几何和直流感知的段令牌，并使用变压器注意力捕获线级上下文。然后，一个轻量级查询解码器在选定的位置和时间瞬间预测应力。模型训练目标结合了归一化监督回归、线级相对$L_2$损失以及物理引导的连续性和终端通量项。在IBM电网基准上的实验表明，所提出的模型实现了低于8%的相对$L_2$误差，并且与矩阵指数求解器相比，速度提升高达2459.68倍。
英文摘要
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.
