通过注意力机制动态调整电路图层权重，提升芯片电源压降预测精度。
WACA-UNet: Weakness-Aware Channel Attention for Static IR Drop Prediction in Integrated Circuit Design
- 设计弱项感知通道注意力，递归增强薄弱特征层
- 在ICCAD-2023数据集上误差降低61.1%，F1提升71.0%
- 适合芯片物理设计与AI加速验证方向的研究者
精准的电源完整性问题（如IR压降）空间预测对可靠VLSI设计至关重要。传统基于仿真的求解器计算成本高且难以扩展。本文将IR压降估计重构为从电路版图生成的异构多通道物理图上的像素级回归任务。现有学习方法对所有输入通道（如金属层、通孔层、电流分布图）同等对待，忽略了其对预测准确性贡献的差异。为此，我们提出一种新型弱项感知通道注意力（WACA）机制，通过双阶段门控策略递归增强弱特征通道，同时抑制过主导通道。该机制集成于基于ConvNeXtV2的注意力U-Net中，实现自适应均衡的特征表示。在公开的ICCAD-2023基准测试中，我们的方法相较2023年竞赛优胜方案，平均绝对误差降低61.1%，F1分数提升71.0%。结果表明，通道间的异质性是用于VLSI物理布局分析的关键归纳偏置。
原文摘要 · Abstract (English)
Accurate spatial prediction of power integrity issues, such as IR drop, is critical for reliable VLSI design. However, traditional simulation-based solvers are computationally expensive and difficult to scale. We address this challenge by reformulating IR drop estimation as a pixel-wise regression task on heterogeneous multi-channel physical maps derived from circuit layouts. Prior learning-based methods treat all input layers (e.g., metal, via, and current maps) equally, ignoring their varying importance to prediction accuracy. To tackle this, we propose a novel Weakness-Aware Channel Attention (WACA) mechanism, which recursively enhances weak feature channels while suppressing over-dominant ones through a two-stage gating strategy. Integrated into a ConvNeXtV2-based attention U-Net, our approach enables adaptive and balanced feature representation. On the public ICCAD-2023 benchmark, our method outperforms the ICCAD-2023 contest winner by reducing mean absolute error by 61.1% and improving F1-score by 71.0%. These results demonstrate that channel-wise heterogeneity is a key inductive bias in physical layout analysis for VLSI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。