用高斯过程与主动学习，高效精准构建电流源模型。
Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning
- 结合高斯过程与主动学习，优化电流源建模流程。
- 平均绝对误差2.05皮秒，相对误差2.27%，精度超商用工具。
- 运行时间降至27%，存储需求减少19.5倍，适合先进制程设计。
复合电流源（CCS）模型作为先进的时序模型，相比传统非线性延迟模型（NLDM），能更准确地刻画单元在先进制程下的动态效应与相互作用。然而，其高精度要求、海量数据及高昂仿真成本带来了严峻挑战。为此，本文提出一种基于高斯过程回归（GPR）与主动学习（AL）的新型建模方法，显著提升了特征提取的效率与准确性。在台积电22纳米工艺下，针对57个单元在9种工艺-电压-温度（PVT）组合条件下的电流波形，该方法平均绝对误差仅为2.05皮秒，相对误差为2.27%。同时，相比商用工具，运行时间降低至27%，存储需求减少高达19.5倍，展现出卓越的实用价值。
原文摘要 · Abstract (English)
The composite current source (CCS) model has been adopted as an advanced timing model that represents the current behavior of cells for improved accuracy and better capability than traditional non-linear delay models (NLDM) to model complex dynamic effects and interactions under advanced process nodes. However, the high accuracy requirement, large amount of data and extensive simulation cost pose severe challenges to CCS characterization. To address these challenges, we introduce a novel Gaussian Process Regression(GPR) model with active learning(AL) to establish the characterization framework efficiently and accurately. Our approach significantly outperforms conventional commercial tools as well as learning based approaches by achieving an average absolute error of 2.05 ps and a relative error of 2.27% for current waveform of 57 cells under 9 process, voltage, temperature (PVT) corners with TSMC 22nm process. Additionally, our model drastically reduces the runtime to 27% and the storage by up to 19.5x compared with that required by commercial tools.
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。