[论文] Surrogate-Assisted Compact-Model Extraction for SKY130 CMOS at 77 K
研究领域: ML 作者: Aaron Wang, Olivia Gzamouranis, Vaibhav Lohia, Hershel Fei Xun Weiner, Olivia Seidel, Richard Cavanaugh, Giuseppe Di Guglielmo, Nhan Tran, Davide…
论文概要
研究领域: ML 作者: Aaron Wang, Olivia Gzamouranis, Vaibhav Lohia, Hershel Fei Xun Weiner, Olivia Seidel, Richard Cavanaugh, Giuseppe Di Guglielmo, Nhan Tran, Davide Braga 发布时间: 2026-11-16 arXiv: 2611.21594
中文摘要
低温电路设计需要能在标准电路模拟器中复现实测低温行为并运行的紧凑晶体管模型。我们使用 NGSpice 的神经替代模型,将 BSIM4 参数拟合到 SkyWater 130 nm(SKY130)晶体管在 77 K 下测得的 I-V 曲线。该替代模型将紧凑模型参数和器件几何映射到完整的输出和转移特性曲线集。参数提取是一个有界最小二乘搜索:NGSpice 模拟库提供初始候选,替代模型的有限差分提供局部雅可比矩阵,NGSpice 对得到的卡片进行重新模拟后再选择。在 18 个实测几何上,我们比较了 7 个卡片参数的搜索与按 NGSpice 灵敏度选取的 43 个参数的搜索。相对于之前发布卡片的 NGSpice 重新模拟,两种搜索分别将样本内平均相对均方根误差(RRMS)降低了 17% 和 26%。43 参数搜索的总体误差更低,但 7 参数搜索在高偏置曲线上的平均值更低。
原文摘要
Cryogenic circuit design requires compact transistor models that reproduce measured low-temperature behavior and run in standard circuit simulators. We fit BSIM4 parameters to measured I-V curves of SkyWater 130 nm (SKY130) transistors at 77 K using a neural surrogate of NGSpice. The surrogate maps compact-model parameters and device geometry to the complete set of output and transfer characteristics. Extraction is a bounded least-squares search: a bank of NGSpice simulations supplies initial candidates, finite differences of the surrogate supply the local Jacobian, and NGSpice re-simulates the resulting cards before selection. On 18 measured geometries, we compare a search over seven card parameters with a search over 43 parameters selected by NGSpice sensitivity. Relative to NGSpice re-s...
*自动采集于 2026-11-18*
#论文 #arXiv #ML #小凯