New-Generation Design-Technology Co-Optimization (DTCO): Machine-Learning Assisted Modeling Framework
New-Generation Design-Technology Co-Optimization (DTCO): Machine-Learning Assisted Modeling Framework
复制标题
新一代设计技术协同优化（DTCO）：机器学习辅助建模框架
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Ru Huang
中科院分区：
文献类型：
--
作者：
Zhe Zhang;Runsheng Wang;Cheng Chen;Qianqian Huang;Yangyuan Wang;Cheng Hu;Dehuang Wu;Joddy W. Wang;Ru Huang
本文提出了设计技术协同优化(DTCO)流程中的机器学习辅助建模框架。基于神经网络(NN)的替代模型被用来替代不需要器件物理先验知识的新器件的紧凑模型来预测器件和电路的电特性。该建模框架在FinFET中得到了验证，在器件级和电路级具有较高的预测精度。对数据处理和预测结果的细节进行了讨论。此外，将相同的框架应用于新的机制器件隧道FET(TFET)，以预测器件和电路特性。该工作为DTCO流动提供了新的建模方法。
In this paper, we propose a machine-learning assisted modeling framework in design-technology co-optimization (DTCO) flow. Neural network (NN) based surrogate model is used as an alternative of compact model of new devices without prior knowledge of device physics to predict device and circuit electrical characteristics. This modeling framework is demonstrated and verified in FinFET with high predicted accuracy in device and circuit level. Details about the data handling and prediction results are discussed. Moreover, same framework is applied to new mechanism device tunnel FET (TFET) to predict device and circuit characteristics. This work provides new modeling method for DTCO flow.