工作量
计算机科学
计算机工程
水准点(测量)
晶体管
电路设计
加速
机器学习
人工智能
电子工程
电压
嵌入式系统
电气工程
工程类
并行计算
操作系统
地理
大地测量学
作者
Paul R. Genßler,Hamza Errahmouni Barkam,Karthik Pandaram,Mohsen Imani,Hussam Amrouch
出处
期刊:IEEE Transactions on Circuits and Systems I-regular Papers
[Institute of Electrical and Electronics Engineers]
日期:2023-07-10
卷期号:70 (9): 3699-3711
被引量:50
标识
DOI:10.1109/tcsi.2023.3289325
摘要
The pivotal issue of reliability is one of the major concerns for circuit designers. The driving force is transistor aging, dependent on operating voltage and workload. At the design time, it is difficult to estimate close-to-the-edge guardbands that keep aging effects during the lifetime at bay. This is because the foundry does not share its calibrated physics-based models, comprised of highly confidential technology and material parameters. However, the unmonitored yet necessary overestimation of degradation amounts to a performance decline, which could be preventable. Furthermore, these physics-based models are computationally complex. The costs of modeling millions of individual transistors at design time can be exorbitant. We propose the use of a machine learning model trained to replicate the physics-based model, such that no confidential parameters are disclosed. This effectual workaround is fully accessible to circuit designers for the purposes of design optimization. We demonstrate the model’s ability to generalize by training on data from one circuit and applying it successfully to a benchmark circuit. The mean relative error is as low as 1.7%, with a speedup of up to$20\times $. Circuit designers, for the first time ever, will have ease of access to a high-precision aging model, which is paramount for efficient designs. In contrast to existing work, our approach takes the full switching activity into account to model recovery effects. This work is a promising step in the direction of bridging the gap between the foundry and circuit designers.
科研通智能强力驱动
Strongly Powered by AbleSci AI