Recently, machine learning and AI have been applied to several electronic design automation (EDA) tasks [1], such as performance prediction, decision-making for designs, and automated design. The data-driven optimization processes provide an alternative approximation solution for NP-complete problems in EDA. However, there are still several challenges to applying machine learning algorithms in EDA problems. First, due to the protection of intellectual property (IP), it is difficult to access huge amounts of public datasets as training data. The deep learning framework relies on pre-trained models and fine-tuning techniques on small datasets. However, this approach demands high computational resources and large model size. Second, the end-to-end optimization in deep learning is viewed as a black box that lacks interpretability for making decisions in hardware designs. As a result, we aim to develop a green learning algorithm to mitigate the high demand for large amounts of training data with explainable results for EDA problems.


Currently, we propose a green learning architecture to address the IR-drop prediction problem. We parse netlist files into 2D format and extract features by our green learning framework automatically. Then, we select discriminative features as the input of XGboost to regress the IR-drop value. We aim to estimate the IR-drop value accurately while keeping a small model size and Flops number in an energy-efficient way.



[1] Huang, Guyue, et al. “Machine learning for electronic design automation: A survey.” ACM Transactions on Design Automation of Electronic Systems (TODAES) 26.5 (2021): 1-46.