XGBIR: An XGBoost-based IR Drop Predictor for Power Delivery Network
Chi-Hsien Pao1,a, An-Yu Su1,b and Yu-Min Lee1,2,c
1Institute of Communications Engineering, College of Electrical and Computer Engineering
2Center for mmWave Smart Radar Systems and Technologies, National Chiao Tung University, Taiwan
ashawn07023.cm05g@nctu.edu.tw
baysu.cm07g@nctu.edu.tw
cyumin@nctu.edu.tw
ABSTRACT
This work utilizes the XGBoost to build a machine learning-based IR drop predictor, XGBIR, for the power grid. To capture the behavior of power grid, we extract its several features and employ its locality property to save the extraction time. XGBIR can be effectively applied to large designs and the average error of predicted IR drops is less than 6 mV.
