Real-Time Dynamic IR-drop Prediction for IR ECO

During the IR Engineering Change Order (ECO) stage, cell moving leads to uncertain IR-drop results, requiring designers to explore multiple ECO candidates in each iteration to find a solution that effectively mitigates IR-drop, resulting in a long evaluation time. Although machine learning (ML)-base...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Lee, Yu-Che, Chen, Yu-Hsuan, Cheng, Yu-Chen, Chang, Yong-Fong, Lin, Jia-Wei, Pao, Hsun-Wei, Chen, Yung-Chih, Li, Yi-Ting, Tang, Wuqian, Chang, Shih-Chieh, Wang, Chun-Yao
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Design automation
Estimation
Machine learning
Predictive models
Real-time systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During the IR Engineering Change Order (ECO) stage, cell moving leads to uncertain IR-drop results, requiring designers to explore multiple ECO candidates in each iteration to find a solution that effectively mitigates IR-drop, resulting in a long evaluation time. Although machine learning (ML)-based predictors have been proposed to expedite IR-drop evaluation, partial simulations are still needed to update features after ECO, taking over an hour and delaying IR-drop results. In this work, we propose a real-time dynamic IR-drop estimation method based on an XGBoost model with a global view of a cell's surroundings. After ECO, our method provides dynamic IR-drop results in minutes without running any simulations and thus achieves real-time estimation. This allows designers to evaluate multiple ECO candidates concurrently in a single iteration. We conducted the experiments on five ECO candidates of an industrial design with 3 nm technology. The results show that the proposed model can effectively predict the IR-drop variations of moved cells after ECO with over 93 \% of fixed cells detected and an average MAE of 8.75 mV achieved. Furthermore, our method achieves an 88 X speedup over Voltus (commercial tool) and a 64 X speedup over traditional ML predictors when evaluating a single ECO candidate. The speedup is expected to increase as the number of ECO candidates increases.
DOI:10.1109/DAC63849.2025.11133331