RUS  ENG
Full version
JOURNALS // Proceedings of the Institute for System Programming of the RAS // Archive

Proceedings of ISP RAS, 2023 Volume 35, Issue 5, Pages 127–144 (Mi tisp819)

Fast analysis of static IR drop effect based on machine learning methods

R. A. Solovyeva, D. V. Telpukhova, E. D. Demidovb, I. I. Shafeeva

a Institute for Design Problems in Microelectronics of Russian Academy of Sciences
b National Research University of Electronic Technology

Abstract: As part of the ICCAD Contest 2023 (Problem C) competition, the paper describes a methodology for applying ML models to perform static IR drop analysis. Methods for obtaining a database for training a neural network to solve this problem are given. We consider a technique for training an ML model to analyze the static IR-drop effect. The generation of input data for training a neural network from SPICE netlists is also discussed in this paper. This solution is ranked in the TOP 3 at the ICCAD Contest 2023 competition.

Keywords: IR drop analysis, ML-model, neural network, machine learning, database

DOI: 10.15514/ISPRAS-2023-35(5)-9



© Steklov Math. Inst. of RAS, 2024