CFIRSTNET: Comprehensive Features for Static IR Drop Estimation with Neural Network

TL;DR

This paper introduces CFIRSTNET, a neural network-based approach that combines image-based and netlist-based features for fast, accurate static IR drop estimation in modern electronic designs, leveraging AI acceleration.

Contribution

It presents a novel CNN framework that effectively integrates diverse features for improved IR drop prediction, validated on open-source datasets and benchmarked in ICCAD CAD Contest 2023.

Findings

Achieved state-of-the-art accuracy in IR drop estimation

Demonstrated efficiency with AI acceleration techniques

Validated effectiveness on benchmark datasets

Abstract

IR drop estimation is now considered a first-order metric due to the concern about reliability and performance in modern electronic products. Since traditional solution involves lengthy iteration and simulation flow, how to achieve fast yet accurate estimation has become an essential demand. In this work, with the help of modern AI acceleration techniques, we propose a comprehensive solution to combine both the advantages of image-based and netlist-based features in neural network framework and obtain high-quality IR drop prediction very effectively in modern designs. A customized convolutional neural network (CNN) is developed to extract PDN features and make static IR drop estimations. Trained and evaluated with the open-source dataset, experiment results show that we have obtained the best quality in the benchmark on the problem of IR drop estimation in ICCAD CAD Contest 2023, proving the effectiveness of this important design topic.