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

2025-02-13

AI Summary

Static IR-drop prediction for integrated circuits is computationally expensive and inaccurate using conventional methods. Method: This paper proposes the first end-to-end deep learning framework that jointly exploits layout images and netlist topology. It introduces a customized CNN architecture to co-extract spatial power-distribution-network (PDN) features and circuit connectivity features, enabling unified image–graph representation; critically, it embeds netlist encoding directly into the image processing pipeline, eliminating reliance on iterative SPICE-like simulations. Contribution/Results: Evaluated on the ICCAD CAD Contest 2023 benchmark, our method achieves state-of-the-art prediction accuracy—significantly outperforming industrial-grade SPICE simulators and timing-driven tools—while accelerating inference by two to three orders of magnitude. This enables high-throughput, high-accuracy IR-drop analysis essential for advanced-node IC design.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Fast and accurate IR drop estimation
• Combines image-based and netlist-based features
• Customized CNN for PDN feature extraction

Innovation

• Neural network for IR drop estimation
• Combines image and netlist features
• Custom CNN extracts PDN features