Global and Local Attention-based Inception U-Net for Static IR Drop Prediction

TL;DR

This paper introduces a novel attention-based U-Net model incorporating Transformer, CBAM, and Inception modules for fast and accurate static IR drop prediction in chip design, significantly improving prediction quality.

Contribution

The paper presents a new global and local attention-based Inception U-Net architecture with additional features and data adjustment techniques, advancing IR drop prediction methods.

Findings

Achieved top results in ICCAD 2023 contest

Outperformed existing state-of-the-art algorithms

Enhanced feature extraction with attention mechanisms

Abstract

Static IR drop analysis is a fundamental and critical task in chip design since the IR drop will significantly affect the design's functionality, performance, and reliability. However, the process of IR drop analysis can be time-consuming, potentially taking several hours. Therefore, a fast and accurate IR drop prediction is paramount for reducing the overall time invested in chip design. In this paper, we propose a global and local attention-based Inception U-Net for static IR drop prediction. Our U-Net incorporates the Transformer, CBAM, and Inception architectures to enhance its feature capture capability at different scales and improve the accuracy of predicted IR drop. Moreover, we propose 4 new features, which enhance our model with richer information. Finally, to balance the sampling probabilities across different regions in one design, we propose a series of novel data spatial adjustment techniques, with each batch randomly selecting one of them during training. Experimental results demonstrate that our proposed algorithm can achieve the best results among the winning teams of the ICCAD 2023 contest and the state-of-the-art algorithms.