LMM-IR: Large-Scale Netlist-Aware Multimodal Framework for Static IR-Drop Prediction

TL;DR

This paper introduces LMM-IR, a large-scale multimodal framework utilizing netlist topology as 3D point clouds for fast, accurate static IR drop prediction in chip design, outperforming existing methods.

Contribution

The paper presents a novel multimodal approach with a netlist transformer and 3D point cloud representation for efficient IR drop prediction at large scale.

Findings

Achieves the best F1 score in ICCAD 2023 contest

Lowest MAE among state-of-the-art algorithms

Handles netlists with up to millions of nodes

Abstract

Static IR drop analysis is a fundamental and critical task in the field of chip design. Nevertheless, this process can be quite time-consuming, potentially requiring several hours. Moreover, addressing IR drop violations frequently demands iterative analysis, thereby causing the computational burden. Therefore, fast and accurate IR drop prediction is vital for reducing the overall time invested in chip design. In this paper, we firstly propose a novel multimodal approach that efficiently processes SPICE files through large-scale netlist transformer (LNT). Our key innovation is representing and processing netlist topology as 3D point cloud representations, enabling efficient handling of netlist with up to hundreds of thousands to millions nodes. All types of data, including netlist files and image data, are encoded into latent space as features and fed into the model for static voltage drop prediction. This enables the integration of data from multiple modalities for complementary predictions. Experimental results demonstrate that our proposed algorithm can achieve the best F1 score and the lowest MAE among the winning teams of the ICCAD 2023 contest and the state-of-the-art algorithms.