OpeNPDN: A Neural-network-based Framework for Power Delivery Network Synthesis

TL;DR

This paper introduces OpeNPDN, a CNN-based framework for efficient power delivery network synthesis that leverages synthetic and real data to optimize routing and meet electrical constraints.

Contribution

It presents a novel machine learning methodology using CNNs and transfer learning for PDN design, improving routing efficiency and compliance with IR drop and electromigration limits.

Findings

Reduces routing congestion by freeing thousands of tracks.

Achieves PDN designs that meet IR drop and EM specifications.

Utilizes transfer learning to adapt synthetic data models to real circuits.

Abstract

Power delivery network (PDN) design is a nontrivial, time-intensive, and iterative task. Correct PDN design must account for considerations related to power bumps, currents, blockages, and signal congestion distribution patterns. This work proposes a machine learning-based methodology that employs a set of predefined PDN templates. At the floorplan stage, coarse estimates of current, congestion, macro/blockages, and C4 bump distributions are used to synthesize a grid for early design. At the placement stage, the grid is incrementally refined based on more accurate and fine-grained distributions of current and congestion. At each stage, a convolutional neural network (CNN) selects an appropriate PDN template for each region on the chip, building a safe-by-construction PDN that meets IR drop and electromigration (EM) specifications. The CNN is initially trained using a large synthetically-created dataset, following which transfer learning is leveraged to bridge the gap between real-circuit data (with a limited dataset size) and synthetically-generated data. On average, the optimization of the PDN frees thousands of routing tracks in congestion-critical regions, when compared to a globally uniform PDN, while staying within the IR drop and EM limits.