OpeNPDN: A Neural-Network-Based Framework for Power Delivery Network Synthesis

• Published in: IEEE transactions on computer-aided design of integrated circuits and systems 2022-10, Vol.41 (10), p.3515-3528
• Main Authors: Chhabria, Vidya A., Sapatnekar, Sachin S.
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Circuits; Congestion; Datasets; deep neural network; Electric potential; Electric power; Electricity generation; Electromigration; Floorplans; Handheld computers; Machine learning; machine learning (ML); Metals; Network synthesis; Neural networks; Optimization; physical design; power delivery network (PDN); Resistance; Routing; Training; transfer learning; Wires
• ISSN: 0278-0070; 1937-4151
• DOI: 10.1109/TCAD.2021.3132554

Power delivery network (PDN) design is a nontrivial, time-intensive, and iterative task. Correct PDN design must consider 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.