Lune

DAC2021Top-tier venue

SPROUT - Smart Power ROUting Tool for Board-Level Exploration and Prototyping

Rassul Bairamkulov, Abinash Roy, Mali Nagarajan, Vaishnav Srinivas, Eby G. Friedman

Abstract

The board-level power network design process is governed by system-level parameters such as the number of layers and the ball grid array (BGA) pattern. These parameters influence the characteristics of the resulting system, such as power, speed, and cost. Evaluating the impact of these parameters is, however, challenging. To estimate the reduction in impedance if, for example, additional BGA balls are dedicated to the power delivery system, adjustments to the board layout and an additional impedance extraction process are required. These processes are poorly automated, requiring significant time and labor. Automating power network exploration and prototyping can greatly enhance the power delivery design process by increasing the number of possible design options. With power network exploration and prototyping, the effects of the system parameters on the electrical characteristics can be better understood, providing valuable insight into the early design stages. SPROUT - an automated algorithm for prototyping printed circuit board (PCB) power networks - is presented here. This tool includes the first fully automated algorithm for board-level power network layout synthesis. Two board-level industrial power networks are synthesized using SPROUT where a ball grid array is connected with a power management IC and decoupling capacitors across four voltage domains. The impedance of the resulting layouts is in good agreement with manual PCB layouts while requiring 95% less design time.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. FanoutNet: A Neuralized PCB Fanout Automation Method Using Deep Reinforcement LearningHaiyun Li, Jixin Zhang, Ning Xu, Mingyu LiuAAAI 2023 · 11 citations
  2. BNN-YEO: an efficient Bayesian Neural Network for yield estimation and optimizationZhenxing Dou, Ming Cheng, Ming Jia, Peng WangDAC 2024 · 2 citations
  3. CDLS: Constraint Driven Generative AI Framework for Analog Layout SynthesisPrasanth Mangalagiri, Lynn Qian, Farrukh Zafar, Praveen Mosalikanti et al.DAC 2024 · 2 citations
  4. A Matching Based Escape Routing Algorithm with Variable Design Rules and ConstraintsQinghai Liu, Disi Lin, Chuandong Chen, Huan He et al.DAC 2023 · 6 citations
  5. Power-Grid Structure Exploration with Unified Sequence-based Learning FrameworkYi-Lin Chuang, Hao-Wei Chan, Chih-Yun Yen, Shih-An Hsieh et al.DAC 2025
Dusk over the sea between two cliffs drawn in fine vertical lines