GridNet

Zhou, Honggang; Jin, Wentian; Tan, Sheldon X.-D.

doi:10.1145/3400302.3415714

Cited by 18 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, EMGraph surpasses EM-GAN with 4 times higher prediction accuracy and 14 times faster speed. In [121], a conditional generative adversarial networks-based (CGAN-based) framework (called GridNet) was developed, as shown in Figure 17, to accelerate the incremental full-chip EM-induced IR drop analysis and the optimization for IR drop violation fixing. GridNet provides accurate prediction on IR drop as compared with the ground truth obtained from EMSpice.…”

Section: Fast Em Assessment and Optimizationmentioning

confidence: 99%

“…In [121], a conditional generative adversarial networks-based (CGAN-based) framework (called GridNet) was developed, as shown in Figure 17, to accelerate the incremental full-chip EM-induced IR drop analysis and the optimization for IR drop violation fixing. GridNet provides accurate prediction on IR drop as compared with the ground truth Successful P/G design targets at a good enough EM lifetime with a reasonable cost on area.…”

Section: Fast Em Assessment and Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Interconnect and Packaging

2023

View full text Add to dashboard Cite

show abstract

Section: Fast Em Assessment and Optimizationmentioning

confidence: 99%

Section: Fast Em Assessment and Optimizationmentioning

confidence: 99%

Advanced Interconnect and Packaging

2023

View full text Add to dashboard Cite

show abstract

“…Convolutional neural networks (CNN) as ML models have the ability to extract and abstract features from imagebased data, outperforming traditional shallow ML models in handling challenging tasks [31], [32]. In the CAD domain, CNNs have been utilized to detect layout manufacturability and reliability violations [29], [33]- [37]. CNNs have been developed to predict congestion heatmaps, and by utilizing the model, unnecessary searches can be avoided, thereby speeding up the overall routing process [38].…”

Section: B Model-based Eda Approachesmentioning

confidence: 99%

Unet-Astar: A Deep Learning-Based Fast Routing Algorithm for Unified PCB Routing

Yin,

Jin,

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In recent years, there has been extensive research on the routing problem of printed circuit boards (PCBs). Due to the increasing number of pins, high pin density, and unique physical constraints, manual PCB routing has become a time-consuming task to achieve design convergence. Previous work decomposed the problem into escape routing and area routing, focusing on these problems separately. However, there was always a gap between these two problems, requiring significant human effort for iterative algorithm adjustments. Furthermore, previous area routing work mainly focused on routing between ball grid array (BGA) packages in escape routing. However, in practice, many components are not in the form of BGA packages, such as passive devices, decoupling capacitors, and through-hole pin arrays. Therefore, it is necessary to study a unified routing approach. The current unified routing approach adopts the A* algorithm, but there is still room for improvement in routing speed. This paper proposes a new algorithm called Unet-Astar, which accelerates the routing efficiency by employing deep learning algorithms in a simulated environment. Additionally, a Deeper Unet is proposed for generating recommended regions for the routing algorithm. The new network structure can provide more contextual information, thereby improving routing efficiency. Experimental results demonstrate the effectiveness and efficiency of the proposed algorithm. Specifically, for all given test cases, our router achieves approximately a 70% improvement in runtime speed compared to the old router. Another major contribution of this work is the development of a routing problem set generator, which can generate parameterized routing problem sets with different sizes and constraints. This enables the evaluation of different routing algorithms and the generation of training datasets for future data-driven routing methods. All the code has been open-sourced and can be found at https://github.com/Firesuiry/Unet-Astar-For-PCB-Routing. INDEX TERMS physical design, printed circuit board, routing, Machine learning I. INTRODUCTION 1 This article has been accepted for publication in IEEE Access.

show abstract

“…In both vector-based and vectorless IR drop scenarios, it performs significantly better than state-of-the-art ML algorithms and requires an order of magnitude less estimating time than commercial tools. Using conditional generative adversarial networks (CGAN), [44] present GridNet, a quick data-driven approach for EM-induced IR drop analysis for power grid networks. Accelerating incremental full-chip EM-induced IR drop analysis and IR drop violation correction during power grid design and optimization are its two main objectives.…”

Section: Figure 20 Routenet Model [33]mentioning

confidence: 99%

Application of Machine Learning to Physical Design

B¹

View full text Add to dashboard Cite

GridNet

Cited by 18 publications

References 30 publications

Advanced Interconnect and Packaging

Advanced Interconnect and Packaging

Unet-Astar: A Deep Learning-Based Fast Routing Algorithm for Unified PCB Routing

Application of Machine Learning to Physical Design

Contact Info

Product

Resources

About