MLCAD: A Survey of Research in Machine Learning for CAD Keynote Paper

Rapp, Martin; Amrouch, Hussam; Lin, Yibo; Yu, Bei; Pan, David Z.; Wolf, Marilyn; Henkel, Jörg

doi:10.1109/tcad.2021.3124762

Cited by 35 publications

(4 citation statements)

References 155 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning (ML) methods have been developed and achieved significant success in the field of computer-aided design (CAD) [25], [26]. ML transforms traditional analysis, modeling, and optimization problems into data-to-data mapping problems, providing efficient and accurate performance evaluation at various design stages [27]- [30].…”

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

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

show abstract

“…al. presented a comprehensive presentation of state of the art on ML for CAD at different abstract levels [27]. Interestingly, the paper also presents a meta-study of ML usage in CAD to capture the overall trend of suitable ML algorithms at various levels of the VLSI cycle.…”

Section: Reviews Ic Testingmentioning

confidence: 99%

AI/ML Algorithms and Applications in VLSI Design and Technology

Amuru¹,

Vudumula²,

K.³

et al. 2022

Preprint

View full text Add to dashboard Cite

An evident challenge ahead for the integrated circuit (IC) industry in the nanometer regime is the investigation and development of methods that can reduce the design complexity ensuing from growing process variations and curtail the turnaround time of chip manufacturing. Conventional methodologies employed for such tasks are largely manual; thus, time-consuming and resource-intensive. In contrast, the unique learning strategies of artificial intelligence (AI) provide numerous exciting automated approaches for handling complex and dataintensive tasks in very-large-scale integration (VLSI) design and testing. Employing AI and machine learning (ML) algorithms in VLSI design and manufacturing reduces the time and effort for understanding and processing the data within and across different abstraction levels via automated learning algorithms. It, in turn, improves the IC yield and reduces the manufacturing turnaround time. This paper thoroughly reviews the AI/ML automated approaches introduced in the past towards VLSI design and manufacturing. Moreover, we discuss the scope of AI/ML applications in the future at various abstraction levels to revolutionize the field of VLSI design, aiming for high-speed, highly intelligent, and efficient implementations.

show abstract

“…application characteristics nor their QoS targets, and only indirectly affect the temperature (via power or energy). ML provides powerful algorithms for system-level optimization [28]. Supervised learning can be used to train models that predict system properties like performance or power [29].…”

Section: Related Workmentioning

confidence: 99%

NPU-Accelerated Imitation Learning for Thermal Optimization of QoS-Constrained Heterogeneous Multi-Cores

Rapp¹,

Khdr²,

Krohmer³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Application migration and dynamic voltage and frequency scaling (DVFS) are indispensable means for fully exploiting the available potential in thermal optimization of a heterogeneous clustered multi-core processor under user-defined quality of service (QoS) targets. However, selecting the core to execute each application and the voltage/frequency (V/f) levels of each cluster is a complex problem because 1) the diverse characteristics and QoS targets of applications require different optimizations, and 2) per-cluster DVFS requires a global optimization considering all running applications. State-of-the-art resource management techniques for power or temperature minimization either rely on measurements that are often not available (such as power) or fail to consider all the dimensions of the problem (e.g., by using simplified analytical models). Imitation learning (IL) enables to use the optimality of an oracle policy, yet at low run-time overhead, by training a model from oracle demonstrations. We are the first to employ IL for temperature minimization under QoS targets. We tackle the complexity by training a neural network (NN) and accelerate the NN inference using a neural processing unit (NPU). While such NN accelerators are becoming increasingly widespread on end devices, they are so far only used to accelerate user applications. In contrast, we use an existing accelerator on a real platform to accelerate NN-based resource management. Our evaluation on a HiKey 970 board with an Arm big.LITTLE CPU and an NPU shows significant temperature reductions at a negligible run-time overhead, with unseen applications and different cooling than used for training.

show abstract

MLCAD: A Survey of Research in Machine Learning for CAD Keynote Paper

Cited by 35 publications

References 155 publications

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

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

AI/ML Algorithms and Applications in VLSI Design and Technology

NPU-Accelerated Imitation Learning for Thermal Optimization of QoS-Constrained Heterogeneous Multi-Cores

Contact Info

Product

Resources

About