Machine Learning-Based Pre-Routing Timing Prediction with Reduced Pessimism

Barboza, Erick Carvajal; Shukla, Nishchal; Chen, Yiran; Hu, Jiang

doi:10.1145/3316781.3317857

Cited by 71 publications

(27 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [22] random forests and regression trees were used to predict path-based slack from graph-based timing analysis. In [3] different non-convolutional models are used to predict signoff timing from the circuit features.…”

Section: Machine Learning In Physical Design Applicationsmentioning

confidence: 99%

“…In [11], a reinforcement learning approach is developed. This approach is based on AlphaGo Zero and models the routing problem [20] non-convolutional Timing analysis Han et al (2014) [14] non-convolutional Kahng et al (2015) [21] Kahng et al (2018) [22] Barboza et al (2019) [3] Routing Zhou et al (2015) [37] non-convolutional Chan et al (2017) [5] Tabrizi et al (2018) [32] convolutional Xie et al (2018) [ This work convolutional as a two-player game, where one player tries to route the circuit and the other one tries to remove the violations.…”

Section: Machine Learning In Physical Design Applicationsmentioning

confidence: 99%

“…Machine Learning (ML) models have been used in physical design for predicting different metrics, such as the result of clock tree synthesis (CTS) algorithms [20], circuit timing [14,21,22,3] and…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Netto

Fabre

Fontana

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Machine learning models have been used to improve the quality of different physical design steps, such as timing analysis, clock tree synthesis and routing. However, so far very few works have addressed the problem of algorithm selection during physical design, which can drastically reduce the computational effort of some steps. This work proposes a legalization algorithm selection framework using deep convolutional neural networks. To extract features, we used snapshots of circuit placements and used transfer learning to train the models using pre-trained weights of the Squeezenet architecture. By doing so we can greatly reduce the training time and required data even though the pre-trained weights come from a different problem. We performed extensive experimental analysis of machine learning models, providing details on how we chose the parameters of our model, such as convolutional neural network architecture, learning rate and number of epochs. We evaluated the proposed framework by training a model to select between different legalization algorithms according to cell displacement and wirelength variation. The trained models achieved an average F-score of 0.98 when predicting cell displacement and 0.83 when predicting wirelength variation. When integrated into the physical design flow, the cell displacement model achieved the best results on 15 out of 16 designs, while the wirelength variation model achieved that for 10 out of 16 designs, being better than any individual legalization algorithm. Finally, using the proposed machine learning model for algorithm selection resulted in a speedup of up to 10x compared to running all the algorithms separately.

show abstract

Section: Machine Learning In Physical Design Applicationsmentioning

confidence: 99%

Section: Machine Learning In Physical Design Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Netto

Fabre

Fontana

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…However, this approach results in an over-design that subsequently wastes optimization time. To overcome this issue, Barboza et al [110] proposed an ML-based pre-routing timing prediction that mostly avoids pessimism by using the RF algorithm. They compared this algorithm with lasso regression, ANN regression, and commercial-based estimation tools, and their experimental results show that the proposed pre-routing prediction achieves accuracy near the postrouting sign-off analysis.…”

Section: Rf As a Routing Algorithmmentioning

confidence: 99%

“…However, with the superiority of MLbased routing, the computational load must also be considered if the technology is to be implemented in a real-world network environment. Several studies, such as those in [110] and [111], argue that collecting data for training the ML algorithm is not an easy task in practice. Furthermore, some of these studies have been based on assumptions that are not realistic enough to be implemented in a network.…”

Section: Figure 20 Limitation Of Conventional Routing Protocolsmentioning

confidence: 99%

Applications of Machine Learning in Networking: A Survey of Current Issues and Future Challenges

et al. 2021

View full text Add to dashboard Cite

Communication networks are expanding rapidly and becoming increasingly complex. As a consequence, the conventional rule-based algorithms or protocols may no longer perform at their best efficiencies in these networks. Machine learning (ML) has recently been applied to solve complex problems in many fields, including finance, health care, and business. ML algorithms can offer computational models that can solve complex communication network problems and consequently improve performance. This paper reviews the recent trends in the application of ML models in communication networks for prediction, intrusion detection, route and path assignment, Quality of Service improvement, and resource management. A review of the recent literature reveals extensive opportunities for researchers to exploit the advantages of ML in solving complex performance issues in a network, especially with the advancement of softwaredefined networks and 5G.

show abstract

A systematic literature review of machine learning applications in IoT

Gherbi

Senouci

Harbi

et al. 2023

Int J Communication

View full text Add to dashboard Cite

The Internet of Things (IoT) is a network of interconnected smart objects having capabilities that collectively form an ecosystem and enable the delivery of smart services to users. The IoT is providing several benefits into people's lives through the environment. The various applications that are run in the IoT environment offer facilities and services. The most crucial services provided by IoT applications are quick decision for efficient management. Recently, machine learning (ML) techniques have been successfully used to maximize the potential of IoT systems. This paper presents a systematic review of the literature on the integration of ML methods in the IoT. The challenges of IoT systems are split into two categories: fundamental operation and performance. We also look at how ML is assisting in the resolution of fundamental system operation challenges such as security, big data, clustering, routing, and data aggregation.

show abstract

Machine Learning-Based Pre-Routing Timing Prediction with Reduced Pessimism

Cited by 71 publications

References 8 publications

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Applications of Machine Learning in Networking: A Survey of Current Issues and Future Challenges

A systematic literature review of machine learning applications in IoT

Contact Info

Product

Resources

About