Identification of Efficient Clustering Techniques for Test Power Activity on the Layout

Dhotre, Harshad; Eggersglüβ, Stephan; Drechsler, Rolf

doi:10.1109/ats.2017.31

Cited by 8 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IR-aware timing Dhotre et al [10] 2017 Clustering Yes , IR prediction Lin et al [23] 2018 ANN No , , , , IR mitigation Fang et al [12] 2018 CNN, XGBoost No , , , , , IR mitigation PowerNet [35] Vectorless IR 2020 CNN Yes , , IR mitigation Mozaffari et al [28] Sillicon PSN 2019 ANN, CNN, NLP Yes , PSN prediction drawn from power grids without considering switching activities [1,3,29]. It is widely used to identify the weakness of a power delivery network (PDN) at an early design stage when switching vectors are not available [1,3].…”

Section: Linear Regression Nomentioning

confidence: 99%

“…Dhotre et al [10] assign all cell instances to multiple clusters by clustering algorithms like k-means or DBSCAN [11]. Each cell's power is approximated by its toggling activity.…”

Section: Dynamic Ir On Regionsmentioning

confidence: 99%

“…Dhotre et al [10] and Mozaffari et al [28] consider the localized power demand by estimating IR drop in regions or partitions. However, as introduced in Figure 1, the dynamic IR drop captures the worst transient IR drop.…”

Section: Dynamic Ir On Regionsmentioning

confidence: 99%

“…In recent years, machine learning (ML) applications in electronics design automation (EDA) have started to attract wide attention. They have enabled fast estimation on many important metrics for chip design, including timing [2], power [16,42], design rule violation [20,34,39], crosstalk [21], testability [26], lithography hotspots [37,40], clock tree's quality [25], placement solution [27], routing solution [43], and IR drop [10,12,15,23,28,30,35,36]. There have been many ML-based IR drop estimators targeting at various design stages with different emphasis.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast IR drop estimation with machine learning

Xie¹,

Li²,

et al. 2020

Proceedings of the 39th International Conference on Computer-Aided Design

View full text Add to dashboard Cite

IR drop constraint is a fundamental requirement enforced in almost all chip designs. However, its evaluation takes a long time, and mitigation techniques for fixing violations may require numerous iterations. As such, fast and accurate IR drop prediction becomes critical for reducing design turnaround time. Recently, machine learning (ML) techniques have been actively studied for fast IR drop estimation due to their promise and success in many fields. These studies target at various design stages with different emphasis, and accordingly, different ML algorithms are adopted and customized. This paper provides a review to the latest progress in ML-based IR drop estimation techniques. It also serves as a vehicle for discussing some general challenges faced by ML applications in electronics design automation (EDA), and demonstrating how to integrate ML models with conventional techniques for the better efficiency of EDA tools.

show abstract

Section: Linear Regression Nomentioning

confidence: 99%

“…Dhotre et al [10] assign all cell instances to multiple clusters by clustering algorithms like k-means or DBSCAN [11]. Each cell's power is approximated by its toggling activity.…”

Section: Dynamic Ir On Regionsmentioning

confidence: 99%

Section: Dynamic Ir On Regionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast IR drop estimation with machine learning

Xie¹,

Li²,

et al. 2020

Proceedings of the 39th International Conference on Computer-Aided Design

View full text Add to dashboard Cite

show abstract

“…Training a new model with new labels entails a long simulation and training time, which defeats the original purpose of fast estimation. The only exception is [2], which is based on unsupervised learning and does not learn any previous knowledge.…”

Section: Introductionmentioning

confidence: 99%

PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network

Xie

Ren

Khailany

et al. 2020

2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC)

View full text Add to dashboard Cite

IR drop is a fundamental constraint required by almost all chip designs. However, its evaluation usually takes a long time that hinders mitigation techniques for fixing its violations. In this work, we develop a fast dynamic IR drop estimation technique, named PowerNet, based on a convolutional neural network (CNN). It can handle both vector-based and vectorless IR analyses. Moreover, the proposed CNN model is general and transferable to different designs. This is in contrast to most existing machine learning (ML) approaches, where a model is applicable only to a specific design. Experimental results show that PowerNet outperforms the latest ML method by 9% in accuracy for the challenging case of vectorless IR drop and achieves a 30× speedup compared to an accurate IR drop commercial tool. Further, a mitigation tool guided by PowerNet reduces IR drop hotspots by 26% and 31% on two industrial designs, respectively, with very limited modification on their power grids.

show abstract

Vector-based Dynamic IR-drop Prediction Using Machine Learning

Chen

Liu

et al. 2022

2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)

View full text Add to dashboard Cite

Identification of Efficient Clustering Techniques for Test Power Activity on the Layout

Cited by 8 publications

References 23 publications

Fast IR drop estimation with machine learning

Fast IR drop estimation with machine learning

PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network

Vector-based Dynamic IR-drop Prediction Using Machine Learning

Contact Info

Product

Resources

About