Deep Learning for Analyzing Power Delivery Networks and Thermal Networks

Vidya A. Chhabria; Sachin S. Sapatnekar

doi:10.1007/978-3-031-13074-8_5

Deep Learning for Analyzing Power Delivery Networks and Thermal Networks

Vidya A. Chhabria, Sachin S. Sapatnekar

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

The design of on-chip power delivery networks (PDNs) and thermal networks involves the solution of large systems of linear equations. This computational intensive step is a critical part of the IC design process and has been a significant computational bottleneck for electronic design automation. Machine learning techniques can efficiently solve these problems by performing fast and accurate analysis and optimization. This chapter presents ML methods in this domain: for analyzing PDNs for IR drop and electromigration, for analyzing thermal networks for temperature, for optimizing PDNs by mapping the problem to a classification problem, and for generating PDN benchmarks.

Original language	English (US)
Title of host publication	Machine Learning Applications in Electronic Design Automation
Publisher	Springer Singapore
Pages	115-150
Number of pages	36
ISBN (Electronic)	9783031130748
ISBN (Print)	9783031130731
DOIs	https://doi.org/10.1007/978-3-031-13074-8_5
State	Published - Jan 1 2023

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Keywords

Convolutional neural networks (CNN)
Electromigration hotspot classification
IR drop analysis
Long short-term memories (LSTMs)
Power delivery network (PDN)
Thermal analysis
U-Nets

Access

10.1007/978-3-031-13074-8_5

OpenUrl availability

Full text

Cite this

@inbook{ac6e51c99a93498cad6a40ff8556516a,

title = "Deep Learning for Analyzing Power Delivery Networks and Thermal Networks",

abstract = "The design of on-chip power delivery networks (PDNs) and thermal networks involves the solution of large systems of linear equations. This computational intensive step is a critical part of the IC design process and has been a significant computational bottleneck for electronic design automation. Machine learning techniques can efficiently solve these problems by performing fast and accurate analysis and optimization. This chapter presents ML methods in this domain: for analyzing PDNs for IR drop and electromigration, for analyzing thermal networks for temperature, for optimizing PDNs by mapping the problem to a classification problem, and for generating PDN benchmarks.",

keywords = "Convolutional neural networks (CNN), Electromigration hotspot classification, IR drop analysis, Long short-term memories (LSTMs), Power delivery network (PDN), Thermal analysis, U-Nets",

author = "Chhabria, {Vidya A.} and Sapatnekar, {Sachin S.}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.",

year = "2023",

month = jan,

day = "1",

doi = "10.1007/978-3-031-13074-8_5",

language = "English (US)",

isbn = "9783031130731",

pages = "115--150",

booktitle = "Machine Learning Applications in Electronic Design Automation",

publisher = "Springer Singapore",

}

TY - CHAP

T1 - Deep Learning for Analyzing Power Delivery Networks and Thermal Networks

AU - Chhabria, Vidya A.

AU - Sapatnekar, Sachin S.

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - The design of on-chip power delivery networks (PDNs) and thermal networks involves the solution of large systems of linear equations. This computational intensive step is a critical part of the IC design process and has been a significant computational bottleneck for electronic design automation. Machine learning techniques can efficiently solve these problems by performing fast and accurate analysis and optimization. This chapter presents ML methods in this domain: for analyzing PDNs for IR drop and electromigration, for analyzing thermal networks for temperature, for optimizing PDNs by mapping the problem to a classification problem, and for generating PDN benchmarks.

AB - The design of on-chip power delivery networks (PDNs) and thermal networks involves the solution of large systems of linear equations. This computational intensive step is a critical part of the IC design process and has been a significant computational bottleneck for electronic design automation. Machine learning techniques can efficiently solve these problems by performing fast and accurate analysis and optimization. This chapter presents ML methods in this domain: for analyzing PDNs for IR drop and electromigration, for analyzing thermal networks for temperature, for optimizing PDNs by mapping the problem to a classification problem, and for generating PDN benchmarks.

KW - Convolutional neural networks (CNN)

KW - Electromigration hotspot classification

KW - IR drop analysis

KW - Long short-term memories (LSTMs)

KW - Power delivery network (PDN)

KW - Thermal analysis

KW - U-Nets

UR - http://www.scopus.com/inward/record.url?scp=85159383783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85159383783&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-13074-8_5

DO - 10.1007/978-3-031-13074-8_5

M3 - Chapter

AN - SCOPUS:85159383783

SN - 9783031130731

SP - 115

EP - 150

BT - Machine Learning Applications in Electronic Design Automation

PB - Springer Singapore

ER -

Deep Learning for Analyzing Power Delivery Networks and Thermal Networks

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this