A Survey of Graph Neural Networks for Electronic Design Automation

Daniela Sanchez Lopera; Lorenzo Servadei; Gamze Naz Kiprit; Souvik Hazra; Robert Wille; Wolfgang Ecker

doi:10.1109/MLCAD52597.2021.9531070

A Survey of Graph Neural Networks for Electronic Design Automation

Daniela Sanchez Lopera, Lorenzo Servadei, Gamze Naz Kiprit, Souvik Hazra, Robert Wille, Wolfgang Ecker

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

63 Scopus citations

Abstract

Driven by Moore's law, the chip design complexity is steadily increasing. Electronic Design Automation (EDA) has been able to cope with the challenging very large-scale integration process, assuring scalability, reliability, and proper time-to-market. However, EDA approaches are time and resource-demanding, and they often do not guarantee optimal solutions. To alleviate these, Machine Learning (ML) has been incorporated into many stages of the design flow, such as in placement and routing. Many solutions employ Euclidean data and ML techniques without considering that many EDA objects are represented naturally as graphs. The trending Graph Neural Networks are an opportunity to solve EDA problems directly using graph structures for circuits, intermediate RTLs, and netlists. In this paper, we present a comprehensive review of the existing works linking the EDA flow for chip design and Graph Neural Networks.

Original language	English
Title of host publication	2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665431668
DOIs	https://doi.org/10.1109/MLCAD52597.2021.9531070
State	Published - 30 Aug 2021
Externally published	Yes
Event	3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021 - Raleigh, United States Duration: 30 Aug 2021 → 3 Sep 2021

Publication series

Name	2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021

Conference

Conference	3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021
Country/Territory	United States
City	Raleigh
Period	30/08/21 → 3/09/21

Keywords

Electronic Design Automation
Graph Neural Networks
Machine Learning
Register-Transfer Level
Very Large-scale Integration

Access to Document

10.1109/MLCAD52597.2021.9531070

Cite this

Lopera, D. S., Servadei, L., Kiprit, G. N., Hazra, S., Wille, R., & Ecker, W. (2021). A Survey of Graph Neural Networks for Electronic Design Automation. In 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021 (2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MLCAD52597.2021.9531070

@inproceedings{809964e091ee44eda17f9749f93c9749,

title = "A Survey of Graph Neural Networks for Electronic Design Automation",

abstract = "Driven by Moore's law, the chip design complexity is steadily increasing. Electronic Design Automation (EDA) has been able to cope with the challenging very large-scale integration process, assuring scalability, reliability, and proper time-to-market. However, EDA approaches are time and resource-demanding, and they often do not guarantee optimal solutions. To alleviate these, Machine Learning (ML) has been incorporated into many stages of the design flow, such as in placement and routing. Many solutions employ Euclidean data and ML techniques without considering that many EDA objects are represented naturally as graphs. The trending Graph Neural Networks are an opportunity to solve EDA problems directly using graph structures for circuits, intermediate RTLs, and netlists. In this paper, we present a comprehensive review of the existing works linking the EDA flow for chip design and Graph Neural Networks.",

keywords = "Electronic Design Automation, Graph Neural Networks, Machine Learning, Register-Transfer Level, Very Large-scale Integration",

author = "Lopera, {Daniela Sanchez} and Lorenzo Servadei and Kiprit, {Gamze Naz} and Souvik Hazra and Robert Wille and Wolfgang Ecker",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

month = aug,

day = "30",

doi = "10.1109/MLCAD52597.2021.9531070",

language = "English",

series = "2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021",

}

Lopera, DS, Servadei, L, Kiprit, GN, Hazra, S, Wille, R & Ecker, W 2021, A Survey of Graph Neural Networks for Electronic Design Automation. in 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021. 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021, Institute of Electrical and Electronics Engineers Inc., 3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021, Raleigh, United States, 30/08/21. https://doi.org/10.1109/MLCAD52597.2021.9531070

A Survey of Graph Neural Networks for Electronic Design Automation. / Lopera, Daniela Sanchez; Servadei, Lorenzo; Kiprit, Gamze Naz et al.
2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Survey of Graph Neural Networks for Electronic Design Automation

AU - Lopera, Daniela Sanchez

AU - Servadei, Lorenzo

AU - Kiprit, Gamze Naz

AU - Hazra, Souvik

AU - Wille, Robert

AU - Ecker, Wolfgang

PY - 2021/8/30

Y1 - 2021/8/30

N2 - Driven by Moore's law, the chip design complexity is steadily increasing. Electronic Design Automation (EDA) has been able to cope with the challenging very large-scale integration process, assuring scalability, reliability, and proper time-to-market. However, EDA approaches are time and resource-demanding, and they often do not guarantee optimal solutions. To alleviate these, Machine Learning (ML) has been incorporated into many stages of the design flow, such as in placement and routing. Many solutions employ Euclidean data and ML techniques without considering that many EDA objects are represented naturally as graphs. The trending Graph Neural Networks are an opportunity to solve EDA problems directly using graph structures for circuits, intermediate RTLs, and netlists. In this paper, we present a comprehensive review of the existing works linking the EDA flow for chip design and Graph Neural Networks.

AB - Driven by Moore's law, the chip design complexity is steadily increasing. Electronic Design Automation (EDA) has been able to cope with the challenging very large-scale integration process, assuring scalability, reliability, and proper time-to-market. However, EDA approaches are time and resource-demanding, and they often do not guarantee optimal solutions. To alleviate these, Machine Learning (ML) has been incorporated into many stages of the design flow, such as in placement and routing. Many solutions employ Euclidean data and ML techniques without considering that many EDA objects are represented naturally as graphs. The trending Graph Neural Networks are an opportunity to solve EDA problems directly using graph structures for circuits, intermediate RTLs, and netlists. In this paper, we present a comprehensive review of the existing works linking the EDA flow for chip design and Graph Neural Networks.

KW - Electronic Design Automation

KW - Graph Neural Networks

KW - Machine Learning

KW - Register-Transfer Level

KW - Very Large-scale Integration

UR - http://www.scopus.com/inward/record.url?scp=85115728472&partnerID=8YFLogxK

U2 - 10.1109/MLCAD52597.2021.9531070

DO - 10.1109/MLCAD52597.2021.9531070

M3 - Conference contribution

AN - SCOPUS:85115728472

T3 - 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021

BT - 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

A Survey of Graph Neural Networks for Electronic Design Automation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this