Deep Learning Framework for Placement

Yibo Lin (), Zizheng Guo () and Jing Mai ()
Additional contact information
Yibo Lin: Peking University
Zizheng Guo: Peking University
Jing Mai: Peking University

Chapter Chapter 9 in Machine Learning Applications in Electronic Design Automation, 2022, pp 221-245 from Springer

Abstract: Abstract Placement is a critical step in the modern backend design flow for integrated circuits (ICs). It needs to determine the locations of millions of instances and meanwhile optimizes for multiple objectives such as wirelength, routability, timing, and so on. These objectives cannot be accurately evaluated until routing and other succeeding stages are performed. As a result, modern placement algorithm follows an iterative procedure for these cross-layer objectives, which is time-consuming. Recent advances in machine learning and its acceleration bring opportunities to speed up placement algorithms from perspectives of both hardware acceleration and cross-layer modeling. This book chapter will survey recent studies on leveraging deep learning frameworks to accelerate kernel placement solvers as well as integrating machine learning models to speed up cross-layer optimization. We hope this line of studies can broaden the applications of machine learning techniques in IC design automation and stimulate more researches in related fields.

Keywords: Placement; Routability; Fence region; Deep learning; PyTorch (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-13074-8_9

Ordering information: This item can be ordered from
http://www.springer.com/9783031130748

DOI: 10.1007/978-3-031-13074-8_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().