Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning

Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Basso, Davide, Bortolussi, Luca, Videnovic-Misic, Mirjana, Habal, Husni
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Basso, Davide
Bortolussi, Luca
Videnovic-Misic, Mirjana
Habal, Husni
description Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constraints, as well as the high level of customization expected in analog design. This paper presents a novel automatic floorplanning algorithm based on reinforcement learning. It is augmented by a relational graph convolutional neural network model for encoding circuit features and positional constraints. The combination of these two machine learning methods enables knowledge transfer across different circuit designs with distinct topologies and constraints, increasing the \emph{generalization ability} of the solution. Applied to $6$ industrial circuits, our approach surpassed established floorplanning techniques in terms of speed, area and half-perimeter wire length. When integrated into a \emph{procedural generator} for layout completion, overall layout time was reduced by $67.3\%$ with a $8.3\%$ mean area reduction compared to manual layout.
doi_str_mv 10.48550/arxiv.2411.15212
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2411_15212</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2411_15212</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2411_152123</originalsourceid><addsrcrecordid>eNqFjsEKgkAURWfTIqoPaNX7gawxhbYhWkG0iPbysDc6NM7Ic9L6-yzat7pcOByOEHO5DqJtHK9XyE_dBWEkZSDjUIZjUaRKUeF1R7CzaFwJx6SFzDjHjUFrtS2h176CCxn02g0M7BmbCs704OGcyfeO7y2gvQ2QtspxQTVZDydC_gimYqTQtDT77UQssvSaHJbfnLxhXSO_8k9W_s3a_CfeN39DnA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning</title><source>arXiv.org</source><creator>Basso, Davide ; Bortolussi, Luca ; Videnovic-Misic, Mirjana ; Habal, Husni</creator><creatorcontrib>Basso, Davide ; Bortolussi, Luca ; Videnovic-Misic, Mirjana ; Habal, Husni</creatorcontrib><description>Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constraints, as well as the high level of customization expected in analog design. This paper presents a novel automatic floorplanning algorithm based on reinforcement learning. It is augmented by a relational graph convolutional neural network model for encoding circuit features and positional constraints. The combination of these two machine learning methods enables knowledge transfer across different circuit designs with distinct topologies and constraints, increasing the \emph{generalization ability} of the solution. Applied to $6$ industrial circuits, our approach surpassed established floorplanning techniques in terms of speed, area and half-perimeter wire length. When integrated into a \emph{procedural generator} for layout completion, overall layout time was reduced by $67.3\%$ with a $8.3\%$ mean area reduction compared to manual layout.</description><identifier>DOI: 10.48550/arxiv.2411.15212</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Computer Science - Systems and Control</subject><creationdate>2024-11</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2411.15212$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2411.15212$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Basso, Davide</creatorcontrib><creatorcontrib>Bortolussi, Luca</creatorcontrib><creatorcontrib>Videnovic-Misic, Mirjana</creatorcontrib><creatorcontrib>Habal, Husni</creatorcontrib><title>Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning</title><description>Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constraints, as well as the high level of customization expected in analog design. This paper presents a novel automatic floorplanning algorithm based on reinforcement learning. It is augmented by a relational graph convolutional neural network model for encoding circuit features and positional constraints. The combination of these two machine learning methods enables knowledge transfer across different circuit designs with distinct topologies and constraints, increasing the \emph{generalization ability} of the solution. Applied to $6$ industrial circuits, our approach surpassed established floorplanning techniques in terms of speed, area and half-perimeter wire length. When integrated into a \emph{procedural generator} for layout completion, overall layout time was reduced by $67.3\%$ with a $8.3\%$ mean area reduction compared to manual layout.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjsEKgkAURWfTIqoPaNX7gawxhbYhWkG0iPbysDc6NM7Ic9L6-yzat7pcOByOEHO5DqJtHK9XyE_dBWEkZSDjUIZjUaRKUeF1R7CzaFwJx6SFzDjHjUFrtS2h176CCxn02g0M7BmbCs704OGcyfeO7y2gvQ2QtspxQTVZDydC_gimYqTQtDT77UQssvSaHJbfnLxhXSO_8k9W_s3a_CfeN39DnA</recordid><startdate>20241120</startdate><enddate>20241120</enddate><creator>Basso, Davide</creator><creator>Bortolussi, Luca</creator><creator>Videnovic-Misic, Mirjana</creator><creator>Habal, Husni</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241120</creationdate><title>Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning</title><author>Basso, Davide ; Bortolussi, Luca ; Videnovic-Misic, Mirjana ; Habal, Husni</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2411_152123</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Basso, Davide</creatorcontrib><creatorcontrib>Bortolussi, Luca</creatorcontrib><creatorcontrib>Videnovic-Misic, Mirjana</creatorcontrib><creatorcontrib>Habal, Husni</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Basso, Davide</au><au>Bortolussi, Luca</au><au>Videnovic-Misic, Mirjana</au><au>Habal, Husni</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning</atitle><date>2024-11-20</date><risdate>2024</risdate><abstract>Analog integrated circuit (IC) floorplanning is typically a manual process with the placement of components (devices and modules) planned by a layout engineer. This process is further complicated by the interdependence of floorplanning and routing steps, numerous electric and layout-dependent constraints, as well as the high level of customization expected in analog design. This paper presents a novel automatic floorplanning algorithm based on reinforcement learning. It is augmented by a relational graph convolutional neural network model for encoding circuit features and positional constraints. The combination of these two machine learning methods enables knowledge transfer across different circuit designs with distinct topologies and constraints, increasing the \emph{generalization ability} of the solution. Applied to $6$ industrial circuits, our approach surpassed established floorplanning techniques in terms of speed, area and half-perimeter wire length. When integrated into a \emph{procedural generator} for layout completion, overall layout time was reduced by $67.3\%$ with a $8.3\%$ mean area reduction compared to manual layout.</abstract><doi>10.48550/arxiv.2411.15212</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2411.15212
ispartof
issn
language eng
recordid cdi_arxiv_primary_2411_15212
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
Computer Science - Systems and Control
title Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T07%3A46%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Effective%20Analog%20ICs%20Floorplanning%20with%20Relational%20Graph%20Neural%20Networks%20and%20Reinforcement%20Learning&rft.au=Basso,%20Davide&rft.date=2024-11-20&rft_id=info:doi/10.48550/arxiv.2411.15212&rft_dat=%3Carxiv_GOX%3E2411_15212%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true