G-SpNN: GPU-Accelerated Passivity Enforcement for S-Parameter Modeling with Neural Networks

The increasing complexity of high-frequency circuits calls for efficient and accurate passive macromodeling techniques. Existing passivity enforcement methods, including those in commercial tools, often encounter convergence issues or compromise accuracy. The Domain-Alternated Optimization (DAO) fra...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autori: Zeng, Lijie, Sun, Jiatai, Wu, Xiao, Niu, Dan, Wang, Tianshi, Lin, Yibo, Ye, Zuochang, Jin, Zhou
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 22.06.2025
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The increasing complexity of high-frequency circuits calls for efficient and accurate passive macromodeling techniques. Existing passivity enforcement methods, including those in commercial tools, often encounter convergence issues or compromise accuracy. The Domain-Alternated Optimization (DAO) framework seeks to restore accuracy through an additional optimization step but is hampered by high memory consumption and slow convergence, particularly for large-scale problems. This paper presents G-SpNN, a novel GPU-accelerated framework that recasts the passivity-enforced macromodeling problem as a neural network training task. This approach significantly enhances both the speed and scalability of passivity enforcement. Experimental results show that G-SpNN achieves an average speedup of 7.63 \times in convergence compared to DAO, while reducing memory usage by two orders of magnitude. This enables G-SpNN to handle complex, high-port-count circuits with greater accuracy and efficiency, paving the way for robust high-frequency circuit simulations.
AbstractList The increasing complexity of high-frequency circuits calls for efficient and accurate passive macromodeling techniques. Existing passivity enforcement methods, including those in commercial tools, often encounter convergence issues or compromise accuracy. The Domain-Alternated Optimization (DAO) framework seeks to restore accuracy through an additional optimization step but is hampered by high memory consumption and slow convergence, particularly for large-scale problems. This paper presents G-SpNN, a novel GPU-accelerated framework that recasts the passivity-enforced macromodeling problem as a neural network training task. This approach significantly enhances both the speed and scalability of passivity enforcement. Experimental results show that G-SpNN achieves an average speedup of 7.63 \times in convergence compared to DAO, while reducing memory usage by two orders of magnitude. This enables G-SpNN to handle complex, high-port-count circuits with greater accuracy and efficiency, paving the way for robust high-frequency circuit simulations.
Author Wu, Xiao
Jin, Zhou
Wang, Tianshi
Ye, Zuochang
Lin, Yibo
Zeng, Lijie
Sun, Jiatai
Niu, Dan
Author_xml – sequence: 1
  givenname: Lijie
  surname: Zeng
  fullname: Zeng, Lijie
  email: z.jin@zju.edu.cn
  organization: China University of Petroleum-Beijing,SSSLab,China
– sequence: 2
  givenname: Jiatai
  surname: Sun
  fullname: Sun, Jiatai
  organization: China University of Petroleum-Beijing,SSSLab,China
– sequence: 3
  givenname: Xiao
  surname: Wu
  fullname: Wu, Xiao
  organization: Huada Empyrean Software Co. Ltd,China
– sequence: 4
  givenname: Dan
  surname: Niu
  fullname: Niu, Dan
  organization: Southeast University,School of Automation,China
– sequence: 5
  givenname: Tianshi
  surname: Wang
  fullname: Wang, Tianshi
  organization: HiSilicon Technologies Co. Ltd
– sequence: 6
  givenname: Yibo
  surname: Lin
  fullname: Lin, Yibo
  organization: Peking University,School of Integrated Circuits,Beijing
– sequence: 7
  givenname: Zuochang
  surname: Ye
  fullname: Ye, Zuochang
  organization: Tsinghua University,School of Integrated Circuits
– sequence: 8
  givenname: Zhou
  surname: Jin
  fullname: Jin, Zhou
  organization: Zhejiang University,College of Integrated Circuits,China
BookMark eNo1j01OwzAUhI0ECyi9AUK-gIvtF2OHXVRKQCohUumKRWUnL2CRn8oxVL09kYDVNzOLGc0FOe2HHgm5FnwhBE9v7rPlLZgkXUgu1RQJAK7lCZmnOjUAQnHgiTknbznb7IvijubllmVVhS0GG7GmpR1H_-3jka76ZggVdthHOim6YaUNtsOIgT4PNba-f6cHHz9ogV_BthPiYQif4yU5a2w74vyPM7J9WL0uH9n6JX9aZmtmhU4js7o2LlG1ndZraEAK0WgjG1SJM8JpYyVUXCvnjOUclKm4E5PnlXMSpIEZufrt9Yi42wff2XDc_X-GH8aDUJw
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133072
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133072
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-a7d8b45dacced3f3211f782fe54b81b78a23c075bb8a00358c0b10750cbb23283
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-a7d8b45dacced3f3211f782fe54b81b78a23c075bb8a00358c0b10750cbb23283
PageCount 7
ParticipantIDs ieee_primary_11133072
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.2950485
Snippet The increasing complexity of high-frequency circuits calls for efficient and accurate passive macromodeling techniques. Existing passivity enforcement methods,...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Convergence
GPU Acceleration
Graphics processing units
Integrated circuit modeling
Memory management
Neural Network
Neural networks
Optimization
Passivity Enforcement
S-Parameter Macromodeling
Scalability
Scattering parameters
Training
Title G-SpNN: GPU-Accelerated Passivity Enforcement for S-Parameter Modeling with Neural Networks
URI https://ieeexplore.ieee.org/document/11133072
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46PHhSceJvcvCarU2TJfU25jYPUgpzMPAw8qsgyDa2zr_f99JN8eDBU0MpBL6mfV9e3vc-Qh6AIgiR24ypIBMmUu6Z0VXKPAS_yjvYFDXd9V9UUejZLC93YvWohQkhxOKz0MFhPMv3S7fFVFkXbdFhTcIf91CpXiPW2ql-0yTvPvUHsJoEyk-47Owf_mWbEqPG6OSf852S9o_-jpbfkeWMHITFOXkbs8mqKB7puJyyvnMQL7DNg6cl8N9oAUGHqC1yMeFHYUQnrDRYfAXYUTQ9Q-k5xcwrxZ4c5gMusQh80ybT0fB18Mx21gjMwBdUM6O8tkJ6A7P5rMpgG1dBrK-CFBaIqNKGZw7YgLXa4GGhdolNkR04a4FD6eyCtBbLRbgklGttuXcSoMtEz0sje8A6qpD7JA8iMVekjcjMV033i_kelOs_7t-QY8Qfy6k4vyWter0Nd-TIfdbvm_V9fGdfSVyYMA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5SBT2pWPFtDl7T7maTbtZbqX2IdVloCwUPJa8FQdrSh7_fmbRVPHjwlBAWApNk58tkvvkIeQCIIERmEpZ6GTERc8e0KmPmwPmVzsKlaFNdv5_muRqPs2JLVg9cGO99SD7zNeyGt3w3s2sMldVRFh32JPxx96UQPNrQtba83zjK6k_NFuwngQQULmu7z38JpwS_0Tn-54wnpPrDwKPFt285JXt-ekbeumwwz_NH2i1GrGkteAws9OBoAQg4iEDQNrKLbAj5UejRASs0pl-B9SjKniH5nGLslWJVDv0BTUgDX1bJqNMetnpsK47ANJyhFdOpU0ZIp2E2l5QJXORK8Pall8IAFE2V5okFPGCM0vhcqGxkYsQH1hhAUSo5J5XpbOovCOVKGe6sBNMlouGklg3AHaXPXJR5EelLUkXLTOab-heTnVGu_hi_J4e94Wt_0n_OX67JEa4FJldxfkMqq8Xa35ID-7l6Xy7uwvp9AWO0m3c
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=G-SpNN%3A+GPU-Accelerated+Passivity+Enforcement+for+S-Parameter+Modeling+with+Neural+Networks&rft.au=Zeng%2C+Lijie&rft.au=Sun%2C+Jiatai&rft.au=Wu%2C+Xiao&rft.au=Niu%2C+Dan&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133072&rft.externalDocID=11133072