A Multi-agent Generative Model for Collaborative Global Routing Refinement

Qijing Wang, Jinwei Liu, Martin D.F. Wong, Evangeline F.Y. Young

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

With minimal compromises on other metrics, eliminating overflow and lowering congestion level of global routing results as much as possible is a crucial topic for reducing violations and hotspots in subsequent design phases. Different from current common practices of using maze routing according to some explicit orders to sequentially re-route particular nets of interest, this paper proposes a collaborative refinement framework that can generate multiple paths simultaneously to enlarge the solution space based on a multi-agent generative model, serving as a flexible post-processing plug-in on existing global routing results to reduce congestion. Experimental results well reveal its effectiveness.

Original languageEnglish
Title of host publicationGLSVLSI 2024 - Proceedings of the Great Lakes Symposium on VLSI 2024
EditorsInna Partin-Vaisband, Srinivas Katkoori, Lu Peng, Boris Vaisband, Tooraj Nikoubin
PublisherAssociation for Computing Machinery (ACM)
Pages383-389
Number of pages7
ISBN (Print)9798400706059
DOIs
Publication statusPublished - 12 Jun 2024
Event34th Great Lakes Symposium on VLSI 2024, GLSVLSI 2024 - Clearwater, United States
Duration: 12 Jun 202414 Jun 2024
https://dl.acm.org/doi/proceedings/10.1145/3649476

Publication series

NameProceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

Conference

Conference34th Great Lakes Symposium on VLSI 2024, GLSVLSI 2024
Country/TerritoryUnited States
CityClearwater
Period12/06/2414/06/24
Internet address

Scopus Subject Areas

  • General Engineering

Fingerprint

Dive into the research topics of 'A Multi-agent Generative Model for Collaborative Global Routing Refinement'. Together they form a unique fingerprint.

Cite this