InstantGR: Scalable GPU Parallelization for Global Routing

Shiju Lin; Liang Xiao; Jinwei Liu; Evangeline F.Y. Young

doi:10.1145/3676536.3676787

InstantGR: Scalable GPU Parallelization for Global Routing

Shiju Lin^*
, Liang Xiao
, Jinwei Liu
, Evangeline F.Y. Young

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

Global routing plays a crucial role in electronic design automation (EDA), serving not only as a means of optimizing routing but also as a tool for estimating routability in earlier stages such as logic synthesis and physical planning. However, these scenarios often require global routing on unpartitioned large designs, posing unique challenges in scalability, both in terms of runtime and design size. To tackle this issue, this paper introduces useful techniques for parallelizing large-scale global routing that can significantly increase parallelism and thus reduce runtime. Building upon these techniques, we have developed an open-source GPU-based global router that achieves the state-of-the-art results in the latest ISPD’24 Contest benchmarks, thereby showcasing the effectiveness of our methods. The source code of this work is available at https://github.com/cuhk-eda/InstantGR.

Original language	English
Title of host publication	Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	9798400710773
DOIs	https://doi.org/10.1145/3676536.3676787
Publication status	Published - 27 Oct 2024
Event	43rd International Conference on Computer-Aided Design - Newark Liberty International Airport Marriott, New York, United States Duration: 27 Oct 2024 → 31 Oct 2024 https://2024.iccad.com/ (Conference website) https://confcats-event-sessions.s3.amazonaws.com/iccad24/uploads/ICCAD_2024_Program_Final.pdf (Conference program) https://dl.acm.org/doi/proceedings/10.1145/3676536 (Conference proceeding)

Publication series

Name	IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
ISSN (Print)	1092-3152

Conference

Conference	43rd International Conference on Computer-Aided Design
Abbreviated title	ICCAD 2024
Country/Territory	United States
City	New York
Period	27/10/24 → 31/10/24
Internet address	https://2024.iccad.com/ (Conference website) https://confcats-event-sessions.s3.amazonaws.com/iccad24/uploads/ICCAD_2024_Program_Final.pdf (Conference program) https://dl.acm.org/doi/proceedings/10.1145/3676536 (Conference proceeding)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1145/3676536.3676787

Cite this

@inproceedings{00ef015ed5a243969060ed6883e51a6a,

title = "InstantGR: Scalable GPU Parallelization for Global Routing",

abstract = "Global routing plays a crucial role in electronic design automation (EDA), serving not only as a means of optimizing routing but also as a tool for estimating routability in earlier stages such as logic synthesis and physical planning. However, these scenarios often require global routing on unpartitioned large designs, posing unique challenges in scalability, both in terms of runtime and design size. To tackle this issue, this paper introduces useful techniques for parallelizing large-scale global routing that can significantly increase parallelism and thus reduce runtime. Building upon these techniques, we have developed an open-source GPU-based global router that achieves the state-of-the-art results in the latest ISPD{\textquoteright}24 Contest benchmarks, thereby showcasing the effectiveness of our methods. The source code of this work is available at https://github.com/cuhk-eda/InstantGR.",

author = "Shiju Lin and Liang Xiao and Jinwei Liu and Young, \{Evangeline F.Y.\}",

note = "Publisher Copyright: {\textcopyright} 2024 Copyright is held by the owner/author(s).; 43rd International Conference on Computer-Aided Design, ICCAD 2024 ; Conference date: 27-10-2024 Through 31-10-2024",

year = "2024",

month = oct,

day = "27",

doi = "10.1145/3676536.3676787",

language = "English",

series = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",

publisher = "IEEE",

booktitle = "Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024",

address = "United States",

url = "https://2024.iccad.com/, https://confcats-event-sessions.s3.amazonaws.com/iccad24/uploads/ICCAD\_2024\_Program\_Final.pdf, https://dl.acm.org/doi/proceedings/10.1145/3676536",

}

Lin, S, Xiao, L, Liu, J & Young, EFY 2024, InstantGR: Scalable GPU Parallelization for Global Routing. in Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024., 148, IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, IEEE, 43rd International Conference on Computer-Aided Design, New York, New Jersey, United States, 27/10/24. https://doi.org/10.1145/3676536.3676787

InstantGR: Scalable GPU Parallelization for Global Routing. / Lin, Shiju; Xiao, Liang; Liu, Jinwei et al.
Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024. IEEE, 2024. 148 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - InstantGR

T2 - 43rd International Conference on Computer-Aided Design

AU - Lin, Shiju

AU - Xiao, Liang

AU - Liu, Jinwei

AU - Young, Evangeline F.Y.

PY - 2024/10/27

Y1 - 2024/10/27

N2 - Global routing plays a crucial role in electronic design automation (EDA), serving not only as a means of optimizing routing but also as a tool for estimating routability in earlier stages such as logic synthesis and physical planning. However, these scenarios often require global routing on unpartitioned large designs, posing unique challenges in scalability, both in terms of runtime and design size. To tackle this issue, this paper introduces useful techniques for parallelizing large-scale global routing that can significantly increase parallelism and thus reduce runtime. Building upon these techniques, we have developed an open-source GPU-based global router that achieves the state-of-the-art results in the latest ISPD’24 Contest benchmarks, thereby showcasing the effectiveness of our methods. The source code of this work is available at https://github.com/cuhk-eda/InstantGR.

AB - Global routing plays a crucial role in electronic design automation (EDA), serving not only as a means of optimizing routing but also as a tool for estimating routability in earlier stages such as logic synthesis and physical planning. However, these scenarios often require global routing on unpartitioned large designs, posing unique challenges in scalability, both in terms of runtime and design size. To tackle this issue, this paper introduces useful techniques for parallelizing large-scale global routing that can significantly increase parallelism and thus reduce runtime. Building upon these techniques, we have developed an open-source GPU-based global router that achieves the state-of-the-art results in the latest ISPD’24 Contest benchmarks, thereby showcasing the effectiveness of our methods. The source code of this work is available at https://github.com/cuhk-eda/InstantGR.

UR - https://www.scopus.com/pages/publications/105003639743

U2 - 10.1145/3676536.3676787

DO - 10.1145/3676536.3676787

M3 - Conference proceeding

AN - SCOPUS:105003639743

T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

BT - Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024

PB - IEEE

Y2 - 27 October 2024 through 31 October 2024

ER -

InstantGR: Scalable GPU Parallelization for Global Routing

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this