Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration

Bangqi Fu; Lixin Liu; Martin D.F. Wong; Evangeline F.Y. Young

doi:10.1145/3676536.3676803

Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration

Bangqi Fu
, Lixin Liu
, Martin D.F. Wong
, Evangeline F.Y. Young

Office of the Provost

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

2 Citations (Scopus)

Abstract

Placement is a crucial step in the physical synthesis flow that significantly determines the timing performance of a design. In this paper, we propose a timing-driven global placement framework with a hybrid pin-based weighting scheme that considers both graph and path information and an optimization-friendly RC tree and wirelength model. A calibration method is proposed to further improve the incremental timing. Experiment results show over 37% improvement on TNS and 15% improvement on WNS, with 4.2% less HPWL on the ICCAD 2015 benchmark compared to the state-ofthe-art GPU-accelerated differentiable timing-driven placer, while also being around 2x faster.

Original language	English
Title of host publication	Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024
Place of Publication	New York
Publisher	IEEE
Number of pages	9
ISBN (Electronic)	9798400710773
DOIs	https://doi.org/10.1145/3676536.3676803
Publication status	Published - 9 Apr 2025
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

User-Defined Keywords

Global placement
GPU Acceleration
Physical design
Timing

Access to Document

10.1145/3676536.3676803

Cite this

Fu, B., Liu, L., Wong, M. D. F., & Young, E. F. Y. (2025). Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024 Article 22 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). IEEE. https://doi.org/10.1145/3676536.3676803

@inproceedings{cb28f264e88a4bb899f140dc886ce7d1,

title = "Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration",

abstract = "Placement is a crucial step in the physical synthesis flow that significantly determines the timing performance of a design. In this paper, we propose a timing-driven global placement framework with a hybrid pin-based weighting scheme that considers both graph and path information and an optimization-friendly RC tree and wirelength model. A calibration method is proposed to further improve the incremental timing. Experiment results show over 37\% improvement on TNS and 15\% improvement on WNS, with 4.2\% less HPWL on the ICCAD 2015 benchmark compared to the state-ofthe-art GPU-accelerated differentiable timing-driven placer, while also being around 2x faster.",

keywords = "Global placement, GPU Acceleration, Physical design, Timing",

author = "Bangqi Fu and Lixin Liu and Wong, \{Martin D.F.\} 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 = "2025",

month = apr,

day = "9",

doi = "10.1145/3676536.3676803",

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",

}

Fu, B, Liu, L, Wong, MDF & Young, EFY 2025, Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration. in Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024., 22, IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, IEEE, New York, 43rd International Conference on Computer-Aided Design, New York, New Jersey, United States, 27/10/24. https://doi.org/10.1145/3676536.3676803

Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration. / Fu, Bangqi; Liu, Lixin; Wong, Martin D.F. et al.
Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024. New York: IEEE, 2025. 22 (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 - Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration

AU - Fu, Bangqi

AU - Liu, Lixin

AU - Wong, Martin D.F.

AU - Young, Evangeline F.Y.

PY - 2025/4/9

Y1 - 2025/4/9

N2 - Placement is a crucial step in the physical synthesis flow that significantly determines the timing performance of a design. In this paper, we propose a timing-driven global placement framework with a hybrid pin-based weighting scheme that considers both graph and path information and an optimization-friendly RC tree and wirelength model. A calibration method is proposed to further improve the incremental timing. Experiment results show over 37% improvement on TNS and 15% improvement on WNS, with 4.2% less HPWL on the ICCAD 2015 benchmark compared to the state-ofthe-art GPU-accelerated differentiable timing-driven placer, while also being around 2x faster.

AB - Placement is a crucial step in the physical synthesis flow that significantly determines the timing performance of a design. In this paper, we propose a timing-driven global placement framework with a hybrid pin-based weighting scheme that considers both graph and path information and an optimization-friendly RC tree and wirelength model. A calibration method is proposed to further improve the incremental timing. Experiment results show over 37% improvement on TNS and 15% improvement on WNS, with 4.2% less HPWL on the ICCAD 2015 benchmark compared to the state-ofthe-art GPU-accelerated differentiable timing-driven placer, while also being around 2x faster.

KW - Global placement

KW - GPU Acceleration

KW - Physical design

KW - Timing

UR - https://www.scopus.com/pages/publications/105003639145

UR - https://dl.acm.org/doi/10.1145/3676536.3676803

U2 - 10.1145/3676536.3676803

DO - 10.1145/3676536.3676803

M3 - Conference proceeding

AN - SCOPUS:105003639145

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

CY - New York

T2 - 43rd International Conference on Computer-Aided Design

Y2 - 27 October 2024 through 31 October 2024

ER -

Fu B, Liu L, Wong MDF, Young EFY. Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024. New York: IEEE. 2025. 22. (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). doi: 10.1145/3676536.3676803

Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this