Efficient Design Rule Checking Script Generation via Key Information Extraction

Binwu Zhu; Xinyun Zhang; Yibo Lin; Bei Yu; Martin Wong

doi:10.1145/3551901.3556494

Efficient Design Rule Checking Script Generation via Key Information Extraction

Binwu Zhu, Xinyun Zhang, Yibo Lin, Bei Yu, Martin Wong

Office of the Provost

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

2 Citations (Scopus)

Abstract

Design rule checking (DRC) is a critical step in integrated circuit design. DRC requires formatted scripts as the input to the design rule checker. However, these scripts are always generated manually in the foundry, and such a generation process is extremely inefficient, especially when encountering a large number of design rules. To mitigate this issue, we first propose a deep learning-based key information extractor to automatically identify the essential arguments of the scripts from rules. Then, a script translator is designed to organize the extracted arguments into executable DRC scripts. In addition, we incorporate three specific design rule generation techniques to improve the performance of our extractor. Experimental results demonstrate that our proposed method can significantly reduce the cost of script generation and show remarkable superiority over other baselines.

Original language	English
Title of host publication	MLCAD 2022
Subtitle of host publication	Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD
Publisher	Association for Computing Machinery (ACM)
Pages	77-82
Number of pages	6
ISBN (Electronic)	9781450394864
DOIs	https://doi.org/10.1145/3551901.3556494
Publication status	Published - 12 Sept 2022
Event	4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022 - Snowbird, United States Duration: 12 Sept 2022 → 13 Sept 2022 https://web.archive.org/web/20220927074610/https://mlcad-workshop.org/ (Conference website ) https://web.archive.org/web/20220927081841/https://mlcad-workshop.org/program/ (Conference programme) https://dl.acm.org/doi/proceedings/10.1145/3551901 (Conference proceedings)

Publication series

Name	Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD

Conference

Conference	4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022
Country/Territory	United States
City	Snowbird
Period	12/09/22 → 13/09/22
Internet address	https://web.archive.org/web/20220927074610/https://mlcad-workshop.org/ (Conference website ) https://web.archive.org/web/20220927081841/https://mlcad-workshop.org/program/ (Conference programme) https://dl.acm.org/doi/proceedings/10.1145/3551901 (Conference proceedings)

Scopus Subject Areas

Artificial Intelligence
Computer Graphics and Computer-Aided Design
Hardware and Architecture

User-Defined Keywords

design rule checking
key information extraction
natural language processing

Access to Document

10.1145/3551901.3556494

Cite this

Zhu, B., Zhang, X., Lin, Y., Yu, B., & Wong, M. (2022). Efficient Design Rule Checking Script Generation via Key Information Extraction. In MLCAD 2022: Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD (pp. 77-82). (Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD). Association for Computing Machinery (ACM). https://doi.org/10.1145/3551901.3556494

@inproceedings{be87611ab01b45c3a662b4049a339e52,

title = "Efficient Design Rule Checking Script Generation via Key Information Extraction",

abstract = "Design rule checking (DRC) is a critical step in integrated circuit design. DRC requires formatted scripts as the input to the design rule checker. However, these scripts are always generated manually in the foundry, and such a generation process is extremely inefficient, especially when encountering a large number of design rules. To mitigate this issue, we first propose a deep learning-based key information extractor to automatically identify the essential arguments of the scripts from rules. Then, a script translator is designed to organize the extracted arguments into executable DRC scripts. In addition, we incorporate three specific design rule generation techniques to improve the performance of our extractor. Experimental results demonstrate that our proposed method can significantly reduce the cost of script generation and show remarkable superiority over other baselines.",

keywords = "design rule checking, key information extraction, natural language processing",

author = "Binwu Zhu and Xinyun Zhang and Yibo Lin and Bei Yu and Martin Wong",

note = "Funding Information: This work is supported in part by HiSilicon and The Research Grants Council of Hong Kong SAR (Project No. CUHK14208021). Publisher Copyright: {\textcopyright} 2022 ACM.; 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022 ; Conference date: 12-09-2022 Through 13-09-2022",

year = "2022",

month = sep,

day = "12",

doi = "10.1145/3551901.3556494",

language = "English",

series = "Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD",

publisher = "Association for Computing Machinery (ACM)",

pages = "77--82",

booktitle = "MLCAD 2022",

address = "United States",

url = "https://web.archive.org/web/20220927074610/https://mlcad-workshop.org/, https://web.archive.org/web/20220927081841/https://mlcad-workshop.org/program/, https://dl.acm.org/doi/proceedings/10.1145/3551901",

}

Zhu, B, Zhang, X, Lin, Y, Yu, B & Wong, M 2022, Efficient Design Rule Checking Script Generation via Key Information Extraction. in MLCAD 2022: Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD, Association for Computing Machinery (ACM), pp. 77-82, 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022, Snowbird, Utah, United States, 12/09/22. https://doi.org/10.1145/3551901.3556494

Efficient Design Rule Checking Script Generation via Key Information Extraction. / Zhu, Binwu; Zhang, Xinyun; Lin, Yibo et al.
MLCAD 2022: Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. Association for Computing Machinery (ACM), 2022. p. 77-82 (Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD).

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

TY - GEN

T1 - Efficient Design Rule Checking Script Generation via Key Information Extraction

AU - Zhu, Binwu

AU - Zhang, Xinyun

AU - Lin, Yibo

AU - Yu, Bei

AU - Wong, Martin

PY - 2022/9/12

Y1 - 2022/9/12

N2 - Design rule checking (DRC) is a critical step in integrated circuit design. DRC requires formatted scripts as the input to the design rule checker. However, these scripts are always generated manually in the foundry, and such a generation process is extremely inefficient, especially when encountering a large number of design rules. To mitigate this issue, we first propose a deep learning-based key information extractor to automatically identify the essential arguments of the scripts from rules. Then, a script translator is designed to organize the extracted arguments into executable DRC scripts. In addition, we incorporate three specific design rule generation techniques to improve the performance of our extractor. Experimental results demonstrate that our proposed method can significantly reduce the cost of script generation and show remarkable superiority over other baselines.

AB - Design rule checking (DRC) is a critical step in integrated circuit design. DRC requires formatted scripts as the input to the design rule checker. However, these scripts are always generated manually in the foundry, and such a generation process is extremely inefficient, especially when encountering a large number of design rules. To mitigate this issue, we first propose a deep learning-based key information extractor to automatically identify the essential arguments of the scripts from rules. Then, a script translator is designed to organize the extracted arguments into executable DRC scripts. In addition, we incorporate three specific design rule generation techniques to improve the performance of our extractor. Experimental results demonstrate that our proposed method can significantly reduce the cost of script generation and show remarkable superiority over other baselines.

KW - design rule checking

KW - key information extraction

KW - natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85139252407&partnerID=8YFLogxK

U2 - 10.1145/3551901.3556494

DO - 10.1145/3551901.3556494

M3 - Conference proceeding

AN - SCOPUS:85139252407

T3 - Proceedings of the ACM/IEEE Workshop on Machine Learning for CAD, MLCAD

SP - 77

EP - 82

BT - MLCAD 2022

PB - Association for Computing Machinery (ACM)

T2 - 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022

Y2 - 12 September 2022 through 13 September 2022

ER -

Efficient Design Rule Checking Script Generation via Key Information Extraction

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this