Directed self-assembly (DSA) template pattern verification

Zigang Xiao, Yuelin Du, Haitong Tian, Martin D.F. Wong, He Yi, H. S.Philip Wong, Hongbo Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Directed Self-Assembly (DSA) is a promising technique for contacts/vias patterning, where groups of contacts/vias are patterned by guiding templates. As the templates are pat- terned by traditional lithography, their shapes may vary due to the process variations, which will ultimately affect the con- tacts/vias even for the same type of template. Due to the complexity of the DSA process, rigorous process simulation is unacceptably slow for full chip verication. This paper formulate several critical problems in DSA verication, and proposes a design automation methodology that consists of a data preparation and a model learning stage. We present a novel DSA model with Point Correspondence and Segment Distance features for robust learning. Following the method- ology, we propose an effective machine learning (ML) based method for DSA hotspot detection. The results of our initial experiments have already demonstrated the high-efficiency of our ML-based approach with over 85% detection accuracy. Compared to the minutes or even hours of simulation time in rigorous method, the methodology in this paper validates the research potential along this direction.

Original languageEnglish (US)
Title of host publicationDAC 2014 - 51st Design Automation Conference, Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479930173
DOIs
StatePublished - Jan 1 2014
Event51st Annual Design Automation Conference, DAC 2014 - San Francisco, CA, United States
Duration: Jun 2 2014Jun 5 2014

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

Other

Other51st Annual Design Automation Conference, DAC 2014
CountryUnited States
CitySan Francisco, CA
Period6/2/146/5/14

Fingerprint

Self-assembly
Self assembly
Template
Contact
Learning systems
Machine Learning
Design Automation
Process Variation
Methodology
Process Simulation
Patterning
Hot Spot
Lithography
High Efficiency
Preparation
Chip
Correspondence
Automation
Vary
Model

Keywords

  • Directed Self-Assembly
  • Hotspot
  • Machine Learning
  • Verication

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Modeling and Simulation

Cite this

Xiao, Z., Du, Y., Tian, H., Wong, M. D. F., Yi, H., Wong, H. S. P., & Zhang, H. (2014). Directed self-assembly (DSA) template pattern verification. In DAC 2014 - 51st Design Automation Conference, Conference Proceedings [2593125] (Proceedings - Design Automation Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/2593069.2593125

Directed self-assembly (DSA) template pattern verification. / Xiao, Zigang; Du, Yuelin; Tian, Haitong; Wong, Martin D.F.; Yi, He; Wong, H. S.Philip; Zhang, Hongbo.

DAC 2014 - 51st Design Automation Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. 2593125 (Proceedings - Design Automation Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xiao, Z, Du, Y, Tian, H, Wong, MDF, Yi, H, Wong, HSP & Zhang, H 2014, Directed self-assembly (DSA) template pattern verification. in DAC 2014 - 51st Design Automation Conference, Conference Proceedings., 2593125, Proceedings - Design Automation Conference, Institute of Electrical and Electronics Engineers Inc., 51st Annual Design Automation Conference, DAC 2014, San Francisco, CA, United States, 6/2/14. https://doi.org/10.1145/2593069.2593125
Xiao Z, Du Y, Tian H, Wong MDF, Yi H, Wong HSP et al. Directed self-assembly (DSA) template pattern verification. In DAC 2014 - 51st Design Automation Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. 2593125. (Proceedings - Design Automation Conference). https://doi.org/10.1145/2593069.2593125
Xiao, Zigang ; Du, Yuelin ; Tian, Haitong ; Wong, Martin D.F. ; Yi, He ; Wong, H. S.Philip ; Zhang, Hongbo. / Directed self-assembly (DSA) template pattern verification. DAC 2014 - 51st Design Automation Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. (Proceedings - Design Automation Conference).
@inproceedings{5ad4f136ea904dc58b5926a9b969de89,
title = "Directed self-assembly (DSA) template pattern verification",
abstract = "Directed Self-Assembly (DSA) is a promising technique for contacts/vias patterning, where groups of contacts/vias are patterned by guiding templates. As the templates are pat- terned by traditional lithography, their shapes may vary due to the process variations, which will ultimately affect the con- tacts/vias even for the same type of template. Due to the complexity of the DSA process, rigorous process simulation is unacceptably slow for full chip verication. This paper formulate several critical problems in DSA verication, and proposes a design automation methodology that consists of a data preparation and a model learning stage. We present a novel DSA model with Point Correspondence and Segment Distance features for robust learning. Following the method- ology, we propose an effective machine learning (ML) based method for DSA hotspot detection. The results of our initial experiments have already demonstrated the high-efficiency of our ML-based approach with over 85{\%} detection accuracy. Compared to the minutes or even hours of simulation time in rigorous method, the methodology in this paper validates the research potential along this direction.",
keywords = "Directed Self-Assembly, Hotspot, Machine Learning, Verication",
author = "Zigang Xiao and Yuelin Du and Haitong Tian and Wong, {Martin D.F.} and He Yi and Wong, {H. S.Philip} and Hongbo Zhang",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2593069.2593125",
language = "English (US)",
isbn = "9781479930173",
series = "Proceedings - Design Automation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "DAC 2014 - 51st Design Automation Conference, Conference Proceedings",
address = "United States",

}

TY - GEN

T1 - Directed self-assembly (DSA) template pattern verification

AU - Xiao, Zigang

AU - Du, Yuelin

AU - Tian, Haitong

AU - Wong, Martin D.F.

AU - Yi, He

AU - Wong, H. S.Philip

AU - Zhang, Hongbo

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Directed Self-Assembly (DSA) is a promising technique for contacts/vias patterning, where groups of contacts/vias are patterned by guiding templates. As the templates are pat- terned by traditional lithography, their shapes may vary due to the process variations, which will ultimately affect the con- tacts/vias even for the same type of template. Due to the complexity of the DSA process, rigorous process simulation is unacceptably slow for full chip verication. This paper formulate several critical problems in DSA verication, and proposes a design automation methodology that consists of a data preparation and a model learning stage. We present a novel DSA model with Point Correspondence and Segment Distance features for robust learning. Following the method- ology, we propose an effective machine learning (ML) based method for DSA hotspot detection. The results of our initial experiments have already demonstrated the high-efficiency of our ML-based approach with over 85% detection accuracy. Compared to the minutes or even hours of simulation time in rigorous method, the methodology in this paper validates the research potential along this direction.

AB - Directed Self-Assembly (DSA) is a promising technique for contacts/vias patterning, where groups of contacts/vias are patterned by guiding templates. As the templates are pat- terned by traditional lithography, their shapes may vary due to the process variations, which will ultimately affect the con- tacts/vias even for the same type of template. Due to the complexity of the DSA process, rigorous process simulation is unacceptably slow for full chip verication. This paper formulate several critical problems in DSA verication, and proposes a design automation methodology that consists of a data preparation and a model learning stage. We present a novel DSA model with Point Correspondence and Segment Distance features for robust learning. Following the method- ology, we propose an effective machine learning (ML) based method for DSA hotspot detection. The results of our initial experiments have already demonstrated the high-efficiency of our ML-based approach with over 85% detection accuracy. Compared to the minutes or even hours of simulation time in rigorous method, the methodology in this paper validates the research potential along this direction.

KW - Directed Self-Assembly

KW - Hotspot

KW - Machine Learning

KW - Verication

UR - http://www.scopus.com/inward/record.url?scp=84903190679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903190679&partnerID=8YFLogxK

U2 - 10.1145/2593069.2593125

DO - 10.1145/2593069.2593125

M3 - Conference contribution

AN - SCOPUS:84903190679

SN - 9781479930173

T3 - Proceedings - Design Automation Conference

BT - DAC 2014 - 51st Design Automation Conference, Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -