From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction

Vidya A. Chhabria; Wenjing Jiang; Andrew B. Kahng; Sachin S. Sapatnekar

doi:10.1145/3551901.3556475

From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction

Vidya A. Chhabria, Wenjing Jiang, Andrew B. Kahng, Sachin S. Sapatnekar

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Timing prediction and optimization are challenging in design stages prior to detailed routing (DR) due to the unavailability of routing information. Inaccurate timing prediction wastes design effort, hurts circuit performance, and may lead to design failure. This work focuses on timing prediction after clock tree synthesis and placement legalization, which is the earliest opportunity to time and optimize a "complete"netlist. The paper first documents that having "oracle knowledge"of the final post-DR parasitics enables post-global routing (GR) optimization to produce improved final timing outcomes. Machine learning (ML)-based models are proposed to bridge the gap between GR-based parasitic and timing estimation and post-DR results during post-GR optimization. These models show higher accuracy than GR-based timing estimation and, when used during post-GR optimization, show demonstrable improvements in post-DR circuit performance. Results on open 45nm and 130nm enablements using OpenROAD show efficient improvements in post-DR WNS and TNS metrics without increasing congestion.

Original language	English (US)
Title of host publication	MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD
Publisher	Association for Computing Machinery, Inc
Pages	7-14
Number of pages	8
ISBN (Electronic)	9781450394864
DOIs	https://doi.org/10.1145/3551901.3556475
State	Published - Sep 12 2022
Event	4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022 - Snowbird, United States Duration: Sep 12 2022 → Sep 13 2022

Publication series

Name	MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD

Conference

Conference	4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022
Country/Territory	United States
City	Snowbird
Period	9/12/22 → 9/13/22

Bibliographical note

Funding Information:
This work was supported in part by DARPA HR0011-18-2-0032 (The OpenROAD Project). The work of ABK is also supported in part by NSF CCF-2122665.

Publisher Copyright:
© 2022 ACM.

Keywords

machine learning
static timing analysis
timing optimization

Access

10.1145/3551901.3556475

OpenUrl availability

Full text

Cite this

Chhabria, V. A., Jiang, W., Kahng, A. B., & Sapatnekar, S. S. (2022). From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction. In MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD (pp. 7-14). (MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD). Association for Computing Machinery, Inc. https://doi.org/10.1145/3551901.3556475

From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction. / Chhabria, Vidya A.; Jiang, Wenjing; Kahng, Andrew B. et al.
MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. Association for Computing Machinery, Inc, 2022. p. 7-14 (MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chhabria, VA, Jiang, W, Kahng, AB & Sapatnekar, SS 2022, From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction. in MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD, Association for Computing Machinery, Inc, pp. 7-14, 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022, Snowbird, United States, 9/12/22. https://doi.org/10.1145/3551901.3556475

Chhabria VA, Jiang W, Kahng AB, Sapatnekar SS. From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction. In MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. Association for Computing Machinery, Inc. 2022. p. 7-14. (MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD). doi: 10.1145/3551901.3556475

Chhabria, Vidya A. ; Jiang, Wenjing ; Kahng, Andrew B. et al. / From Global Route to Detailed Route : ML for Fast and Accurate Wire Parasitics and Timing Prediction. MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD. Association for Computing Machinery, Inc, 2022. pp. 7-14 (MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD).

@inproceedings{e9ff85fee62f45a7aca02b4ac4413434,

title = "From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction",

abstract = "Timing prediction and optimization are challenging in design stages prior to detailed routing (DR) due to the unavailability of routing information. Inaccurate timing prediction wastes design effort, hurts circuit performance, and may lead to design failure. This work focuses on timing prediction after clock tree synthesis and placement legalization, which is the earliest opportunity to time and optimize a {"}complete{"}netlist. The paper first documents that having {"}oracle knowledge{"}of the final post-DR parasitics enables post-global routing (GR) optimization to produce improved final timing outcomes. Machine learning (ML)-based models are proposed to bridge the gap between GR-based parasitic and timing estimation and post-DR results during post-GR optimization. These models show higher accuracy than GR-based timing estimation and, when used during post-GR optimization, show demonstrable improvements in post-DR circuit performance. Results on open 45nm and 130nm enablements using OpenROAD show efficient improvements in post-DR WNS and TNS metrics without increasing congestion.",

keywords = "machine learning, static timing analysis, timing optimization",

author = "Chhabria, {Vidya A.} and Wenjing Jiang and Kahng, {Andrew B.} and Sapatnekar, {Sachin S.}",

note = "Funding Information: This work was supported in part by DARPA HR0011-18-2-0032 (The OpenROAD Project). The work of ABK is also supported in part by NSF CCF-2122665. 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 = "10.1145/3551901.3556475",

language = "English (US)",

series = "MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD",

publisher = "Association for Computing Machinery, Inc",

pages = "7--14",

booktitle = "MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD",

}

TY - GEN

T1 - From Global Route to Detailed Route

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

AU - Chhabria, Vidya A.

AU - Jiang, Wenjing

AU - Kahng, Andrew B.

AU - Sapatnekar, Sachin S.

N1 - Funding Information: This work was supported in part by DARPA HR0011-18-2-0032 (The OpenROAD Project). The work of ABK is also supported in part by NSF CCF-2122665. Publisher Copyright: © 2022 ACM.

PY - 2022/9/12

Y1 - 2022/9/12

N2 - Timing prediction and optimization are challenging in design stages prior to detailed routing (DR) due to the unavailability of routing information. Inaccurate timing prediction wastes design effort, hurts circuit performance, and may lead to design failure. This work focuses on timing prediction after clock tree synthesis and placement legalization, which is the earliest opportunity to time and optimize a "complete"netlist. The paper first documents that having "oracle knowledge"of the final post-DR parasitics enables post-global routing (GR) optimization to produce improved final timing outcomes. Machine learning (ML)-based models are proposed to bridge the gap between GR-based parasitic and timing estimation and post-DR results during post-GR optimization. These models show higher accuracy than GR-based timing estimation and, when used during post-GR optimization, show demonstrable improvements in post-DR circuit performance. Results on open 45nm and 130nm enablements using OpenROAD show efficient improvements in post-DR WNS and TNS metrics without increasing congestion.

AB - Timing prediction and optimization are challenging in design stages prior to detailed routing (DR) due to the unavailability of routing information. Inaccurate timing prediction wastes design effort, hurts circuit performance, and may lead to design failure. This work focuses on timing prediction after clock tree synthesis and placement legalization, which is the earliest opportunity to time and optimize a "complete"netlist. The paper first documents that having "oracle knowledge"of the final post-DR parasitics enables post-global routing (GR) optimization to produce improved final timing outcomes. Machine learning (ML)-based models are proposed to bridge the gap between GR-based parasitic and timing estimation and post-DR results during post-GR optimization. These models show higher accuracy than GR-based timing estimation and, when used during post-GR optimization, show demonstrable improvements in post-DR circuit performance. Results on open 45nm and 130nm enablements using OpenROAD show efficient improvements in post-DR WNS and TNS metrics without increasing congestion.

KW - machine learning

KW - static timing analysis

KW - timing optimization

UR - http://www.scopus.com/inward/record.url?scp=85139179239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85139179239&partnerID=8YFLogxK

U2 - 10.1145/3551901.3556475

DO - 10.1145/3551901.3556475

M3 - Conference contribution

AN - SCOPUS:85139179239

T3 - MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD

SP - 7

EP - 14

BT - MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD

PB - Association for Computing Machinery, Inc

Y2 - 12 September 2022 through 13 September 2022

ER -

From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this