Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning

Zhiyuan Zhou; Syrine Belakaria; Aryan Deshwal; Wookpyo Hong; Janardhan Rao Doppa; Partha Pratim Pande; Deukhyoun Heo

doi:10.23919/DATE48585.2020.9116413

Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning

Zhiyuan Zhou
, Syrine Belakaria
, Aryan Deshwal
, Wookpyo Hong
, Janardhan Rao Doppa
, Partha Pratim Pande
, Deukhyoun Heo

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

16 Scopus citations

Abstract

Efficiency of power management system (PMS) is one of the key performance metrics for highly integrated system on chips (SoCs). Towards the goal of improving power efficiency of SoCs, we make two key technical contributions in this paper. First, we develop a multi-output switched-capacitor voltage regulator (SCVR) with a new flying capacitor crossing technique (FCCT) and cloud-capacitor method. Second, to optimize the design parameters of SCVR, we introduce a novel machine¬learning (ML)-inspired optimization framework to reduce the number of expensive design simulations. Simulation shows that power loss of the multi-output SCVR with FCCT is reduced by more than 40% compared to conventional multiple single-output SCVRs. Our ML-based design optimization framework is able to achieve more than 90% reduction in the number of simulations needed to uncover optimized circuit parameters of the proposed SCVR.

Original language	English (US)
Title of host publication	Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
Editors	Giorgio Di Natale, Cristiana Bolchini, Elena-Ioana Vatajelu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	502-507
Number of pages	6
ISBN (Electronic)	9783981926347
DOIs	https://doi.org/10.23919/DATE48585.2020.9116413
State	Published - Mar 2020
Externally published	Yes
Event	2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 - Grenoble, France Duration: Mar 9 2020 → Mar 13 2020

Publication series

Name	Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

Conference

Conference	2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
Country/Territory	France
City	Grenoble
Period	3/9/20 → 3/13/20

Bibliographical note

Publisher Copyright:
© 2020 EDAA.

Keywords

Electronic design automation
Machine Learning
Multi-objective Optimization
Power management system

Publisher link

10.23919/DATE48585.2020.9116413

Find It

Find It at U of M Libraries

Cite this

Zhou, Z., Belakaria, S., Deshwal, A., Hong, W., Doppa, J. R., Pratim Pande, P., & Heo, D. (2020). Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning. In G. Di Natale, C. Bolchini, & E.-I. Vatajelu (Eds.), Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 (pp. 502-507). Article 9116413 (Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/DATE48585.2020.9116413

Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning. / Zhou, Zhiyuan; Belakaria, Syrine; Deshwal, Aryan et al.
Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. ed. / Giorgio Di Natale; Cristiana Bolchini; Elena-Ioana Vatajelu. Institute of Electrical and Electronics Engineers Inc., 2020. p. 502-507 9116413 (Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020).

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

Zhou, Z, Belakaria, S, Deshwal, A, Hong, W, Doppa, JR, Pratim Pande, P & Heo, D 2020, Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning. in G Di Natale, C Bolchini & E-I Vatajelu (eds), Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020., 9116413, Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020, Institute of Electrical and Electronics Engineers Inc., pp. 502-507, 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020, Grenoble, France, 3/9/20. https://doi.org/10.23919/DATE48585.2020.9116413

Zhou Z, Belakaria S, Deshwal A, Hong W, Doppa JR, Pratim Pande P et al. Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning. In Di Natale G, Bolchini C, Vatajelu EI, editors, Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 502-507. 9116413. (Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020). doi: 10.23919/DATE48585.2020.9116413

Zhou, Zhiyuan ; Belakaria, Syrine ; Deshwal, Aryan et al. / Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning. Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. editor / Giorgio Di Natale ; Cristiana Bolchini ; Elena-Ioana Vatajelu. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 502-507 (Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020).

@inproceedings{1b672f693126445ca441e8b91feffc3c,

title = "Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning",

abstract = "Efficiency of power management system (PMS) is one of the key performance metrics for highly integrated system on chips (SoCs). Towards the goal of improving power efficiency of SoCs, we make two key technical contributions in this paper. First, we develop a multi-output switched-capacitor voltage regulator (SCVR) with a new flying capacitor crossing technique (FCCT) and cloud-capacitor method. Second, to optimize the design parameters of SCVR, we introduce a novel machine¬learning (ML)-inspired optimization framework to reduce the number of expensive design simulations. Simulation shows that power loss of the multi-output SCVR with FCCT is reduced by more than 40\% compared to conventional multiple single-output SCVRs. Our ML-based design optimization framework is able to achieve more than 90\% reduction in the number of simulations needed to uncover optimized circuit parameters of the proposed SCVR.",

keywords = "Electronic design automation, Machine Learning, Multi-objective Optimization, Power management system",

author = "Zhiyuan Zhou and Syrine Belakaria and Aryan Deshwal and Wookpyo Hong and Doppa, \{Janardhan Rao\} and \{Pratim Pande\}, Partha and Deukhyoun Heo",

note = "Publisher Copyright: {\textcopyright} 2020 EDAA.; 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 ; Conference date: 09-03-2020 Through 13-03-2020",

year = "2020",

month = mar,

doi = "10.23919/DATE48585.2020.9116413",

language = "English (US)",

series = "Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "502--507",

editor = "\{Di Natale\}, Giorgio and Cristiana Bolchini and Elena-Ioana Vatajelu",

booktitle = "Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020",

}

TY - GEN

T1 - Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning

AU - Zhou, Zhiyuan

AU - Belakaria, Syrine

AU - Deshwal, Aryan

AU - Hong, Wookpyo

AU - Doppa, Janardhan Rao

AU - Pratim Pande, Partha

AU - Heo, Deukhyoun

PY - 2020/3

Y1 - 2020/3

N2 - Efficiency of power management system (PMS) is one of the key performance metrics for highly integrated system on chips (SoCs). Towards the goal of improving power efficiency of SoCs, we make two key technical contributions in this paper. First, we develop a multi-output switched-capacitor voltage regulator (SCVR) with a new flying capacitor crossing technique (FCCT) and cloud-capacitor method. Second, to optimize the design parameters of SCVR, we introduce a novel machine¬learning (ML)-inspired optimization framework to reduce the number of expensive design simulations. Simulation shows that power loss of the multi-output SCVR with FCCT is reduced by more than 40% compared to conventional multiple single-output SCVRs. Our ML-based design optimization framework is able to achieve more than 90% reduction in the number of simulations needed to uncover optimized circuit parameters of the proposed SCVR.

AB - Efficiency of power management system (PMS) is one of the key performance metrics for highly integrated system on chips (SoCs). Towards the goal of improving power efficiency of SoCs, we make two key technical contributions in this paper. First, we develop a multi-output switched-capacitor voltage regulator (SCVR) with a new flying capacitor crossing technique (FCCT) and cloud-capacitor method. Second, to optimize the design parameters of SCVR, we introduce a novel machine¬learning (ML)-inspired optimization framework to reduce the number of expensive design simulations. Simulation shows that power loss of the multi-output SCVR with FCCT is reduced by more than 40% compared to conventional multiple single-output SCVRs. Our ML-based design optimization framework is able to achieve more than 90% reduction in the number of simulations needed to uncover optimized circuit parameters of the proposed SCVR.

KW - Electronic design automation

KW - Machine Learning

KW - Multi-objective Optimization

KW - Power management system

UR - https://www.scopus.com/pages/publications/85087406022

UR - https://www.scopus.com/pages/publications/85087406022#tab=citedBy

U2 - 10.23919/DATE48585.2020.9116413

DO - 10.23919/DATE48585.2020.9116413

M3 - Conference contribution

AN - SCOPUS:85087406022

T3 - Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

SP - 502

EP - 507

BT - Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

A2 - Di Natale, Giorgio

A2 - Bolchini, Cristiana

A2 - Vatajelu, Elena-Ioana

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

Y2 - 9 March 2020 through 13 March 2020

ER -

Design of Multi-Output Switched-Capacitor Voltage Regulator via Machine Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this