Proactive Power Regulation with Real-time Prediction and Fast Response Guardband for Fine-grained Dynamic Voltage Droop Mitigation on Digital SoCs

Xi Chen*, Jiaxiang Feng*, Aly Shoukry*, Xin Zhang, Raveesh Magod, Nachiket Desai, Jie Gu*

*Corresponding author for this work

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

Abstract

A proactive power regulation scheme for mitigating dynamic supply droop is proposed with a fully-integrated buck converter, a CPU core and a real-time machine learning (ML) engine. Combined with droop guardband circuits, the proactive scheme demonstrates up to 9.9% higher CPU frequency or 9.2% higher power efficiency compared with prior fast LDO scheme or conventional converters using a 65 nm test chip.

Original languageEnglish (US)
Title of host publication2023 IEEE Symposium on VLSI Technology and Circuits, VLSI Technology and Circuits 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784863488069
DOIs
StatePublished - 2023
Event2023 IEEE Symposium on VLSI Technology and Circuits, VLSI Technology and Circuits 2023 - Kyoto, Japan
Duration: Jun 11 2023Jun 16 2023

Publication series

NameDigest of Technical Papers - Symposium on VLSI Technology
Volume2023-June
ISSN (Print)0743-1562

Conference

Conference2023 IEEE Symposium on VLSI Technology and Circuits, VLSI Technology and Circuits 2023
Country/TerritoryJapan
CityKyoto
Period6/11/236/16/23

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Proactive Power Regulation with Real-time Prediction and Fast Response Guardband for Fine-grained Dynamic Voltage Droop Mitigation on Digital SoCs'. Together they form a unique fingerprint.

Cite this