Abstract

A workload-aware low-power neuromorphic controller for dynamic voltage and frequency scaling (DVFS) in very large scale integration (VLSI)systems is presented. The neuromorphic controller predicts future workload values and preemptively regulates supply voltage and frequency based on past workload profile. Our specific contributions include: 1) implementation of a digital and analog version of the controller in 45 nm CMOS technology, resulting in a 3% performance hit with a power overhead in the range of 10-150 μW from the controller circuit; 2) higher prediction accuracy compared to a software based OS-governed DVFS scheme, reducing wasted power and improving error margins; and 3) power savings of up to 52% and improvement of up to 15% compared to the OS-based scheme. The digital design has minimal power overhead and is more reconfigurable, while analog design is better suited for nonlinear and complex computational tasks.

Original languageEnglish (US)
Article number6035994
Pages (from-to)381-390
Number of pages10
JournalIEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume1
Issue number3
DOIs
StatePublished - Sep 2011

Fingerprint

Controllers
VLSI circuits
Networks (circuits)
Electric potential
Voltage scaling
Dynamic frequency scaling

Keywords

  • Adaptive
  • neuromorphic
  • power management
  • simulation
  • very large scale integration (VLSI)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Workload-aware neuromorphic design of the power controller. / Sinha, Saurabh; Suh, Jounghyuk; Bakkaloglu, Bertan; Cao, Yu.

In: IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Vol. 1, No. 3, 6035994, 09.2011, p. 381-390.

Research output: Contribution to journalArticle

@article{92fe4c7fba3f436f966965edc86a5e57,
title = "Workload-aware neuromorphic design of the power controller",
abstract = "A workload-aware low-power neuromorphic controller for dynamic voltage and frequency scaling (DVFS) in very large scale integration (VLSI)systems is presented. The neuromorphic controller predicts future workload values and preemptively regulates supply voltage and frequency based on past workload profile. Our specific contributions include: 1) implementation of a digital and analog version of the controller in 45 nm CMOS technology, resulting in a 3{\%} performance hit with a power overhead in the range of 10-150 μW from the controller circuit; 2) higher prediction accuracy compared to a software based OS-governed DVFS scheme, reducing wasted power and improving error margins; and 3) power savings of up to 52{\%} and improvement of up to 15{\%} compared to the OS-based scheme. The digital design has minimal power overhead and is more reconfigurable, while analog design is better suited for nonlinear and complex computational tasks.",
keywords = "Adaptive, neuromorphic, power management, simulation, very large scale integration (VLSI)",
author = "Saurabh Sinha and Jounghyuk Suh and Bertan Bakkaloglu and Yu Cao",
year = "2011",
month = "9",
doi = "10.1109/JETCAS.2011.2165233",
language = "English (US)",
volume = "1",
pages = "381--390",
journal = "IEEE Journal on Emerging and Selected Topics in Circuits and Systems",
issn = "2156-3357",
publisher = "IEEE Circuits and Systems Society",
number = "3",

}

TY - JOUR

T1 - Workload-aware neuromorphic design of the power controller

AU - Sinha, Saurabh

AU - Suh, Jounghyuk

AU - Bakkaloglu, Bertan

AU - Cao, Yu

PY - 2011/9

Y1 - 2011/9

N2 - A workload-aware low-power neuromorphic controller for dynamic voltage and frequency scaling (DVFS) in very large scale integration (VLSI)systems is presented. The neuromorphic controller predicts future workload values and preemptively regulates supply voltage and frequency based on past workload profile. Our specific contributions include: 1) implementation of a digital and analog version of the controller in 45 nm CMOS technology, resulting in a 3% performance hit with a power overhead in the range of 10-150 μW from the controller circuit; 2) higher prediction accuracy compared to a software based OS-governed DVFS scheme, reducing wasted power and improving error margins; and 3) power savings of up to 52% and improvement of up to 15% compared to the OS-based scheme. The digital design has minimal power overhead and is more reconfigurable, while analog design is better suited for nonlinear and complex computational tasks.

AB - A workload-aware low-power neuromorphic controller for dynamic voltage and frequency scaling (DVFS) in very large scale integration (VLSI)systems is presented. The neuromorphic controller predicts future workload values and preemptively regulates supply voltage and frequency based on past workload profile. Our specific contributions include: 1) implementation of a digital and analog version of the controller in 45 nm CMOS technology, resulting in a 3% performance hit with a power overhead in the range of 10-150 μW from the controller circuit; 2) higher prediction accuracy compared to a software based OS-governed DVFS scheme, reducing wasted power and improving error margins; and 3) power savings of up to 52% and improvement of up to 15% compared to the OS-based scheme. The digital design has minimal power overhead and is more reconfigurable, while analog design is better suited for nonlinear and complex computational tasks.

KW - Adaptive

KW - neuromorphic

KW - power management

KW - simulation

KW - very large scale integration (VLSI)

UR - http://www.scopus.com/inward/record.url?scp=81255171387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255171387&partnerID=8YFLogxK

U2 - 10.1109/JETCAS.2011.2165233

DO - 10.1109/JETCAS.2011.2165233

M3 - Article

AN - SCOPUS:81255171387

VL - 1

SP - 381

EP - 390

JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

SN - 2156-3357

IS - 3

M1 - 6035994

ER -