A self-tuning design methodology for power-efficient multi-core systems

Jin Sun, Rui Zheng, Jyothi Velamala, Yu Cao, Roman L Lysecky, Karthik Shankar, Meiling Wang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This article aims to achieve computational reliability and energy efficiency through codevelopment of algorithms, device, and circuit designs for application-specific, reconfigurable architectures. The new methodology characterizes aging-switching activity and aging-supply voltage relationships that are applicable for minimizing power consumption and task execution efficiency in order to achieve low bit energy ratio (BER). In addition, a new dynamic management algorithm (DMA) is proposed to alleviate device degradation and to extend system lifespan. In contrast to traditional workload balancing schemes in which cores are regarded as homogeneous, the new algorithm ranks cores as 'highly competitive,' 'less competitive,' and 'not competitive' according to their various competitiveness. Core competitiveness is evaluated based upon their reliability, temperature, and timing requirements. Consequently, 'competitive' cores will take charge of the majority of the tasks at relatively high voltage/frequency without violating power and timing budgets, while 'not competitive' cores will have light workloads to ensure their reliability. The new approach combines intrinsic device characteristics (aging-switching activity and aging-supply voltage curves) into an integrated framework to achieve high reliability and low energy level with graceful degradation of system performance. Experimental results show that the proposed method has achieved up to 20% power reduction, with about 4% performance degradation (in terms of accomplished workload and system throughput), compared with traditional workload balancing methods. The new method also improves system mean-time-to-failure (MTTF) by up to 25%.

Original languageEnglish (US)
Article number4
JournalACM Transactions on Design Automation of Electronic Systems
Volume18
Issue number1
DOIs
StatePublished - Dec 2012

Fingerprint

Tuning
Aging of materials
Degradation
Electric potential
Reconfigurable architectures
Electron energy levels
Energy efficiency
Electric power utilization
Throughput
Networks (circuits)
Temperature

Keywords

  • Competitive index
  • Dynamic management algorithm
  • Multi-core systems
  • Negative bias temperature instability
  • Self-tuning design

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Cite this

A self-tuning design methodology for power-efficient multi-core systems. / Sun, Jin; Zheng, Rui; Velamala, Jyothi; Cao, Yu; Lysecky, Roman L; Shankar, Karthik; Wang, Meiling.

In: ACM Transactions on Design Automation of Electronic Systems, Vol. 18, No. 1, 4, 12.2012.

Research output: Contribution to journalArticle

@article{0116222c462f4d0bb5ea7e4027781542,
title = "A self-tuning design methodology for power-efficient multi-core systems",
abstract = "This article aims to achieve computational reliability and energy efficiency through codevelopment of algorithms, device, and circuit designs for application-specific, reconfigurable architectures. The new methodology characterizes aging-switching activity and aging-supply voltage relationships that are applicable for minimizing power consumption and task execution efficiency in order to achieve low bit energy ratio (BER). In addition, a new dynamic management algorithm (DMA) is proposed to alleviate device degradation and to extend system lifespan. In contrast to traditional workload balancing schemes in which cores are regarded as homogeneous, the new algorithm ranks cores as 'highly competitive,' 'less competitive,' and 'not competitive' according to their various competitiveness. Core competitiveness is evaluated based upon their reliability, temperature, and timing requirements. Consequently, 'competitive' cores will take charge of the majority of the tasks at relatively high voltage/frequency without violating power and timing budgets, while 'not competitive' cores will have light workloads to ensure their reliability. The new approach combines intrinsic device characteristics (aging-switching activity and aging-supply voltage curves) into an integrated framework to achieve high reliability and low energy level with graceful degradation of system performance. Experimental results show that the proposed method has achieved up to 20{\%} power reduction, with about 4{\%} performance degradation (in terms of accomplished workload and system throughput), compared with traditional workload balancing methods. The new method also improves system mean-time-to-failure (MTTF) by up to 25{\%}.",
keywords = "Competitive index, Dynamic management algorithm, Multi-core systems, Negative bias temperature instability, Self-tuning design",
author = "Jin Sun and Rui Zheng and Jyothi Velamala and Yu Cao and Lysecky, {Roman L} and Karthik Shankar and Meiling Wang",
year = "2012",
month = "12",
doi = "10.1145/2390191.2390195",
language = "English (US)",
volume = "18",
journal = "ACM Transactions on Design Automation of Electronic Systems",
issn = "1084-4309",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - A self-tuning design methodology for power-efficient multi-core systems

AU - Sun, Jin

AU - Zheng, Rui

AU - Velamala, Jyothi

AU - Cao, Yu

AU - Lysecky, Roman L

AU - Shankar, Karthik

AU - Wang, Meiling

PY - 2012/12

Y1 - 2012/12

N2 - This article aims to achieve computational reliability and energy efficiency through codevelopment of algorithms, device, and circuit designs for application-specific, reconfigurable architectures. The new methodology characterizes aging-switching activity and aging-supply voltage relationships that are applicable for minimizing power consumption and task execution efficiency in order to achieve low bit energy ratio (BER). In addition, a new dynamic management algorithm (DMA) is proposed to alleviate device degradation and to extend system lifespan. In contrast to traditional workload balancing schemes in which cores are regarded as homogeneous, the new algorithm ranks cores as 'highly competitive,' 'less competitive,' and 'not competitive' according to their various competitiveness. Core competitiveness is evaluated based upon their reliability, temperature, and timing requirements. Consequently, 'competitive' cores will take charge of the majority of the tasks at relatively high voltage/frequency without violating power and timing budgets, while 'not competitive' cores will have light workloads to ensure their reliability. The new approach combines intrinsic device characteristics (aging-switching activity and aging-supply voltage curves) into an integrated framework to achieve high reliability and low energy level with graceful degradation of system performance. Experimental results show that the proposed method has achieved up to 20% power reduction, with about 4% performance degradation (in terms of accomplished workload and system throughput), compared with traditional workload balancing methods. The new method also improves system mean-time-to-failure (MTTF) by up to 25%.

AB - This article aims to achieve computational reliability and energy efficiency through codevelopment of algorithms, device, and circuit designs for application-specific, reconfigurable architectures. The new methodology characterizes aging-switching activity and aging-supply voltage relationships that are applicable for minimizing power consumption and task execution efficiency in order to achieve low bit energy ratio (BER). In addition, a new dynamic management algorithm (DMA) is proposed to alleviate device degradation and to extend system lifespan. In contrast to traditional workload balancing schemes in which cores are regarded as homogeneous, the new algorithm ranks cores as 'highly competitive,' 'less competitive,' and 'not competitive' according to their various competitiveness. Core competitiveness is evaluated based upon their reliability, temperature, and timing requirements. Consequently, 'competitive' cores will take charge of the majority of the tasks at relatively high voltage/frequency without violating power and timing budgets, while 'not competitive' cores will have light workloads to ensure their reliability. The new approach combines intrinsic device characteristics (aging-switching activity and aging-supply voltage curves) into an integrated framework to achieve high reliability and low energy level with graceful degradation of system performance. Experimental results show that the proposed method has achieved up to 20% power reduction, with about 4% performance degradation (in terms of accomplished workload and system throughput), compared with traditional workload balancing methods. The new method also improves system mean-time-to-failure (MTTF) by up to 25%.

KW - Competitive index

KW - Dynamic management algorithm

KW - Multi-core systems

KW - Negative bias temperature instability

KW - Self-tuning design

UR - http://www.scopus.com/inward/record.url?scp=84872380863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872380863&partnerID=8YFLogxK

U2 - 10.1145/2390191.2390195

DO - 10.1145/2390191.2390195

M3 - Article

VL - 18

JO - ACM Transactions on Design Automation of Electronic Systems

JF - ACM Transactions on Design Automation of Electronic Systems

SN - 1084-4309

IS - 1

M1 - 4

ER -