The University of Southampton
University of Southampton Institutional Repository

Dynamic and Leakage Power-Composition Profile Driven Co-Synthesis for Energy and Cost Reduction

Dynamic and Leakage Power-Composition Profile Driven Co-Synthesis for Energy and Cost Reduction
Dynamic and Leakage Power-Composition Profile Driven Co-Synthesis for Energy and Cost Reduction
Recent research has shown that combining dynamic voltage scaling (DVS) and adaptive body bias (ABB) techniques achieve the highest reduction in embedded systems energy dissipation [1]. In this paper we show that it is possible to produce comparable energy saving to that obtained using combined DVS and ABB techniques but with reduced hardware cost achieved by employing processing elements (PEs) with separate DVS or ABB capability. A co-synthesis methodology which is aware of tasks’ power-composition profile (the ratio of the dynamic power to the leakage power) is presented. The methodology selects voltage scaling capabilities (DVS, ABB, or combined DVS and ABB) for the PEs, maps, schedules, and voltage scales applications given as task graphs with timing constraints, aiming to dynamic and leakage energy reduction at low hardware cost. We conduct detailed experiments, including a real-life example, to demonstrate the effectiveness of our methodology. We demonstrate that it is possible to produce designs that contain PEs with only DVS or ABB technique but have energy dissipation that are only 4.4% higher when compared with the same designs that employ PEs with combined DVS and ABB capabilities.
Wu, Dong
0929d522-75bc-46f5-887e-027662ea4ebc
Al-Hashimi, Bashir M
0b29c671-a6d2-459c-af68-c4614dce3b5d
Eles, Petru
ff663918-4c91-4774-a196-06d87393323f
Wu, Dong
0929d522-75bc-46f5-887e-027662ea4ebc
Al-Hashimi, Bashir M
0b29c671-a6d2-459c-af68-c4614dce3b5d
Eles, Petru
ff663918-4c91-4774-a196-06d87393323f

Wu, Dong, Al-Hashimi, Bashir M and Eles, Petru (2004) Dynamic and Leakage Power-Composition Profile Driven Co-Synthesis for Energy and Cost Reduction. System-On-Chip Design, Test and Technology, Loughborough, United Kingdom.

Record type: Conference or Workshop Item (Paper)

Abstract

Recent research has shown that combining dynamic voltage scaling (DVS) and adaptive body bias (ABB) techniques achieve the highest reduction in embedded systems energy dissipation [1]. In this paper we show that it is possible to produce comparable energy saving to that obtained using combined DVS and ABB techniques but with reduced hardware cost achieved by employing processing elements (PEs) with separate DVS or ABB capability. A co-synthesis methodology which is aware of tasks’ power-composition profile (the ratio of the dynamic power to the leakage power) is presented. The methodology selects voltage scaling capabilities (DVS, ABB, or combined DVS and ABB) for the PEs, maps, schedules, and voltage scales applications given as task graphs with timing constraints, aiming to dynamic and leakage energy reduction at low hardware cost. We conduct detailed experiments, including a real-life example, to demonstrate the effectiveness of our methodology. We demonstrate that it is possible to produce designs that contain PEs with only DVS or ABB technique but have energy dissipation that are only 4.4% higher when compared with the same designs that employ PEs with combined DVS and ABB capabilities.

Text
wu_soc3.pdf - Other
Download (135kB)

More information

Published date: 2004
Additional Information: Event Dates: September 2004
Venue - Dates: System-On-Chip Design, Test and Technology, Loughborough, United Kingdom, 2004-09-01
Organisations: Electronic & Software Systems

Identifiers

Local EPrints ID: 259899
URI: http://eprints.soton.ac.uk/id/eprint/259899
PURE UUID: ff13dcc6-bda4-49cf-9827-11403b5253d9

Catalogue record

Date deposited: 02 Sep 2004
Last modified: 14 Mar 2024 06:29

Export record

Contributors

Author: Dong Wu
Author: Bashir M Al-Hashimi
Author: Petru Eles

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×