A leakage efficient data TLB design for embedded processors

Zhao Lei, Hui Xu, Daisuke Ikebuchi, Tetsuya Sunata, Mitaro Namiki, Hideharu Amano

Research output: Contribution to journalArticle

Abstract

This paper presents a leakage efficient data TLB (Translation Look-aside Buffer) design for embedded processors. Due to the data locality in programs, data TLB references tend to hit only a small number of pages during short execution intervals. After dividing the overall execution time into smaller time slices, a leakage reduction mechanism is proposed to detect TLB entries which actually serve for virtual-to-physical address translations within each time slice. Thus, with the integration of the dual voltage supply technique, those TLB entries which are not used for address translations can be put into low leakage mode (with lower voltage supply) to save power Evaluation results with eight MiBench programs show that the proposed design can reduce the leakage power of a data TLB by 37% on average, with performance degradation less than 0.01%.

Original languageEnglish
Pages (from-to)51-59
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE94-D
Issue number1
DOIs
Publication statusPublished - 2011 Jan

Fingerprint

Physical addresses
Electric potential
Degradation

Keywords

  • Embedded processor
  • Leakage power
  • TLB

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

A leakage efficient data TLB design for embedded processors. / Lei, Zhao; Xu, Hui; Ikebuchi, Daisuke; Sunata, Tetsuya; Namiki, Mitaro; Amano, Hideharu.

In: IEICE Transactions on Information and Systems, Vol. E94-D, No. 1, 01.2011, p. 51-59.

Research output: Contribution to journalArticle

Lei, Zhao ; Xu, Hui ; Ikebuchi, Daisuke ; Sunata, Tetsuya ; Namiki, Mitaro ; Amano, Hideharu. / A leakage efficient data TLB design for embedded processors. In: IEICE Transactions on Information and Systems. 2011 ; Vol. E94-D, No. 1. pp. 51-59.
@article{6747a8cbf00c48038fba0db8ca78ecd5,
title = "A leakage efficient data TLB design for embedded processors",
abstract = "This paper presents a leakage efficient data TLB (Translation Look-aside Buffer) design for embedded processors. Due to the data locality in programs, data TLB references tend to hit only a small number of pages during short execution intervals. After dividing the overall execution time into smaller time slices, a leakage reduction mechanism is proposed to detect TLB entries which actually serve for virtual-to-physical address translations within each time slice. Thus, with the integration of the dual voltage supply technique, those TLB entries which are not used for address translations can be put into low leakage mode (with lower voltage supply) to save power Evaluation results with eight MiBench programs show that the proposed design can reduce the leakage power of a data TLB by 37{\%} on average, with performance degradation less than 0.01{\%}.",
keywords = "Embedded processor, Leakage power, TLB",
author = "Zhao Lei and Hui Xu and Daisuke Ikebuchi and Tetsuya Sunata and Mitaro Namiki and Hideharu Amano",
year = "2011",
month = "1",
doi = "10.1587/transinfE94.D.51",
language = "English",
volume = "E94-D",
pages = "51--59",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "1",

}

TY - JOUR

T1 - A leakage efficient data TLB design for embedded processors

AU - Lei, Zhao

AU - Xu, Hui

AU - Ikebuchi, Daisuke

AU - Sunata, Tetsuya

AU - Namiki, Mitaro

AU - Amano, Hideharu

PY - 2011/1

Y1 - 2011/1

N2 - This paper presents a leakage efficient data TLB (Translation Look-aside Buffer) design for embedded processors. Due to the data locality in programs, data TLB references tend to hit only a small number of pages during short execution intervals. After dividing the overall execution time into smaller time slices, a leakage reduction mechanism is proposed to detect TLB entries which actually serve for virtual-to-physical address translations within each time slice. Thus, with the integration of the dual voltage supply technique, those TLB entries which are not used for address translations can be put into low leakage mode (with lower voltage supply) to save power Evaluation results with eight MiBench programs show that the proposed design can reduce the leakage power of a data TLB by 37% on average, with performance degradation less than 0.01%.

AB - This paper presents a leakage efficient data TLB (Translation Look-aside Buffer) design for embedded processors. Due to the data locality in programs, data TLB references tend to hit only a small number of pages during short execution intervals. After dividing the overall execution time into smaller time slices, a leakage reduction mechanism is proposed to detect TLB entries which actually serve for virtual-to-physical address translations within each time slice. Thus, with the integration of the dual voltage supply technique, those TLB entries which are not used for address translations can be put into low leakage mode (with lower voltage supply) to save power Evaluation results with eight MiBench programs show that the proposed design can reduce the leakage power of a data TLB by 37% on average, with performance degradation less than 0.01%.

KW - Embedded processor

KW - Leakage power

KW - TLB

UR - http://www.scopus.com/inward/record.url?scp=78650949393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650949393&partnerID=8YFLogxK

U2 - 10.1587/transinfE94.D.51

DO - 10.1587/transinfE94.D.51

M3 - Article

AN - SCOPUS:78650949393

VL - E94-D

SP - 51

EP - 59

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 1

ER -