A self-adaptive DVS scheduling algorithm for multi-core systems

Kaiqiang Wu; Yi Liu; Mingyu Wu; Depei Qian

doi:10.1109/ICCDA.2010.5541379

A self-adaptive DVS scheduling algorithm for multi-core systems

Kaiqiang Wu^*
, Yi Liu
, Mingyu Wu
, Depei Qian

^*Corresponding author for this work

School of Computer Science and Engineering

Xi'an Jiaotong University
Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Dynamic Voltage Scaling (DVS) is widely supported in modern general purpose systems, like desktops. Intervalbased DVS algorithms have been used in some operating systems (OSs), like Linux. But their load prediction models can't fit various needs of users so well, since most of them employ one prediction method only. In this paper, a selfadaptive algorithm called SADVS is presented. It selects the best algorithm according to the prediction accuracy of historical records, and the selector will be used to adjust the CPU speed in the following interval. SADVS behaves well in both simulations and actual implementation. For actual implementation, we find that SADVS reduces energy consumption 0.02%-4% without time extension compared to results of ondemand policy in Linux kernel.

Original language	English
Title of host publication	2010 International Conference on Computer Design and Applications, ICCDA 2010
Publisher	IEEE Computer Society
Pages	585-589
Number of pages	5
ISBN (Print)	9781424471638
DOIs	https://doi.org/10.1109/ICCDA.2010.5541379
State	Published - 2010
Event	2010 International Conference on Computer Design and Applications, ICCDA 2010 - Qinhuangdao, Hebei, China Duration: 25 Jun 2010 → 27 Jun 2010

Publication series

Name	2010 International Conference on Computer Design and Applications, ICCDA 2010
Volume	3

Conference

Conference	2010 International Conference on Computer Design and Applications, ICCDA 2010
Country/Territory	China
City	Qinhuangdao, Hebei
Period	25/06/10 → 27/06/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

DVS
Energy savings
General purpose systems

Access to Document

10.1109/ICCDA.2010.5541379

Cite this

Wu, K., Liu, Y., Wu, M., & Qian, D. (2010). A self-adaptive DVS scheduling algorithm for multi-core systems. In 2010 International Conference on Computer Design and Applications, ICCDA 2010 (pp. 585-589). Article 5541379 (2010 International Conference on Computer Design and Applications, ICCDA 2010; Vol. 3). IEEE Computer Society. https://doi.org/10.1109/ICCDA.2010.5541379

@inproceedings{0d71f5f9c4254f5a897e699484b16301,

title = "A self-adaptive DVS scheduling algorithm for multi-core systems",

abstract = "Dynamic Voltage Scaling (DVS) is widely supported in modern general purpose systems, like desktops. Intervalbased DVS algorithms have been used in some operating systems (OSs), like Linux. But their load prediction models can't fit various needs of users so well, since most of them employ one prediction method only. In this paper, a selfadaptive algorithm called SADVS is presented. It selects the best algorithm according to the prediction accuracy of historical records, and the selector will be used to adjust the CPU speed in the following interval. SADVS behaves well in both simulations and actual implementation. For actual implementation, we find that SADVS reduces energy consumption 0.02\%-4\% without time extension compared to results of ondemand policy in Linux kernel.",

keywords = "DVS, Energy savings, General purpose systems",

author = "Kaiqiang Wu and Yi Liu and Mingyu Wu and Depei Qian",

year = "2010",

doi = "10.1109/ICCDA.2010.5541379",

language = "英语",

isbn = "9781424471638",

series = "2010 International Conference on Computer Design and Applications, ICCDA 2010",

publisher = "IEEE Computer Society",

pages = "585--589",

booktitle = "2010 International Conference on Computer Design and Applications, ICCDA 2010",

address = "美国",

note = "2010 International Conference on Computer Design and Applications, ICCDA 2010 ; Conference date: 25-06-2010 Through 27-06-2010",

}

Wu, K, Liu, Y, Wu, M & Qian, D 2010, A self-adaptive DVS scheduling algorithm for multi-core systems. in 2010 International Conference on Computer Design and Applications, ICCDA 2010., 5541379, 2010 International Conference on Computer Design and Applications, ICCDA 2010, vol. 3, IEEE Computer Society, pp. 585-589, 2010 International Conference on Computer Design and Applications, ICCDA 2010, Qinhuangdao, Hebei, China, 25/06/10. https://doi.org/10.1109/ICCDA.2010.5541379

A self-adaptive DVS scheduling algorithm for multi-core systems. / Wu, Kaiqiang; Liu, Yi; Wu, Mingyu et al.
2010 International Conference on Computer Design and Applications, ICCDA 2010. IEEE Computer Society, 2010. p. 585-589 5541379 (2010 International Conference on Computer Design and Applications, ICCDA 2010; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A self-adaptive DVS scheduling algorithm for multi-core systems

AU - Wu, Kaiqiang

AU - Liu, Yi

AU - Wu, Mingyu

AU - Qian, Depei

PY - 2010

Y1 - 2010

N2 - Dynamic Voltage Scaling (DVS) is widely supported in modern general purpose systems, like desktops. Intervalbased DVS algorithms have been used in some operating systems (OSs), like Linux. But their load prediction models can't fit various needs of users so well, since most of them employ one prediction method only. In this paper, a selfadaptive algorithm called SADVS is presented. It selects the best algorithm according to the prediction accuracy of historical records, and the selector will be used to adjust the CPU speed in the following interval. SADVS behaves well in both simulations and actual implementation. For actual implementation, we find that SADVS reduces energy consumption 0.02%-4% without time extension compared to results of ondemand policy in Linux kernel.

AB - Dynamic Voltage Scaling (DVS) is widely supported in modern general purpose systems, like desktops. Intervalbased DVS algorithms have been used in some operating systems (OSs), like Linux. But their load prediction models can't fit various needs of users so well, since most of them employ one prediction method only. In this paper, a selfadaptive algorithm called SADVS is presented. It selects the best algorithm according to the prediction accuracy of historical records, and the selector will be used to adjust the CPU speed in the following interval. SADVS behaves well in both simulations and actual implementation. For actual implementation, we find that SADVS reduces energy consumption 0.02%-4% without time extension compared to results of ondemand policy in Linux kernel.

KW - DVS

KW - Energy savings

KW - General purpose systems

UR - https://www.scopus.com/pages/publications/77955857979

U2 - 10.1109/ICCDA.2010.5541379

DO - 10.1109/ICCDA.2010.5541379

M3 - 会议稿件

AN - SCOPUS:77955857979

SN - 9781424471638

T3 - 2010 International Conference on Computer Design and Applications, ICCDA 2010

SP - 585

EP - 589

BT - 2010 International Conference on Computer Design and Applications, ICCDA 2010

PB - IEEE Computer Society

T2 - 2010 International Conference on Computer Design and Applications, ICCDA 2010

Y2 - 25 June 2010 through 27 June 2010

ER -

A self-adaptive DVS scheduling algorithm for multi-core systems

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this