Power-capped DVFS and thread allocation with ANN models on modern NUMA systems

Satoshi Imamura, Hiroshi Sasaki, Inoue Koji, Dimitrios S. Nikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to 67.1%, under a power cap.

Original languageEnglish
Title of host publication2014 32nd IEEE International Conference on Computer Design, ICCD 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages324-331
Number of pages8
ISBN (Electronic)9781479964925
DOIs
Publication statusPublished - Dec 3 2014
Event32nd IEEE International Conference on Computer Design, ICCD 2014 - Seoul, Korea, Republic of
Duration: Oct 19 2014Oct 22 2014

Publication series

Name2014 32nd IEEE International Conference on Computer Design, ICCD 2014

Other

Other32nd IEEE International Conference on Computer Design, ICCD 2014
CountryKorea, Republic of
CitySeoul
Period10/19/1410/22/14

Fingerprint

Knobs
Neural networks
Data storage equipment
Servers
Budget control
Computer systems
Electric power utilization
Voltage scaling
Dynamic frequency scaling
Costs

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications

Cite this

Imamura, S., Sasaki, H., Koji, I., & Nikolopoulos, D. S. (2014). Power-capped DVFS and thread allocation with ANN models on modern NUMA systems. In 2014 32nd IEEE International Conference on Computer Design, ICCD 2014 (pp. 324-331). [6974701] (2014 32nd IEEE International Conference on Computer Design, ICCD 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCD.2014.6974701

Power-capped DVFS and thread allocation with ANN models on modern NUMA systems. / Imamura, Satoshi; Sasaki, Hiroshi; Koji, Inoue; Nikolopoulos, Dimitrios S.

2014 32nd IEEE International Conference on Computer Design, ICCD 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 324-331 6974701 (2014 32nd IEEE International Conference on Computer Design, ICCD 2014).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Imamura, S, Sasaki, H, Koji, I & Nikolopoulos, DS 2014, Power-capped DVFS and thread allocation with ANN models on modern NUMA systems. in 2014 32nd IEEE International Conference on Computer Design, ICCD 2014., 6974701, 2014 32nd IEEE International Conference on Computer Design, ICCD 2014, Institute of Electrical and Electronics Engineers Inc., pp. 324-331, 32nd IEEE International Conference on Computer Design, ICCD 2014, Seoul, Korea, Republic of, 10/19/14. https://doi.org/10.1109/ICCD.2014.6974701
Imamura S, Sasaki H, Koji I, Nikolopoulos DS. Power-capped DVFS and thread allocation with ANN models on modern NUMA systems. In 2014 32nd IEEE International Conference on Computer Design, ICCD 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 324-331. 6974701. (2014 32nd IEEE International Conference on Computer Design, ICCD 2014). https://doi.org/10.1109/ICCD.2014.6974701
Imamura, Satoshi ; Sasaki, Hiroshi ; Koji, Inoue ; Nikolopoulos, Dimitrios S. / Power-capped DVFS and thread allocation with ANN models on modern NUMA systems. 2014 32nd IEEE International Conference on Computer Design, ICCD 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 324-331 (2014 32nd IEEE International Conference on Computer Design, ICCD 2014).
@inproceedings{429e2ed1342e40039ca47731bfa3a4e7,
title = "Power-capped DVFS and thread allocation with ANN models on modern NUMA systems",
abstract = "Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to 67.1{\%}, under a power cap.",
author = "Satoshi Imamura and Hiroshi Sasaki and Inoue Koji and Nikolopoulos, {Dimitrios S.}",
year = "2014",
month = "12",
day = "3",
doi = "10.1109/ICCD.2014.6974701",
language = "English",
series = "2014 32nd IEEE International Conference on Computer Design, ICCD 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "324--331",
booktitle = "2014 32nd IEEE International Conference on Computer Design, ICCD 2014",
address = "United States",

}

TY - GEN

T1 - Power-capped DVFS and thread allocation with ANN models on modern NUMA systems

AU - Imamura, Satoshi

AU - Sasaki, Hiroshi

AU - Koji, Inoue

AU - Nikolopoulos, Dimitrios S.

PY - 2014/12/3

Y1 - 2014/12/3

N2 - Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to 67.1%, under a power cap.

AB - Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to 67.1%, under a power cap.

UR - http://www.scopus.com/inward/record.url?scp=84919626863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919626863&partnerID=8YFLogxK

U2 - 10.1109/ICCD.2014.6974701

DO - 10.1109/ICCD.2014.6974701

M3 - Conference contribution

T3 - 2014 32nd IEEE International Conference on Computer Design, ICCD 2014

SP - 324

EP - 331

BT - 2014 32nd IEEE International Conference on Computer Design, ICCD 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -