Ghent University Academic Bibliography

Advanced

DEP plus BURST : online DVFS performance prediction for energy-efficient managed language execution

Shoaib Akram UGent, Jennifer B. Sartor and Lieven Eeckhout UGent (2017) IEEE TRANSACTIONS ON COMPUTERS. 66(4). p.601-615
abstract
Making modern computer systems energy-efficient is of paramount importance. Dynamic Voltage and Frequency Scaling (DVFS) is widely used to manage the energy and power consumption in modern processors; however, for DVFS to be effective, we need the ability to accurately predict the performance impact of scaling a processor's voltage and frequency. No accurate performance predictors exist for multithreaded applications, let alone managed language applications. In this work, we propose DEP+BURST, a new performance predictor for managed multithreaded applications that takes into account synchronization, inter-thread dependencies, and store bursts, which frequently occur in managed language workloads. Our predictor lowers the performance estimation error from 27 percent for a state-of-the-art predictor to 6 percent on average, for a set of multithreaded Java applications when the frequency is scaled from 1 to 4 GHz. We also novelly propose an energy management framework that uses DEP+BURST to reduce energy consumption. We first target reducing the processor's energy consumption by lowering its frequency and hence its power consumption, while staying within a user-specified maximum slowdown threshold. For a slowdown of 5 and 10 percent, our energy manager reduces on average 13 and 19 percent of energy consumed by the memory-intensive benchmarks. We then use the energy manager to optimize total system energy, achieving an average reduction of 15.6 percent for a set of Java benchmarks. Accurate performance predictors are key to achieving high performance while keeping energy consumption low for managed language applications using DVFS.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
keyword
POWER, SYSTEMS, Dynamic voltage and frequency scaling, multithreaded performance, estimation, managed runtimes, dynamic energy management
journal title
IEEE TRANSACTIONS ON COMPUTERS
IEEE Trans. Comput.
volume
66
issue
4
pages
15 pages
publisher
Ieee Computer Soc
place of publication
Los alamitos
Web of Science type
Article
Web of Science id
000397632300004
ISSN
0018-9340
1557-9956
DOI
10.1109/TC.2016.2609903
language
English
UGent publication?
yes
classification
A1
copyright statement
I have transferred the copyright for this publication to the publisher
id
8542506
handle
http://hdl.handle.net/1854/LU-8542506
date created
2017-12-19 12:09:53
date last changed
2018-01-08 12:43:47
@article{8542506,
  abstract     = {Making modern computer systems energy-efficient is of paramount importance. Dynamic Voltage and Frequency Scaling (DVFS) is widely used to manage the energy and power consumption in modern processors; however, for DVFS to be effective, we need the ability to accurately predict the performance impact of scaling a processor's voltage and frequency. No accurate performance predictors exist for multithreaded applications, let alone managed language applications. In this work, we propose DEP+BURST, a new performance predictor for managed multithreaded applications that takes into account synchronization, inter-thread dependencies, and store bursts, which frequently occur in managed language workloads. Our predictor lowers the performance estimation error from 27 percent for a state-of-the-art predictor to 6 percent on average, for a set of multithreaded Java applications when the frequency is scaled from 1 to 4 GHz. We also novelly propose an energy management framework that uses DEP+BURST to reduce energy consumption. We first target reducing the processor's energy consumption by lowering its frequency and hence its power consumption, while staying within a user-specified maximum slowdown threshold. For a slowdown of 5 and 10 percent, our energy manager reduces on average 13 and 19 percent of energy consumed by the memory-intensive benchmarks. We then use the energy manager to optimize total system energy, achieving an average reduction of 15.6 percent for a set of Java benchmarks. Accurate performance predictors are key to achieving high performance while keeping energy consumption low for managed language applications using DVFS.},
  author       = {Akram, Shoaib and Sartor, Jennifer B. and Eeckhout, Lieven},
  issn         = {0018-9340},
  journal      = {IEEE TRANSACTIONS ON COMPUTERS},
  keyword      = {POWER,SYSTEMS,Dynamic voltage and frequency scaling,multithreaded performance,estimation,managed runtimes,dynamic energy management},
  language     = {eng},
  number       = {4},
  pages        = {601--615},
  publisher    = {Ieee Computer Soc},
  title        = {DEP plus BURST : online DVFS performance prediction for energy-efficient managed language execution},
  url          = {http://dx.doi.org/10.1109/TC.2016.2609903},
  volume       = {66},
  year         = {2017},
}

Chicago
Akram, Shoaib, Jennifer B. Sartor, and Lieven Eeckhout. 2017. “DEP Plus BURST : Online DVFS Performance Prediction for Energy-efficient Managed Language Execution.” Ieee Transactions on Computers 66 (4): 601–615.
APA
Akram, Shoaib, Sartor, J. B., & Eeckhout, L. (2017). DEP plus BURST : online DVFS performance prediction for energy-efficient managed language execution. IEEE TRANSACTIONS ON COMPUTERS, 66(4), 601–615.
Vancouver
1.
Akram S, Sartor JB, Eeckhout L. DEP plus BURST : online DVFS performance prediction for energy-efficient managed language execution. IEEE TRANSACTIONS ON COMPUTERS. Los alamitos: Ieee Computer Soc; 2017;66(4):601–15.
MLA
Akram, Shoaib, Jennifer B. Sartor, and Lieven Eeckhout. “DEP Plus BURST : Online DVFS Performance Prediction for Energy-efficient Managed Language Execution.” IEEE TRANSACTIONS ON COMPUTERS 66.4 (2017): 601–615. Print.