Article

Differential energy profiling: energy optimization via diffing similar apps

Authors:

Abhilash Jindal,

Y. Charlie HuAuthors Info & Claims

OSDI'18: Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation

Pages 511 - 526

Published: 08 October 2018 Publication History

Abstract

Mobile app energy profilers provide a foundational energy diagnostic tool by identifying energy hotspots in the app source code. However, they only tackle the first challenge faced by developers, as, after presented with the energy hotspots, developers typically do not have any guidance on how to proceed with the remaining optimization process: (1) Is there a more energy-efficient implementation for the same app task? (2) How to come up with the more efficient implementation?

To help developers tackle these challenges, we developed a new energy profiling methodology called differential energy profiling that automatically uncovers more efficient implementations of common app tasks by leveraging existing implementations of similar apps which are bountiful in the app marketplace. To demonstrate its effectiveness, we implemented such a differential energy profiler, DIFFPROF, for Android apps and used it to profile 8 groups (from 6 popular app categories) of 5 similar apps each. Our extensive case studies show that DIFFPROF provides developers with actionable diagnosis beyond a traditional energy profiler: it identifies non-essential (unmatched or extra) and known-to-be inefficient (matched) tasks, and the call trees of tasks it extracts further allow developers to quickly understand the reasons and develop fixes for the energy difference with minor manual debugging efforts.

References

[1]

Apache maven project. http://maven.apache.org.

[2]

Create.net apps faster with NuGeT. https://www.nuget.org.

[3]

Delayed loading of views. https://developer.android.com/training/improving-layouts/loading-ondemand.html#ViewStub.

[4]

dex2jar. https://sourceforge.net/projects/dex2jar/.

[5]

dexinfo. https://github.com/poliva/dexinfo.

[6]

Npm package manager. https://www.npmjs.com.

[7]

Optimizing battery life. https://developer.android.com/training/monitoring-device-state/index.html.

[8]

Using compound drawables. https://developer.android.com/training/improving-layouts/optimizing-layout.html#Lint.

[9]

AMMONS, G., BALL, T., AND LARUS, J. R. Exploiting hardware performance counters with flow and context sensitive profiling. ACM Sigplan Notices 32, 5 (1997), 85-96.

Digital Library

[10]

ANAND, A., GUPTA, A., AKELLA, A., SESHAN, S., AND SHENKER, S. Packet caches on routers: the implications of universal redundant traffic elimination. In Proc. of ACM SIGCOMM (2008), pp. 219-230.

Digital Library

[11]

ANAND, A., SEKAR, V., AND AKELLA, A. Smartre: an architecture for coordinated network-wide redundancy elimination. In Proc. of ACM SIGCOMM (2009), pp. 87-98.

Digital Library

[12]

BILLE, P. A survey on tree edit distance and related problems. Theoretical computer science 337, 1 (2005), 217-239.

Digital Library

[13]

CALCAGNO, C., DISTEFANO, D., DUBREIL, J., GABI, D., HOOIMEIJER, P., LUCA, M., OHEARN, P., PAPAKONSTANTINOU, I., PURBRICK, J., AND RODRIGUEZ, D. Moving fast with software verification. In NASA Formal Methods Symposium (2015), Springer, pp. 3-11.

[14]

CHEN, A., WU, Y., HAEBERLEN, A., ZHOU, W., AND LOO, B. T. The good, the bad, and the differences: Better network diagnostics with differential provenance. In Proc. of ACM SIGCOMM (2016), pp. 115-128.

Digital Library

[15]

COPPA, E., DEMETRESCU, C., AND FINOCCHI, I. Input-sensitive profiling. ACM SIGPLAN Notices 47, 6 (2012), 89-98.

Digital Library

[16]

COZZIE, A., STRATTON, F., XUE, H., AND KING, S. T. Digging for data structures. In Proc. of USENIX OSDI (2008), pp. 255-266.

Digital Library

[17]

CURTSINGER, C., AND BERGER, E. D. Coz: finding code that counts with causal profiling. In Proceedings of the 25th Symposium on Operating Systems Principles (2015), ACM, pp. 184-197.

Digital Library

[18]

DING, N., AND HU, Y. C. Gfxdoctor: A holistic graphics energy profiler for mobile devices. In Proceedings of the Twelfth European Conference on Computer Systems (2017), ACM, pp. 359-373.

Digital Library

[19]

Erlenmeyer flask. https://en.wikipedia.org/wiki/Erlenmeyer_flask.

[20]

GRAHAM, S. L., KESSLER, P. B., AND MCKUSICK, M. K. gprof: A call graph execution profiler. In Proc. of ACM PLDI (1982).

[21]

GUO, L., ROYCHOUDHURY, A., AND WANG, T. Accurately choosing execution runs for software fault localization. In International Conference on Compiler Construction (2006), Springer, pp. 80-95.

Digital Library

[22]

GUPTA, R., HARROLD, M. J., AND SOFFA, M. L. An approach to regression testing using slicing. In Software Maintenance, 1992. Proceedings., Conference on (1992), IEEE, pp. 299-308.

[23]

HASSAN, A. E. Predicting faults using the complexity of code changes. In Proceedings of the 31st International Conference on Software Engineering (2009), IEEE Computer Society, pp. 78-88.

Digital Library

[24]

HUNT, A., AND THOMAS, D. The Pragmatic Programmer: From Journeyman to Master. Addison Wesley Longman, Inc., ISBN-10: 020161622X., 1999.

Digital Library

[25]

HWANG, C., PUSHP, S., KOH, C., YOON, J., LIU, Y., CHOI, S., AND SONG, J. Raven: Perception-aware optimization of power consumption for mobile games. In Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking (2017), ACM, pp. 422-434.

Digital Library

[26]

Energy efficiency and the user experience. https://developer.apple.com/library/archive/documentation/Performance/Conceptual/EnergyGuide-iOS/EnergyandNetworking.html.

[27]

JOHNSON, N. M., CABALLERO, J., CHEN, K. Z., MCCAMANT, S., POOSANKAM, P., REYNAUD, D., AND SONG, D. Differential slicing: Identifying causal execution differences for security applications. In Security and Privacy (SP), 2011 IEEE Symposium on (2011), IEEE, pp. 347-362.

Digital Library

[28]

JOSHI, P., PARK, C.-S., SEN, K., AND NAIK, M. A randomized dynamic program analysis technique for detecting real deadlocks. In Proc. of ACM PLDI (2009), pp. 110-120.

Digital Library

[29]

KULKARNI, P., DOUGLIS, F., LAVOIE, J. D., AND TRACEY, J. M. Redundancy elimination within large collections of files. In USENIX Annual Technical Conference, General Track (2004), pp. 59-72.

Digital Library

[30]

KÜSTNER, T., WEIDENDORFER, J., AND WEINZIERL, T. Argument controlled profiling. In European Conference on Parallel Processing (2009), Springer, pp. 177-184.

Digital Library

[31]

MITTAL, R., KANSAL, A., AND CHANDRA, R. Empowering developers to estimate app energy consumption. In Proc. of ACM MobiCom (2012).

Digital Library

[32]

PATHAK, A., HU, Y. C., AND ZHANG, M. Where is the energy spent inside my app? fine grained energy accounting on smartphones with eprof. In Proc. of EuroSys (2012).

Digital Library

[33]

PERKINSA, J. H., KIMB, S., LARSENG, S., AMARASINGHEA, S., BACHRACHA, J., CARBINA, M., PACHECOD, C., SHERWOOD, F., SIDIROGLOUA, S., SULLIVANE, G., WONGZ, W.-F., ERNSTQ, Y. Z. M. D., AND RINARD, M. Automatically patching errors in deployed software. In SOSP (2009), pp. 87-102.

Digital Library

[34]

QIAN, F., WANG, Z., GERBER, A., MAO, Z., SEN, S., AND SPATSCHECK, O. Profiling resource usage for mobile applications: a cross-layer approach. In Proc. of Mobisys (2011).

Digital Library

[35]

RAVINDRANATH, L., PADHYE, J., AGARWAL, S., MAHAJAN, R., OBERMILLER, I., AND SHAYANDEH, S. Appinsight: mobile app performance monitoring in the wild. In Proc. of USENIX OSDI (2012), pp. 107-120.

Digital Library

[36]

ROTHERMEL, G., AND HARROLD, M. J. Selecting regression tests for object-oriented software. In ICSM (1994), vol. 94, pp. 14-25.

Digital Library

[37]

SHEN, K., STEWART, C., LI, C., AND LI, X. Reference-driven performance anomaly identification. In ACM SIGMETRICS (2009), pp. 85-96.

Digital Library

[38]

TAI, K.-C. The tree-to-tree correction problem. Journal of the ACM (JACM) 26, 3 (1979), 422-433.

Digital Library

[39]

TALLENT, N. R., AND MELLOR-CRUMMEY, J. M. Effective performance measurement and analysis of multithreaded applications. In PPoPP (2009), ACM, pp. 229-240.

Digital Library

[40]

TAN, L., YUAN, D., KRISHNA, G., AND ZHOU, Y. *icomment: bugs or bad comments?*. In Proc. of ACMSOSP (2007), pp. 145-158.

Digital Library

[41]

WAGNER, R. A., AND FISCHER, M. J. The string-to-string correction problem. Journal of the ACM (JACM) 21, 1 (1974), 168-173.

Digital Library

[42]

WANG, H. J., PLATT, J. C., CHEN, Y., ZHANG, R., AND WANG, Y.-M. Automatic misconfiguration troubleshooting with peerpressure. In Proc. of USENIX OSDI (2004), pp. 245-258.

Digital Library

[43]

XIN, B., SUMNER, W. N., AND ZHANG, X. Efficient program execution indexing. In Proc. of ACM PLDI (2008), ACM, pp. 238-248.

Digital Library

[44]

ZHANG, K. Algorithms for the constrained editing distance between ordered labeled trees and related problems. Pattern recognition 28, 3 (1995), 463-474.

[45]

ZHANG, X., TALLAM, S., GUPTA, N., AND GUPTA, R. Towards locating execution omission errors. In Proc. of ACM PLDI (2007), ACM, pp. 415-424.

Digital Library

[46]

ZHANG, J., RENGANARAYANA, L., ZHANG, X., GE, N., BALA, V., XU, T., AND ZHOU, Y. Encore: exploiting system environment and correlation information for misconfiguration detection. In ASPLOS (2014), pp. 687-700.

Digital Library

Cited By

Yao YLiu XQian FKawsar FMin CMathur AAshok AAlessandro Montanari A(2019)Understanding the Predictability of Smartwatch UsageThe 5th ACM Workshop on Wearable Systems and Applications10.1145/3325424.3329661(11-16)Online publication date: 12-Jun-2019
https://dl.acm.org/doi/10.1145/3325424.3329661

Recommendations

KLEP: a kernel level energy profiling tool for Android: poster abstract
IPSN '17: Proceedings of the 16th ACM/IEEE International Conference on Information Processing in Sensor Networks

We propose a kernel-level energy profiling tool KLEP that can work with diverse APIs of Android. KLEP addresses the challenges of the tail energy problem and the complex interrelation between hardware components in the device energy consumption profile. ...
Profiling energy profilers
SAC '15: Proceedings of the 30th Annual ACM Symposium on Applied Computing

While energy is directly consumed by hardware, it is the software that provides the instructions to do so. Energy profilers provide a means to measure the energy consumption of software, enabling the user to take measures in making software more ...
Profiling Software for Energy Consumption
GREENCOM '12: Proceedings of the 2012 IEEE International Conference on Green Computing and Communications

The amount of energy consumed by computer systems can be lowered through the use of more efficient algorithms and software. Unfortunately, software developers lack the tools to pinpoint energy-hungry sections in their code and therefore have to rely on ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

OSDI'18: Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation

October 2018

815 pages

ISBN:9781931971478

Program Chairs:
Andrea Arpaci-Dusseau
University of Wisconsin-Madison
,
Geoff Voelker
University of California, San Diego

Sponsors

NetApp
Google Inc.
NSF
Microsoft: Microsoft
Facebook: Facebook

In-Cooperation

SIGOPS: ACM Special Interest Group on Operating Systems

Publisher

USENIX Association

United States

Publication History

Published: 08 October 2018

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 13 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Yao YLiu XQian FKawsar FMin CMathur AAshok AAlessandro Montanari A(2019)Understanding the Predictability of Smartwatch UsageThe 5th ACM Workshop on Wearable Systems and Applications10.1145/3325424.3329661(11-16)Online publication date: 12-Jun-2019
https://dl.acm.org/doi/10.1145/3325424.3329661

View Options

View options

Media

Figures

Other

Tables

View Table of Contents