Most Android applications are written in JAVA and run on a Dalvik virtual machine. For smartphone vendors and users who wish to know the performance of an application on a particular smartphone but cannot obtain the source code, we propose a new technique, Dalvik Profiler for Applications (DPA), to profile an Android application on a Dalvik virtual machine without the support of source code. Within a Dalvik virtual machine, we determine the entry and exit locations of a method, log its execution time, and analyze the log to determine the performance of the application. Our experimental results show an error ratio of less than 5% from the baseline tool Traceview which instruments source code. The results also show some interesting behaviors of applications and smartphones: the performance of some smartphones with higher hardware specifications is 1.5 times less than the phones with lower specifications. DPA is now publicly available as an open source tool.
Hung-Cheng CHANG
National Chiao Tung University
Kuei-Chung CHANG
Feng Chia University
Ying-Dar LIN
National Chiao Tung University
Yuan-Cheng LAI
National Taiwan University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hung-Cheng CHANG, Kuei-Chung CHANG, Ying-Dar LIN, Yuan-Cheng LAI, "Application Performance Profiling in Android Dalvik Virtual Machines" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 5, pp. 1296-1303, May 2016, doi: 10.1587/transinf.2015EDP7277.
Abstract: Most Android applications are written in JAVA and run on a Dalvik virtual machine. For smartphone vendors and users who wish to know the performance of an application on a particular smartphone but cannot obtain the source code, we propose a new technique, Dalvik Profiler for Applications (DPA), to profile an Android application on a Dalvik virtual machine without the support of source code. Within a Dalvik virtual machine, we determine the entry and exit locations of a method, log its execution time, and analyze the log to determine the performance of the application. Our experimental results show an error ratio of less than 5% from the baseline tool Traceview which instruments source code. The results also show some interesting behaviors of applications and smartphones: the performance of some smartphones with higher hardware specifications is 1.5 times less than the phones with lower specifications. DPA is now publicly available as an open source tool.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7277/_p
Copy
@ARTICLE{e99-d_5_1296,
author={Hung-Cheng CHANG, Kuei-Chung CHANG, Ying-Dar LIN, Yuan-Cheng LAI, },
journal={IEICE TRANSACTIONS on Information},
title={Application Performance Profiling in Android Dalvik Virtual Machines},
year={2016},
volume={E99-D},
number={5},
pages={1296-1303},
abstract={Most Android applications are written in JAVA and run on a Dalvik virtual machine. For smartphone vendors and users who wish to know the performance of an application on a particular smartphone but cannot obtain the source code, we propose a new technique, Dalvik Profiler for Applications (DPA), to profile an Android application on a Dalvik virtual machine without the support of source code. Within a Dalvik virtual machine, we determine the entry and exit locations of a method, log its execution time, and analyze the log to determine the performance of the application. Our experimental results show an error ratio of less than 5% from the baseline tool Traceview which instruments source code. The results also show some interesting behaviors of applications and smartphones: the performance of some smartphones with higher hardware specifications is 1.5 times less than the phones with lower specifications. DPA is now publicly available as an open source tool.},
keywords={},
doi={10.1587/transinf.2015EDP7277},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Application Performance Profiling in Android Dalvik Virtual Machines
T2 - IEICE TRANSACTIONS on Information
SP - 1296
EP - 1303
AU - Hung-Cheng CHANG
AU - Kuei-Chung CHANG
AU - Ying-Dar LIN
AU - Yuan-Cheng LAI
PY - 2016
DO - 10.1587/transinf.2015EDP7277
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2016
AB - Most Android applications are written in JAVA and run on a Dalvik virtual machine. For smartphone vendors and users who wish to know the performance of an application on a particular smartphone but cannot obtain the source code, we propose a new technique, Dalvik Profiler for Applications (DPA), to profile an Android application on a Dalvik virtual machine without the support of source code. Within a Dalvik virtual machine, we determine the entry and exit locations of a method, log its execution time, and analyze the log to determine the performance of the application. Our experimental results show an error ratio of less than 5% from the baseline tool Traceview which instruments source code. The results also show some interesting behaviors of applications and smartphones: the performance of some smartphones with higher hardware specifications is 1.5 times less than the phones with lower specifications. DPA is now publicly available as an open source tool.
ER -