Android video processing system combined with automatically parallelized and power optimized code by OSCAR compiler

Bui Duc Binh, Tomohiro Hirano, Hiroki Mikami, Hideo Yamamoto, Keiji Kimura, Hironori Kasahara

研究成果: Article

抄録

The emergence of multi-core processors in smart devices promises higher performance and low power consumption. The parallelization of applications enables us to improve their performance. However, simultaneously utilizing many cores would drastically drain the device battery life. This paper shows a demonstration system of realtime video processing combined with power reduction controlled by the OSCAR automatic parallelization compiler on ODROID-X2, an open Android development platform based on Samsung Exynos4412 Prime with 4 ARM Cortext- A9 cores. In this paper, we exploited the DVFS framework, core partitioning, and profiling technique and OSCAR parallelization - power control algorithm to reduce the total consumption in a real-time video application. The demonstration results show that it can cut power consumption by 42.8% for MPEG-2 Decoder application and 59.8% for Optical Flow application by using 3 cores in both applications.

元の言語English
ページ(範囲)504-511
ページ数8
ジャーナルJournal of Information Processing
24
発行部数3
DOI
出版物ステータスPublished - 2016

Fingerprint

Processing
Electric power utilization
Demonstrations
Optical flows
Power control

ASJC Scopus subject areas

  • Computer Science(all)

これを引用

@article{eb6c4838546d40559ae877c9265bdda9,
title = "Android video processing system combined with automatically parallelized and power optimized code by OSCAR compiler",
abstract = "The emergence of multi-core processors in smart devices promises higher performance and low power consumption. The parallelization of applications enables us to improve their performance. However, simultaneously utilizing many cores would drastically drain the device battery life. This paper shows a demonstration system of realtime video processing combined with power reduction controlled by the OSCAR automatic parallelization compiler on ODROID-X2, an open Android development platform based on Samsung Exynos4412 Prime with 4 ARM Cortext- A9 cores. In this paper, we exploited the DVFS framework, core partitioning, and profiling technique and OSCAR parallelization - power control algorithm to reduce the total consumption in a real-time video application. The demonstration results show that it can cut power consumption by 42.8{\%} for MPEG-2 Decoder application and 59.8{\%} for Optical Flow application by using 3 cores in both applications.",
keywords = "Android, Automatic parallelizing compiler, Low-power consumption, Multi-core processor",
author = "Binh, {Bui Duc} and Tomohiro Hirano and Hiroki Mikami and Hideo Yamamoto and Keiji Kimura and Hironori Kasahara",
year = "2016",
doi = "10.2197/ipsjjip.24.504",
language = "English",
volume = "24",
pages = "504--511",
journal = "Journal of Information Processing",
issn = "0387-5806",
publisher = "Information Processing Society of Japan",
number = "3",

}

TY - JOUR

T1 - Android video processing system combined with automatically parallelized and power optimized code by OSCAR compiler

AU - Binh, Bui Duc

AU - Hirano, Tomohiro

AU - Mikami, Hiroki

AU - Yamamoto, Hideo

AU - Kimura, Keiji

AU - Kasahara, Hironori

PY - 2016

Y1 - 2016

N2 - The emergence of multi-core processors in smart devices promises higher performance and low power consumption. The parallelization of applications enables us to improve their performance. However, simultaneously utilizing many cores would drastically drain the device battery life. This paper shows a demonstration system of realtime video processing combined with power reduction controlled by the OSCAR automatic parallelization compiler on ODROID-X2, an open Android development platform based on Samsung Exynos4412 Prime with 4 ARM Cortext- A9 cores. In this paper, we exploited the DVFS framework, core partitioning, and profiling technique and OSCAR parallelization - power control algorithm to reduce the total consumption in a real-time video application. The demonstration results show that it can cut power consumption by 42.8% for MPEG-2 Decoder application and 59.8% for Optical Flow application by using 3 cores in both applications.

AB - The emergence of multi-core processors in smart devices promises higher performance and low power consumption. The parallelization of applications enables us to improve their performance. However, simultaneously utilizing many cores would drastically drain the device battery life. This paper shows a demonstration system of realtime video processing combined with power reduction controlled by the OSCAR automatic parallelization compiler on ODROID-X2, an open Android development platform based on Samsung Exynos4412 Prime with 4 ARM Cortext- A9 cores. In this paper, we exploited the DVFS framework, core partitioning, and profiling technique and OSCAR parallelization - power control algorithm to reduce the total consumption in a real-time video application. The demonstration results show that it can cut power consumption by 42.8% for MPEG-2 Decoder application and 59.8% for Optical Flow application by using 3 cores in both applications.

KW - Android

KW - Automatic parallelizing compiler

KW - Low-power consumption

KW - Multi-core processor

UR - http://www.scopus.com/inward/record.url?scp=84968832012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84968832012&partnerID=8YFLogxK

U2 - 10.2197/ipsjjip.24.504

DO - 10.2197/ipsjjip.24.504

M3 - Article

VL - 24

SP - 504

EP - 511

JO - Journal of Information Processing

JF - Journal of Information Processing

SN - 0387-5806

IS - 3

ER -