Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems

Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems

Today's embedded systems operate under increasingly dynamic conditions. First, computational workloads can be either variable by nature or adjustable. Moreover, as many devices are battery-powered, it is common to have runtime power management technique, which results in dynamic power budget. T...

Full description

Bibliographic Details
Main Authors: Hyeonseok Jung, Hoeseok Yang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Context-awareness
dataflow adaptation
low-power electronics
mode switching
multicore processing
Online Access:https://ieeexplore.ieee.org/document/8926450/
id doaj-e27d0513d2a74ba6a57e44b22a9e7abe
record_format Article
spelling doaj-e27d0513d2a74ba6a57e44b22a9e7abe2021-03-29T22:45:52ZengIEEEIEEE Access2169-35362019-01-01717797417798710.1109/ACCESS.2019.29580458926450Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded SystemsHyeonseok Jung0https://orcid.org/0000-0001-8902-9624Hoeseok Yang1https://orcid.org/0000-0002-7929-7470Department of Electrical and Computer Engineering, Ajou University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Ajou University, Suwon, South KoreaToday's embedded systems operate under increasingly dynamic conditions. First, computational workloads can be either variable by nature or adjustable. Moreover, as many devices are battery-powered, it is common to have runtime power management technique, which results in dynamic power budget. This paper presents a design methodology for multi-core systems, based on dataflow specification, that can deal with various contexts. We optimize the original dataflow considering various working conditions, then, autonomously adapt it to a pre-defined optimal form in response to context changes. Such context changes at runtime might cause non-negligible delay or power budget violation. In order to overcome them, an efficient mode switching method is proposed. We show the effectiveness of the proposed technique with a real-life case study, stereo-vision, and synthetic benchmarks.https://ieeexplore.ieee.org/document/8926450/Context-awarenessdataflow adaptationlow-power electronicsmode switchingmulticore processing
collection DOAJ
language English
format Article
sources DOAJ
author Hyeonseok Jung
Hoeseok Yang
spellingShingle Hyeonseok Jung
Hoeseok Yang
Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
IEEE Access
Context-awareness
dataflow adaptation
low-power electronics
mode switching
multicore processing
author_facet Hyeonseok Jung
Hoeseok Yang
author_sort Hyeonseok Jung
title Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
title_short Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
title_full Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
title_fullStr Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
title_full_unstemmed Efficiently Switchable Context-Aware Dataflow Adaptation Technique for Low-Power Multi-Core Embedded Systems
title_sort efficiently switchable context-aware dataflow adaptation technique for low-power multi-core embedded systems
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2019-01-01
description Today's embedded systems operate under increasingly dynamic conditions. First, computational workloads can be either variable by nature or adjustable. Moreover, as many devices are battery-powered, it is common to have runtime power management technique, which results in dynamic power budget. This paper presents a design methodology for multi-core systems, based on dataflow specification, that can deal with various contexts. We optimize the original dataflow considering various working conditions, then, autonomously adapt it to a pre-defined optimal form in response to context changes. Such context changes at runtime might cause non-negligible delay or power budget violation. In order to overcome them, an efficient mode switching method is proposed. We show the effectiveness of the proposed technique with a real-life case study, stereo-vision, and synthetic benchmarks.
topic Context-awareness
dataflow adaptation
low-power electronics
mode switching
multicore processing
url https://ieeexplore.ieee.org/document/8926450/
work_keys_str_mv AT hyeonseokjung efficientlyswitchablecontextawaredataflowadaptationtechniqueforlowpowermulticoreembeddedsystems
AT hoeseokyang efficientlyswitchablecontextawaredataflowadaptationtechniqueforlowpowermulticoreembeddedsystems
_version_ 1724190968456937472

Similar Items