RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms
The demand for heterogeneous multicore platforms is growing at a rapid pace in modern gadgets. Such platforms help cater to various types of applications and thus provide high resource utilization. As each task has a different execution time on different types of cores, it is very challenging to sch...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Results in Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123022003784 |
_version_ | 1811257466348896256 |
---|---|
author | Yanshul Sharma Sanjay Moulik |
author_facet | Yanshul Sharma Sanjay Moulik |
author_sort | Yanshul Sharma |
collection | DOAJ |
description | The demand for heterogeneous multicore platforms is growing at a rapid pace in modern gadgets. Such platforms help cater to various types of applications and thus provide high resource utilization. As each task has a different execution time on different types of cores, it is very challenging to schedule tasks on such platforms. With the advancement in technology, it has become imperative to manage energy consumption and temperatures of cores in multicore platforms. Hence, in this work, we propose RT-SEAT, a hybrid real-time scheduler for energy and temperature-efficient heterogeneous multicore systems. Through extensive experimental analysis, we have found that RT-SEAT is able to schedule more tasks (up to 46.75%), save more energy (up to 6.89%), and reduce the average temperature of the cores by 20.45%, when the system workload varies from 50% to 100%, with respect to the state-of-the-art. |
first_indexed | 2024-04-12T17:56:56Z |
format | Article |
id | doaj.art-ce36aa73364644f2b501bcea9ceaa451 |
institution | Directory Open Access Journal |
issn | 2590-1230 |
language | English |
last_indexed | 2024-04-12T17:56:56Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | Results in Engineering |
spelling | doaj.art-ce36aa73364644f2b501bcea9ceaa4512022-12-22T03:22:18ZengElsevierResults in Engineering2590-12302022-12-0116100708RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platformsYanshul Sharma0Sanjay Moulik1Department of Computer Science and Engineering, Indian Institute of Information Technology, Guwahati, IndiaCorresponding author.; Department of Computer Science and Engineering, Indian Institute of Information Technology, Guwahati, IndiaThe demand for heterogeneous multicore platforms is growing at a rapid pace in modern gadgets. Such platforms help cater to various types of applications and thus provide high resource utilization. As each task has a different execution time on different types of cores, it is very challenging to schedule tasks on such platforms. With the advancement in technology, it has become imperative to manage energy consumption and temperatures of cores in multicore platforms. Hence, in this work, we propose RT-SEAT, a hybrid real-time scheduler for energy and temperature-efficient heterogeneous multicore systems. Through extensive experimental analysis, we have found that RT-SEAT is able to schedule more tasks (up to 46.75%), save more energy (up to 6.89%), and reduce the average temperature of the cores by 20.45%, when the system workload varies from 50% to 100%, with respect to the state-of-the-art.http://www.sciencedirect.com/science/article/pii/S2590123022003784MulticoreDeadlineEnergyHeterogeneousTemperature |
spellingShingle | Yanshul Sharma Sanjay Moulik RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms Results in Engineering Multicore Deadline Energy Heterogeneous Temperature |
title | RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms |
title_full | RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms |
title_fullStr | RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms |
title_full_unstemmed | RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms |
title_short | RT-SEAT: A hybrid approach based real-time scheduler for energy and temperature efficient heterogeneous multicore platforms |
title_sort | rt seat a hybrid approach based real time scheduler for energy and temperature efficient heterogeneous multicore platforms |
topic | Multicore Deadline Energy Heterogeneous Temperature |
url | http://www.sciencedirect.com/science/article/pii/S2590123022003784 |
work_keys_str_mv | AT yanshulsharma rtseatahybridapproachbasedrealtimeschedulerforenergyandtemperatureefficientheterogeneousmulticoreplatforms AT sanjaymoulik rtseatahybridapproachbasedrealtimeschedulerforenergyandtemperatureefficientheterogeneousmulticoreplatforms |