Open AccessTemperature‐aware core management in MPSoCs: modelling and evaluation using MRMs
Author(s) -
Taheri Golnaz,
Khonsari Ahmad,
EntezariMaleki Reza,
Sousa Leonel
Publication year - 2020
Publication title -
iet computers and digital techniques
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.219
H-Index - 46
ISSN - 1751-861X
DOI - 10.1049/iet-cdt.2018.5131
Subject(s) - scheduling (production processes) , computer science , multi core processor , system on a chip , thermal management of electronic devices and systems , temperature control , thermal , embedded system , parallel computing , engineering , control engineering , meteorology , mechanical engineering , operations management , physics
With successive scaling of CMOS technology, power density and cooling costs significantly increase. Consequently, the cooling system of processors can no longer be designed for the worst‐case situation in each generation of CMOS technology and there is an essential need for run‐time techniques to control the operating temperature. Task scheduling and resource management with respect to thermal constraints are run‐time methods used to control the thermal profile of a system. In this study, the authors use Markov Reward Models (MRMs) to model and evaluate a new core thermal management method, which can reduce hotspots and balance the thermal profile of a multi‐core system. Although the proposed management method degrades the performance of the system, such as other previously presented methods, it controls the temperature of a die to decrease the temperature variation and hotspots. The proposed approach is assessed on a quad‐core system and the experimental results are compared to the results obtained from the proposed MRM to demonstrate the accuracy of the proposed analytical model.