Thermal constrained workload distribution for maximizing throughput on multi-core processors

Author

Wang, Zhe ; Ranka, Sanjay

Author_Institution

Dept. of Comput. & Inf. Sci. & Eng., Univ. of Florida, Gainesville, FL, USA

fYear

2010

fDate

15-18 Aug. 2010

Firstpage

291

Lastpage

298

Abstract

Power density and heat density of multi-core processor system are increasing exponentially based on Moore´s Law. The reliability of a chip is severely impacted by temperature “hot spots”. In this paper, we study scheduling algorithms for multi-core processors that incorporate temperature constraints. Our goal is to optimize the workload distribution on a multicore processor to maximize throughput with a given maximum operating temperature. Our algorithms are targeted for a larger class of data parallel and task parallel applications. Experimental results show that our algorithms are computationally fast, maximize throughput and provide effective temperature management.

Keywords

multiprocessing systems; parallel processing; processor scheduling; Moore´s Law; chip reliability; data parallel application; heat density; multicore processor system; power density; scheduling algorithm; task parallel application; temperature constraints; temperature hot spots; temperature management; thermal constrained workload distribution; throughput maximisation; Multicore processing; DVFS; Linear and Integer Programming; Multi-core Processor; Thermal Constrained Scheduling;

fLanguage

English

Publisher

ieee

Conference_Titel

Green Computing Conference, 2010 International

Conference_Location

Chicago, IL

Print_ISBN

978-1-4244-7612-1

Type

conf

DOI

10.1109/GREENCOMP.2010.5598302

Filename

5598302