Title :
A Fuzzy algorithm for parallelizability evaluation and load balance on the multi-core processor
Author :
Dai Hongjun ; Xu XinShun ; Jia Zhiping
Author_Institution :
Dept. of Comput. Sci. & Technol., Shandong Univ., Jinan
Abstract :
To schedule real-time threads on the multi-core processors, a fuzzy algorithm is presented for parallelizability evaluation and load balance, which can be used into the operating system scheduling or the hardware controller design. It is based on the fuzzy inference system (FIS) to derive answers from a knowledge base with a fuzzy inference engine and the rules are taken deadline, laxity and interval into account. The experiments and results show that the algorithm can improve the performance of the overall multi-core threading execution.
Keywords :
fuzzy set theory; inference mechanisms; knowledge based systems; multi-threading; processor scheduling; resource allocation; fuzzy inference system; hardware controller design; knowledge base; load balancing; multicore processor; multicore threading execution; operating system scheduling; parallelizability evaluation; real-time thread scheduling; Fuzzy control; Fuzzy systems; Hardware; Inference algorithms; Multicore processing; Operating systems; Processor scheduling; Real time systems; Scheduling algorithm; Yarn;
Conference_Titel :
Granular Computing, 2008. GrC 2008. IEEE International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4244-2512-9
Electronic_ISBN :
978-1-4244-2513-6
DOI :
10.1109/GRC.2008.4664678
