A Fuzzy algorithm for parallelizability evaluation and load balance on the multi-core processor
Hongjun Dai, XinShun Xu, Zhiping Jia · 2008
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.