摘要
针对嵌入式多核平台下分区调度算法不能满足系统高效的需求,提出一种三维立体调度模型,该模型根据任务各项参数将任务划分为可调和任务和不可调和任务,并将其执行区域用面积表示,根据区域的特征分为执行区域、干扰区以及空闲区。利用干扰区的特征将不同性质的任务分派到不同的处理器核上运行。实验表明,该方法无论在提高系统利用率还是在吞吐量方面都优于PEDF。
This paper proposes a new three-dimensional scheduling model which can divide the tasks into harmonic tasks and non-harmonic tasks for the high demands of embedded mucticne plactorim. According to the characteristic parameters of the tasks and make the value of the rectangular area as the attribute of the execution region which is divided into executive region,interference region and free region with the characteristic of the area. By using these attributes of the different region,the tasks are allocated to different cores. Experimental results show that the proposed method is more fully optimizing the system utilization and throughput than PEDF.
引文
[1] Tong G,Liu C. Supporting Soft Real-Time Sporadic Task Systems on Uniform Heterogeneous Multiprocessors with No Utilization Loss[J]. IEEE Trans on Parallel and Distributed Systems,2016,27(9):2740-2752
[2]康鹏,刘从新,沈绪榜.一种基于分组的多核嵌入式实时调度算法[J].微电子学与计算机,2016,33(10):32-35Kang Peng,Liu Congxin,Shen Xubang. Multicore Embedded Real-Time Scheduling Algorithm Based on Gang Scheduling[J].Microelectronics&Computer,2016,33(10):32-35(in Chinese)
[3] Giovani Gracioli,Real-Time Operating System Support for Multicore Application[D]. Universidade Federal de Santa Catarina,2014
[4] Yang K,Anderson J H. On the Soft Real-Time Optimality of Global EDF on Multiprocessors:from Identical to Uniform Heterogeneous[C]∥Proceedings of the 21st IEEE International Conference on Embedded and Real-Time Computing Systems and Applications,Hong Kong,China,2015:1-10
[5] Baruah S,Bonifaci V,Marchetti-Spaccamela A. The Global EDF Scheduling of Systems of Conditional Sporadic DAG Tasks[C]∥Proceedings of the 27th Euromicro Conference on Real-Time Systems,Lund,Sweden,2015:222-231
[6] Zhang Y,Guo Z,Wang L,et al. Integrating Cache-Related Preemption Delay into GEDF Analysis for Multiprocessor Scheduling with On-Chip Cache[C]∥Proceedings of the The 14th IEEE International Conference on Embedded Software and Systems Sydney,Australia,2017:815-822
[7] Rhaiem G,Gharsellaoui H,Ahmed S B. A Novel Proposed Approach for Real-Time Scheduling Based on Neural Networks Approach with Minimization of Power Consumption[C]∥Proceeings of the 2016 World Symposium on Computer Applications&Research(WSCAR),Cairo,Egypt,2016:98-103
[8]谷传才,关楠,于金铭,等.多处理器混合关键性系统中的划分调度策略[J].软件学报,2014,25(2):284-297Gu Chuancai,Guan Nan,Yu Jinming,et al. Partitioned Scheduling Policies on Multi-Processor Mixed-Criticality Systems[J].Journal of Software,2014,25(2):284-297(in Chinese)
[9] Xi Sisu,Xu Meng,Lu Chenyang,et al. Christopher Gill,Oleg Sokolsky,Insup Lee,Real-Time Multi-Core Virtual Machine Scheduling in Xen[C]∥Proceedings of the International Conference on in Embedded Software(EMSOFT),New Delhi,India,2014:1-10
[10]Abusayeed Saifullah,David Ferry,Jing Li,et al. Parallel Real-Time Scheduling of DAGs[J]. IEEE Trans on Parallel and Distributed Systems,2014,12(25):3242-3252
[11]Liy Jing,Chenx Jianjia,Kunal Agrawaly,et al. Analysis of Federated and Global Scheduling for Parallel Real-Time Tasks[C]∥Proceedings of the 26th Euromicro Conference on Real-Time Systems(ECRTS),Madrid,Spain 2014:85-96
[12]Saranya N,Hansdah R C. Dynamic Partitioning Based Scheduling of Real-Time Tasks in Multicore Processors[C]∥Proceedings of the IEEE 18th International Symposium on Real-Time Distributed Computing,Auckland,New Zealand,2015:190-197
[13]James H Anderson,Jeremy P Erickson,Uma Maheswari C Devi,et al. Optimal Semi-Partitioned Scheduling in Soft Real-Time Systems[C]∥Proceedings of the 20th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications(RTCSA),Chongqing,China,2014:1-16