计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 3081-3087.DOI: 10.11772/j.issn.1001-9081.2020010118

• 应用前沿、交叉与综合 • 上一篇    下一篇

基于机器学习的异构感知多核调度方法

安鑫1,2, 康安1,2, 夏近伟1,2, 李建华1,2, 陈田1,2, 任福继1,2   

  1. 1. 合肥工业大学 计算机与信息学院, 合肥 230601;
    2. 情感计算与先进智能机器安徽省重点实验室(合肥工业大学), 合肥 230601
  • 收稿日期:2020-02-15 修回日期:2020-05-11 出版日期:2020-10-10 发布日期:2020-05-12
  • 通讯作者: 安鑫
  • 作者简介:安鑫(1987-),男,山东潍坊人,副教授,博士,CCF会员,主要研究方向:嵌入式系统、机器学习;康安(1995-),男,河北邢台人,硕士研究生,主要研究方向:嵌入式软件;夏近伟(1994-),男,安徽合肥人,硕士研究生,主要研究方向:嵌入式软件;李建华(1985-),男,安徽肥西人,副教授,博士,主要研究方向:计算机体系结构、非易失性存储器;陈田(1974-),女,安徽合肥人,副教授,博士,CCF高级会员,主要研究方向:超大规模集成电路/系统芯片低功耗测试、可穿戴计算;任福继(1959-),男,四川南充人,教授,博士,主要研究方向:信号与信息处理、计算机视觉。
  • 基金资助:
    国家自然科学基金资助项目(U1613217);中央高校基本科研业务费专项资金资助项目(JZ2020YYPY0092)。

Heterogeneous sensing multi-core scheduling method based on machine learning

AN Xin1,2, KANG An1,2, XIA Jinwei1,2, LI Jianhua1,2, CHEN Tian1,2, REN Fuji1,2   

  1. 1. School of Computer Science and Information Engineering, Hefei University of Technology, Hefei Anhui 230601, China;
    2. Anhui Key Laboratory of Affective Computing and Advanced Intelligent Machine(Hefei University of Technology), Hefei Anhui 230601, China
  • Received:2020-02-15 Revised:2020-05-11 Online:2020-10-10 Published:2020-05-12
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (U1613217), the Fundamental Research Funds for the Central Universities (JZ2020YYPY0092).

摘要: 异构多核处理器已成为现代嵌入式系统的主流解决方案,而好的在线映射或调度方法对其充分发挥高性能和低功耗的优势起着至关重要的作用。针对异构多核处理系统上的应用程序动态映射和调度问题,提出一种基于机器学习、能快速准确评估程序性能和程序行为阶段变化的检测技术来有效确定重映射时机从而最大化系统性能的映射和调度解决方案。该方案一方面通过合理选择处理核和程序运行时的静态和动态特征来有效感知异构处理所带来的计算能力和工作负载运行行为的差异,从而能够构建更加准确的预测模型;另一方面通过引入阶段检测来尽可能减少在线映射计算的次数,从而能够提供更加高效的调度方案。最后,在SPLASH-2数据集上验证了所提出调度方案的有效性。实验结果表明,与Linux默认的完全公平调度(CFS)方法相比,所提出的方法在系统计算性能方面提高了52%,在CPU资源利用率上提高了9.4%。这表明所提方法在系统计算性能和CPU资源利用率方面具备优良的性能,可以有效提升异构多核系统的应用动态映射和调度效果。

关键词: 异构多核处理系统, 动态映射和调度, 机器学习, 性能预测, 阶段检测

Abstract: Heterogeneous multi-core processor is the mainstream solution for modern embedded systems now. Good online mapping or scheduling approaches play important roles in improving their advantages of high performance and low power consumption. To deal with the problem of dynamic mapping and scheduling of applications on heterogeneous multi-core processing systems, a dynamic mapping and scheduling solution was proposed to effectively determine remapping time in order to maximize the system performance by using the machine learning based detection technology of quickly and accurately evaluating program performance and program behavior phase change. In this solution, by carefully selecting the static and dynamic features of processing cores and programs to running to effectively detect the difference in computing power and workload running behaviors brought by heterogeneous processing, a more accurate prediction model was built. At the same time, by introducing phase detection technology, the number of online mapping computations was reduced as much as possible, so as to provide more efficient scheduling scheme. Finally, the effectiveness of the proposed scheduling scheme was verified on the SPLASH-2 dataset. Experimental results showed that, compared to the Completely Fair Scheduler (CFS) of Linux, the proposed method achieved about 52% computing performance gains and 9.4% improvement on CPU resource utilization rate. It shows that the proposed method has excellent performance in system computing performance and processor resource utilization, and can effectively improve the dynamic mapping and scheduling effect of applications of heterogeneous multi-core systems.

Key words: heterogeneous multi-core system, dynamic mapping and scheduling, machine learning, performance prediction, phase detection

中图分类号: