Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (6): 1753-1759.DOI: 10.11772/j.issn.1001-9081.2018112311

• Advanced computing • Previous Articles     Next Articles

Machine learning based online mapping approach for heterogeneous multi-core processor system

AN Xin1,2, ZHANG Ying1,2, KANG An1,2, CHEN Tian1,2, LI Jianhua1,2   

  1. 1. School of Computer and Information, Hefei University of Technology, Hefei Anhui 230601, China;
    2. Anhui Provincial Key Laboratory of Affective Computing and Advanced Intelligent Machine(Hefei University of Technology), Hefei Anhui 230601, China
  • Received:2018-11-21 Revised:2019-01-07 Online:2019-06-10 Published:2019-06-17
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61502140, 61474035).


安鑫1,2, 张影1,2, 康安1,2, 陈田1,2, 李建华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
  • 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:嵌入式系统设计和验证、机器学习;张影(1994-),女,安徽亳州人,硕士研究生,主要研究方向:嵌入式系统、片上系统、机器学习;康安(1995-),男,河北邢台人,硕士研究生,主要研究方向:嵌入式软件及应用、机器学习;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、可测试性设计、可穿戴计算;李建华(1985-),男,安徽肥西人,副研究员,博士,主要研究方向:计算机体系结构、非易失性存储器、片上系统。
  • 基金资助:

Abstract: Heterogeneous Multi-core Processors (HMPs) platform has become the mainstream solution for modern embedded system design, and online mapping or scheduling plays a vital role in making full use of the advantages of high performance and low power consumption. Aiming at the dynamic mapping problem of application tasks in HMPs, a mapping and scheduling approach based on machine learning prediction model was proposed. On the one hand, a machine learning model was constructed to predict and evaluate the performance of different mapping strategies rapidly and efficiently, so as to provide support for online scheduling. On the other hand, the machine learning model was integrated with genetic algorithm to find out the optimal resource allocation strategy efficiently. Finally, an Motion-Join Photographic Experts Group (M-JPEG) decoder was used to verify the effectiveness of the proposed approach. The experimental results show that, compared with the Round Robin Scheduler (RRS) and sampling scheduling approaches, the proposed online mapping/scheduling approach has reduced the average execution time by about 19% and 28% respectively.

Key words: Heterogeneous Multi-core Processors (HMPs), machine learning, dynamic resource allocation, performance prediction, mapping and scheduling

摘要: 异构多核处理器(HMPs)平台已成为现代嵌入式系统的主流解决方案,其中在线映射或调度对充分发挥其高性能和低功耗的优势起着至关重要的作用。针对HMPs的应用任务动态映射问题,提出了一种基于机器学习预测模型的在线映射调度解决方案。一方面,构建了一个可以快速高效地预测和评估不同映射方案性能的机器学习模型,为在线调度提供支持;另一方面,将该机器学习模型整合到遗传算法中以高效地找到(接近)最优的资源分配方案。最后,通过一个M-JPEG解码器验证了所提方法的有效性。实验结果表明,该方法的平均执行时间相较于常见的轮询调度和抽样调度方法分别降低了28%和19%左右。

关键词: 异构多核处理器, 机器学习, 动态资源分配, 性能预测, 映射和调度

CLC Number: