Quantification and Localization of Cross-Core Interference for Embedded Multi-Core Control Applications

被引:0
|
作者
Wagner, Eric [1 ]
Karls, Christoph [2 ]
Lehser, Martina [2 ]
机构
[1] Saarland Univ, Lab Actuat Technol, Htw Saar, Sch Engn, Saarbrucken, Germany
[2] Saarland Univ Appl Sci, Sch Engn, Saarbrucken, Germany
关键词
Embedded; Multi-Core; Interference; Control System;
D O I
10.1145/3185089.3185095
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper presents an analysis approach to the quantification and localization of multi-core interference for applications controlling mechatronic systems. The analysis focuses on the execution of several control applications, each dedicated to one core of an embedded multi-core microprocessor. Based on timed instruction traces for the single-core execution of each application, we first extract a bus access trace under consideration of an out-of-order execution of store instructions. The bus access trace is then used to calculate the cross-core contentions for each instruction. The calculation uses time characteristics of the applications emerging from the design of the control of physical systems. The analysis approach integrates hardware-related timings to apply the analysis to a wide range of multi-core microcontrollers. Experimental results indicate accuracy between 93.83% and 99.93% of the calculated quantity of cross-core contentions. The contention data can be used to determine multi-core runtimes and build contention traces for the application execution. To reduce cross-core contentions and maintain the real-time behavior of control applications, the obtained contention information contributes to further analyses for the application design, implementation and integration processes.
引用
收藏
页码:189 / 193
页数:5
相关论文
共 50 条
  • [1] Analyzing cross-core performance interference on multi-core processors based on statistical learning
    Zhao, Jia-Cheng
    Cui, Hui-Min
    Feng, Xiao-Bing
    Ruan Jian Xue Bao/Journal of Software, 2013, 24 (11): : 2558 - 2570
  • [2] Application performance prediction method based on cross-core performance interference on multi-core processor
    Guo, Jun
    Ma, Anxiang
    Yan, Yongming
    Zhang, Bin
    MICROPROCESSORS AND MICROSYSTEMS, 2016, 47 : 112 - 120
  • [3] Embedded multi-core computing and applications
    Che-Lun Hung
    Frédéric Magoulès
    Meikang Qiu
    Robert C. Hsu
    Chun-Yuan Lin
    The Journal of Supercomputing, 2017, 73 : 3327 - 3332
  • [4] Embedded multi-core computing and applications
    Hung, Che-Lun
    Magoules, Frederic
    Qiu, Meikang
    Hsu, Robert C.
    Lin, Chun-Yuan
    JOURNAL OF SUPERCOMPUTING, 2017, 73 (08): : 3327 - 3332
  • [5] Applied static analysis and specialization of cross-core syscalls for multi-core AUTOSAR OS
    Entrup, Gerion
    Kaessens, Andreas
    Fiedler, Bjoern
    Lohmann, Daniel
    REAL-TIME SYSTEMS, 2024, : 491 - 533
  • [6] Multi-Core/Multi-IP Technology for Embedded Applications
    Irie, Naohiko
    Hattori, Toshihiro
    IEICE TRANSACTIONS ON ELECTRONICS, 2009, E92C (10): : 1232 - 1239
  • [7] Identification of multi-core interference
    Boniol, Frederic
    Pagetti, Claire
    Sensfelder, Nathanael
    201919TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH ASSURANCE SYSTEMS ENGINEERING (HASE 2019), 2019, : 98 - 106
  • [8] Multi-Core Embedded Wireless Sensor Networks: Architecture and Applications
    Munir, Arslan
    Gordon-Ross, Ann
    Ranka, Sanjay
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2014, 25 (06) : 1553 - 1562
  • [9] Development of Heterogeneous Multi-core Embedded Platform for Automotive Applications
    Wei, Ting-Ying
    Qiu, Zhi-Liang
    Young, Chung-Ping
    Chang, Da-Wei
    CIRCUITS, SYSTEM AND SIMULATION, 2011, 7 : 193 - 197
  • [10] Predicting Cross-Core Performance Interference on Multicore Processors with Regression Analysis
    Zhao, Jiacheng
    Cui, Huimin
    Xue, Jingling
    Feng, Xiaobing
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2016, 27 (05) : 1443 - 1456