IMPACCT: Methodology and tools for power-aware embedded systems

被引:7
|
作者
Chou, PH [1 ]
Liu, JF [1 ]
Li, DX [1 ]
Bagherzadeh, N [1 ]
机构
[1] Univ Calif Irvine, Dept Elect & Comp Engn, Irvine, CA 92697 USA
关键词
power-aware scheduling; power mode selection; system-level power management;
D O I
10.1023/A:1019730322551
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Power-aware systems are those that must exploit a wide range of power/performance trade-offs in order to adapt to the power availability and application requirements. They require the integration of many novel power management techniques, ranging from voltage scaling to subsystem shutdown. However, those techniques do not always compose synergistically with each other; in fact, they can combine subtractively and often yield counterintuitive, and sometimes incorrect, results in the context of a complete system. This can become a serious problem as more of these power aware systems are being deployed in mission critical applications. To address the problem of technique integration for power-aware embedded systems, we propose a new design tool framework called IMPACCT and the associated design methodology. The system modeling methodology includes application model for capturing timing/power constraints and mode dependencies at the system level. The tool performs power-aware scheduling and mode selection to ensure that all timing/power constraints are satisfied and that all overhead is taken into account. IMPACCT then synthesizes the implementation targeting a symmetric multiprocessor platform. Experimental results show that the increased dynamic range of power/performance settings enabled a Mars rover to achieve significant acceleration while using less energy. More importantly, our tool correctly combines the state-of-the-art techniques at the system level, thereby saving even experienced designers from many pitfalls of system-level power management.
引用
收藏
页码:205 / 232
页数:28
相关论文
共 50 条
  • [41] Power-aware epidemics
    van Renesse, R
    21ST IEEE SYMPOSIUM ON RELIABLE DISTRIBUTED SYSTEMS, PROCEEDINGS, 2002, : 358 - 361
  • [42] Power-aware placement
    Cheon, Y
    Ho, PH
    Kahng, AB
    Reda, S
    Wang, QK
    42ND DESIGN AUTOMATION CONFERENCE, PROCEEDINGS 2005, 2005, : 795 - 800
  • [43] A Power-Aware Online Scheduling Algorithm for Streaming Applications in Embedded MPSoC
    Sassolas, Tanguy
    Ventroux, Nicolas
    Boudouani, Nassima
    Blanc, Guillaume
    INTEGRATED CIRCUIT AND SYSTEM DESIGN: POWER AND TIMING MODELING, OPTIMIZATION AND SIMULATION, 2011, 6448 : 1 - 10
  • [44] API for Power-Aware Application Design on Mobile Systems
    Peters, N.
    Park, S.
    Clifford, D.
    Kyostila, S.
    McIlroy, R.
    Meurer, B.
    Payer, H.
    Chakraborty, S.
    2018 IEEE/ACM 5TH INTERNATIONAL CONFERENCE ON MOBILE SOFTWARE ENGINEERING AND SYSTEMS (MOBILESOFT), 2018, : 90 - 91
  • [45] POWER-AWARE DESIGN TECHNIQUE FOR PAC DUO BASED EMBEDDED SYSTEM
    Wen, Shui-An
    Lin, Huang-Lun
    Wu, Chi
    Chen, Chun-Chin
    Tsai, Kun-Hsien
    Cheng, Wei-Min
    2011 IEEE INTERNATIONAL SOC CONFERENCE (SOCC), 2011, : 132 - 135
  • [46] Low-voltage memories for power-aware systems
    Itoh, K
    ISLPED'02: PROCEEDINGS OF THE 2002 INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN, 2002, : 1 - 6
  • [47] Power-Aware Speed Scaling in Processor Sharing Systems
    Wierman, Adam
    Andrew, Lachlan L. H.
    Tang, Ao
    IEEE INFOCOM 2009 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS, VOLS 1-5, 2009, : 2007 - +
  • [48] A Power-Aware Multi-Level Cache Organization Effective for Multi-Core Embedded Systems
    Abu Asaduzzaman
    JOURNAL OF COMPUTERS, 2013, 8 (01) : 49 - 60
  • [49] Novel Power-Aware Optimization Methodology and Efficient Task Scheduling Algorithm
    Kumar, K. Sathis
    Paramasivam, K.
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2022, 41 (01): : 209 - 224
  • [50] A Methodology for Automated Consistency Checking Between Different Power-Aware Descriptions
    Kalsing, Arthur
    Fesquet, Laurent
    Aktouf, Chouki
    LANGUAGES, DESIGN METHODS, AND TOOLS FOR ELECTRONIC SYSTEM DESIGN, 2019, 530 : 107 - 127