Evaluation of Low-Power Computing when Operating on Subsets of Multicore Processors

被引:5
|
作者
Hamady, Faisal [1 ]
Kayssi, Ayman [1 ]
Chehab, Ali [1 ]
Mansour, Mohammad [1 ]
机构
[1] Amer Univ Beirut, Dept Elect & Comp Engn, Beirut, Lebanon
关键词
Low power computing; Mobile platforms; Power management;
D O I
10.1007/s11265-012-0697-z
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Given the accelerated growth in tablet devices, smartphones, and netbooks, designers are faced with serious challenges to meet the needs of mobility in terms of battery life and form factor. It is vital to investigate how to deliver the best mobile experience to users while ensuring adequate levels of performance. In this paper, we present a power management evaluation of multi-core processor systems by comparing thermal power, battery life, and performance when running different types of workloads under a limited number of cores. To show the potential gains from a system power management perspective, we have assessed a mobile platform featuring the Second Generation Intel Core i5 processor, and tested it on a wide selection of workloads and benchmarks. Experimental results show significant thermal power reduction (up to 40 %) in a variety of scenarios, while system performance was sustained in most cases but sacrificed in a few other uncommon situations.
引用
收藏
页码:193 / 208
页数:16
相关论文
共 50 条
  • [31] Implementing low-power configurable processors - Practical options and tradeoffs
    Wei, J
    Rowen, C
    42nd Design Automation Conference, Proceedings 2005, 2005, : 706 - 711
  • [32] A fresh look at low-power mobile computing
    Franz, M
    COMPILERS AND OPERATING SYSTEMS FOR LOW POWER, 2003, : 209 - 219
  • [33] A low-power image convolution algorithm for variable voltage processors
    Kwon, H
    Kim, J
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS: SPEECH II; INDUSTRY TECHNOLOGY TRACKS; DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS; NEURAL NETWORKS FOR SIGNAL PROCESSING, 2003, : 677 - 680
  • [34] The wearARM modular low-power computing core
    Lukowicz, P
    Anliker, U
    Tröster, G
    Schwartz, SJ
    DeVaul, RW
    IEEE MICRO, 2001, 21 (03) : 16 - 28
  • [35] Flash on disk for low-power multimedia computing
    Singleton, Leo
    Nathuji, Ripal
    Schwan, Karsten
    MULTIMEDIA COMPUTING AND NETWORKING 2007, 2007, 6504
  • [36] Nanoelectromechanical Switches for Low-Power Digital Computing
    Peschot, Alexis
    Qian, Chuang
    Liu, Tsu-Jae King
    MICROMACHINES, 2015, 6 (08): : 1046 - 1065
  • [37] Spinning Electrons to Attain Low-Power Computing
    Edwards, Chris
    COMMUNICATIONS OF THE ACM, 2024, 67 (08) : 8 - 10
  • [38] THE SMART CHOICE FOR LOW-POWER EMBEDDED COMPUTING
    ELECTRONICS WORLD, 2014, 120 (1942): : 30 - 32
  • [39] Low-power design strategies for mobile computing
    Prasad, AVSS
    Mathews, J
    Naganathan, N
    19TH INTERNATIONAL CONFERENCE ON VLSI DESIGN, PROCEEDINGS, 2005, : 3 - 4
  • [40] A Hybrid Instruction Prefetching Mechanism for Ultra Low-Power Multicore Clusters
    Payami, Maryam
    Azarkhish, Erfan
    Loi, Igor
    Benini, Luca
    IEEE EMBEDDED SYSTEMS LETTERS, 2017, 9 (04) : 125 - 128