Accurate Modeling of the Delay and Energy Overhead of Dynamic Voltage and Frequency Scaling in Modern Microprocessors

被引:81
|
作者
Park, Sangyoung [1 ]
Park, Jaehyun [1 ]
Shin, Donghwa [2 ]
Wang, Yanzhi [3 ]
Xie, Qing [3 ]
Pedram, Massoud [3 ]
Chang, Naehyuck [1 ]
机构
[1] Seoul Natl Univ, Seoul 151744, South Korea
[2] Politecn Torino, I-10129 Turin, Italy
[3] Univ So Calif, Los Angeles, CA 90089 USA
基金
新加坡国家研究基金会; 美国国家科学基金会;
关键词
Delay and energy overhead; dynamic voltage and frequency scaling (DVFS); macromodel; POWER MANAGEMENT; DC;
D O I
10.1109/TCAD.2012.2235126
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Dynamic voltage and frequency scaling (DVFS) has been studied for well over a decade. Nevertheless, existing DVFS transition overhead models suffer from significant inaccuracies; for example, by incorrectly accounting for the effect of DC-DC converters, frequency synthesizers, voltage, and frequency change policies on energy losses incurred during mode transitions. Incorrect and/or inaccurate DVFS transition overhead models prevent one from determining the precise break-even time and thus forfeit some of the energy saving that is ideally achievable. This paper introduces accurate DVFS transition overhead models for both energy consumption and delay. In particular, we redefine the DVFS transition overhead including the underclocking-related losses in a DVFS-enabled microprocessor, additional inductor IR losses, and power losses due to discontinuous-mode DC-DC conversion. We report the transition overheads for a desktop, a mobile and a low-power representative processor. We also present DVFS transition overhead macromodel for use by high-level DVFS schedulers.
引用
收藏
页码:695 / 708
页数:14
相关论文
共 50 条
  • [1] Dynamic Voltage and Frequency Scaling Under an Accurate System Energy Model
    Xu Shen
    Li Junsong
    Jiang Jianfeng
    [J]. SMART MATERIALS AND INTELLIGENT SYSTEMS, 2012, 442 : 321 - +
  • [2] Energy-aware clock-frequency assignment in microprocessors and memory devices for dynamic voltage scaling
    Cho, Youngjin
    Chang, Naehyuck
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2007, 26 (06) : 1030 - 1040
  • [3] Monitoring of cache miss rates for accurate dynamic voltage and frequency scaling
    Singleton, L
    Poellabauer, C
    Schwan, K
    [J]. Multimedia Computing and Networking 2005, 2005, 5680 : 121 - 125
  • [4] Compiler-directed dynamic voltage/frequency scheduling for energy reduction in microprocessors
    Hsu, CH
    Kremer, U
    Hsiao, M
    [J]. ISLPED'01: PROCEEDINGS OF THE 2001 INTERNATIONAL SYMPOSIUM ON LOWPOWER ELECTRONICS AND DESIGN, 2001, : 275 - 278
  • [5] Enabling Dynamic Voltage & Frequency Scaling In Next-Generation Microprocessors: Thermal & Reliability Considerations
    Ankireddi, Sai
    Copeland, David
    [J]. IEEE 9TH VLSI PACKAGING WORKSHOP IN JAPAN, 2008, : 35 - 38
  • [6] Dynamic Voltage and Frequency Scaling Over Delay Constrained Mobile Multimedia Service
    Yun, Jihyeok
    Park, Kyungmo
    Suh, Doug Young
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2013, : 414 - 417
  • [7] Adaptive voltage scaling and dynamic voltage frequency
    King, Oliver
    [J]. ELECTRONICS WORLD, 2017, 123 (1970): : 19 - 19
  • [8] A Modeling Framework for NBTI Degradation Under Dynamic Voltage and Frequency Scaling
    Parihar, Narendra
    Goel, Nilesh
    Chaudhary, Ankush
    Mahapatra, Souvik
    [J]. IEEE TRANSACTIONS ON ELECTRON DEVICES, 2016, 63 (03) : 946 - 953
  • [9] An accurate model for soft error rate estimation considering dynamic voltage and frequency scaling effects
    Firouzi, Farshad
    Salehi, Mostafa E.
    Wang, Fan
    Fakhraie, Sied Mehdi
    [J]. MICROELECTRONICS RELIABILITY, 2011, 51 (02) : 460 - 467
  • [10] Dynamic Voltage and Frequency Scaling to Improve Energy-Efficiency of Hardware Accelerators
    Liu, Siqin
    Karanth, Avinash
    [J]. 2021 IEEE 28TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING, DATA, AND ANALYTICS (HIPC 2021), 2021, : 232 - 241