Performance Evaluation and Energy Consumption for DVFS Processor

被引:0
|
作者
El Mahjoub, Youssef Ait [1 ,2 ]
Fourneau, Jean-Michel [1 ]
Castel-Taleb, Hind [2 ]
机构
[1] Univ Paris Saclay, DAVID UVSQ, Paris, France
[2] Inst Polytech Paris, Telecom SudParis, SAMOVAR, Paris, France
关键词
DVFS; Performance evaluation; Energy consumption; Stochastic comparison;
D O I
10.1007/978-3-030-91825-5_10
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Dynamic Voltage and Frequency Scaling (DVFS) involves adjusting the speed to match power consumption and performance requirements of the system. This technology has been shown to provide major power and energy savings in many system components (processor cores, memory system ...). In this work, we study the DVFS mechanism for a processor that implements various levels of speed and power (we call these levels "Pstates"). We model the system as a birth-death process and we compare different configurations, using stochastic comparison, in order to evaluate the impact on the response time and power (and energy) consumption. In the case of two Pstates, we proposed a closed form for the steady state distribution and we derived a cost function that uses both performance and energy consumption. Finally, we derive an algorithm that suggests a threshold which minimizes the cost function.
引用
收藏
页码:165 / 180
页数:16
相关论文
共 50 条
  • [1] Improving Processor Lifespan and Energy Consumption Using DVFS Based on ILP Monitoring
    Xu, Shikang
    Koren, Israel
    Krishna, C. M.
    2015 SIXTH INTERNATIONAL GREEN COMPUTING CONFERENCE AND SUSTAINABLE COMPUTING CONFERENCE (IGSC), 2015,
  • [2] Adaptive Resource Scheduling for Energy Efficient QRD Processor with DVFS
    Liu, Yangxurui
    Prabhu, Hemanth
    Liu, Liang
    Owall, Viktor
    2015 IEEE INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING SYSTEMS (SIPS 2015), 2015,
  • [3] Performance analysis of DVS algorithms for reducing processor energy consumption
    Chilambuchelvan, A.
    Saravanan, S.
    Perinbam, J. Raja Paul
    ICCIMA 2007: INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND MULTIMEDIA APPLICATIONS, VOL II, PROCEEDINGS, 2007, : 174 - +
  • [4] Hybrid technique for reducing energy consumption in high performance embedded processor
    Shim, S
    Kim, CH
    Kwak, JW
    Jhon, CS
    EMBEDDED AND UBIQUITOUS COMPUTING, PROCEEDINGS, 2004, 3207 : 74 - 84
  • [5] DV-DVFS: merging data variety and DVFS technique to manage the energy consumption of big data processing
    Ahmadvand, Hossein
    Foroutan, Fouzhan
    Fathy, Mahmood
    JOURNAL OF BIG DATA, 2021, 8 (01)
  • [6] DV-DVFS: merging data variety and DVFS technique to manage the energy consumption of big data processing
    Hossein Ahmadvand
    Fouzhan Foroutan
    Mahmood Fathy
    Journal of Big Data, 8
  • [7] Adaptive and Polymorphic VLIW Processor to Optimize Fault Tolerance, Energy Consumption, and Performance
    Sartor, Anderson L.
    Lorenzon, Arthur F.
    Kundu, Sandip
    Koren, Israel
    Beck, Antonio C. S.
    2018 ACM INTERNATIONAL CONFERENCE ON COMPUTING FRONTIERS, 2018, : 54 - 61
  • [8] Performance Evaluation of Opportunistic Downclocking in Energy Consumption
    Wang, Zhimin
    Zhao, Qinglin
    Xu, Fangxin
    2018 INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING (CSSE 2018), 2018, : 157 - 164
  • [9] REDUCING PROCESSOR ENERGY CONSUMPTION BY COMPILER OPTIMIZATION
    Guzma, Vladimir
    Pitkanen, Teemu
    Kellomaki, Pertti
    Takala, Jarmo
    SIPS: 2009 IEEE WORKSHOP ON SIGNAL PROCESSING SYSTEMS, 2009, : 63 - 68
  • [10] Energy/performance evaluation of the multithreaded extension of a multicluster VLIW processor.
    Barretta, D
    Palermo, G
    Sami, M
    Zafalon, R
    CAMP 2005: SEVENTH INTERNATIONAL WORKSHOP ON COMPUTER ARCHITECTURE FOR MACHINE PERCEPTION , PROCEEDINGS, 2005, : 265 - 270