CoScale: Coordinating CPU and Memory System DVFS in Server Systems

被引:107
|
作者
Deng, Qingyuan [1 ]
Meisner, David
Bhattacharjee, Abhishek [1 ]
Wenisch, Thomas F.
Bianchini, Ricardo [1 ]
机构
[1] Rutgers State Univ, Piscataway, NJ 08855 USA
关键词
D O I
10.1109/MICRO.2012.22
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Recent work has introduced memory system dynamic voltage and frequency scaling (DVFS), and has suggested that balanced scaling of both CPU and the memory system is the most promising approach for conserving energy in server systems. In this paper, we first demonstrate that CPU and memory system DVFS often conflict when performed independently by separate controllers. In response, we propose CoScale, the first method for effectively coordinating these mechanisms under performance constraints. CoScale relies on execution profiling of each core via (existing and new) performance counters, and models of core and memory performance and power consumption. CoScale explores the set of possible frequency settings in such a way that it efficiently minimizes the full-system energy consumption within the performance bound. Our results demonstrate that, by effectively coordinating CPU and memory power management, CoScale conserves a significant amount of system energy compared to existing approaches, while consistently remaining within the prescribed performance bounds. The results also show that CoScale conserves almost as much system energy as an offline, idealized approach.
引用
收藏
页码:143 / 154
页数:12
相关论文
共 50 条
  • [1] Power Capping of CPU-GPU Heterogeneous Systems through Coordinating DVFS and Task Mapping
    Komoda, Toshiya
    Hayashi, Shingo
    Nakada, Takashi
    Miwa, Shinobu
    Nakamura, Hiroshi
    2013 IEEE 31ST INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD), 2013, : 349 - 356
  • [2] Combine Dynamic Time-slice Scaling with DVFS for Coordinating Thermal and Fairness on CPU
    Jia, Gangyong
    Han, Guangjie
    2014 IEEE COMPUTING, COMMUNICATIONS AND IT APPLICATIONS CONFERENCE (COMCOMAP), 2014, : 50 - 55
  • [3] DVFS method of memory hierarchy based on CPU microarchitectural information
    Park, Bumgyu
    Park, Jonglae
    Joo, Hyunwook
    Park, Choonghoon
    Lee, Daeyeong
    Jo, Chulmin
    Hur, Woonhaing
    2022 29TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS (IEEE ICECS 2022), 2022,
  • [4] CPU-GPU-Memory DVFS for Power-Efficient MPSoC in Mobile Cyber Physical Systems
    Dey, Somdip
    Isuwa, Samuel
    Saha, Suman
    Singh, Amit Kumar
    McDonald-Maier, Klaus
    FUTURE INTERNET, 2022, 14 (03)
  • [5] Coordinating VMs' Memory Demand Heterogeneity and Memory DVFS for Energy-efficient VMs Consolidation
    Takouna, Ibrahim
    Meinel, Christoph
    2014 IEEE INTERNATIONAL CONFERENCE (ITHINGS) - 2014 IEEE INTERNATIONAL CONFERENCE ON GREEN COMPUTING AND COMMUNICATIONS (GREENCOM) - 2014 IEEE INTERNATIONAL CONFERENCE ON CYBER-PHYSICAL-SOCIAL COMPUTING (CPS), 2014, : 478 - 485
  • [6] JOSS: Joint Exploration of CPU-Memory DVFS and Task Scheduling for Energy Efficiency
    Chen, Jing
    Manivannan, Madhavan
    Goel, Bhavishya
    Pericas, Miguel
    PROCEEDINGS OF THE 52ND INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, ICPP 2023, 2023, : 828 - 838
  • [7] Memory-aware Cooperative CPU-GPU DVFS Governor for Mobile Games
    Hsieh, Chen-Ying
    Park, Jurn-Gyu
    Dutt, Nikil
    Lim, Sung-Soo
    2015 13TH IEEE SYMPOSIUM ON EMBEDDED SYSTEMS FOR REAL-TIME MULTIMEDIA, 2015, : 113 - 120
  • [8] Energy Efficient Job Scheduling with DVFS for CPU-GPU Heterogeneous Systems
    Chau, Vincent
    Chu, Xiaowen
    Liu, Hai
    Leung, Yiu-Wing
    PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON FUTURE ENERGY SYSTEMS (E-ENERGY'17), 2017, : 1 - 11
  • [9] Predicting Performance Impact of DVFS for Realistic Memory Systems
    Miftakhutdinov, Rustam
    Ebrahimi, Eiman
    Patt, Yale N.
    2012 IEEE/ACM 45TH INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE (MICRO-45), 2012, : 155 - 165
  • [10] CNN Workloads Characterization and Integrated CPU-GPU DVFS Governors on Embedded Systems
    Karzhaubayeva, Meruyert
    Amangeldi, Aidar
    Park, Jurn-Gyu
    IEEE EMBEDDED SYSTEMS LETTERS, 2023, 15 (04) : 202 - 205