Thermal Status and Workload Prediction Using Support Vector Regression

被引:0
作者
Stockman, Mel [1 ]
Awad, Mariette [1 ]
Akkary, Haitham [1 ]
Khanna, Rahul [2 ]
机构
[1] Amer Univ Beirut, Elect & Comp Engn Dept, Beirut, Lebanon
[2] Intel Corp, Portland, OR USA
来源
2012 INTERNATIONAL CONFERENCE ON ENERGY AWARE COMPUTING | 2012年
关键词
Support Vector Regression; Processor Thermal Status Prediction; Workload Prediction; MANAGEMENT;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Because knowing information about the currently running workload and the thermal status of the processor is of importance for more adequate planning and allocating resources in microprocessor environments, we propose in this paper using support vector regression (SVR) to predict future processor thermal status as well as the currently running workload. We build two generalized SVR models trained with data from monitoring hardware performance counters collected from running SPEC2006 benchmarks. The first model predicts the Central Processing Unit's thermal status in Celsius with a percentage error of less than 10%. The second model predicts the current workload with a percentage error of 0.08% for a heterogeneous training set of 6 different integer and floating point benchmark workloads. Cross validation for the two models show the effectiveness of our approach and motivate follow on research.
引用
收藏
页数:5
相关论文
共 11 条
  • [1] LIBSVM: A Library for Support Vector Machines
    Chang, Chih-Chung
    Lin, Chih-Jen
    [J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
  • [2] Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482
  • [3] Cochran R, 2010, DES AUT CON, P62
  • [4] Utilizing Predictors for Efficient Thermal Management in Multiprocessor SoCs
    Coskun, Ayse Kivilcim
    Rosing, Tajana Simunic
    Gross, Kenny C.
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2009, 28 (10) : 1503 - 1516
  • [5] Gmach Daniel, 2007, 2007 IEEE International Symposium on Workload Characterization, P171, DOI 10.1109/IISWC.2007.4362193
  • [6] ε-SSVR:: A smooth support vector machine for ε-insensitive regression
    Lee, YJ
    Hsieh, WF
    Huang, CM
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (05) : 678 - 685
  • [7] Li T., 2007, INT S MICR MICRO
  • [8] Pedram M., 2008, P 21 INT C VLSI DES, P415
  • [9] Tzeng N. F., 2008, HOTPOWER 08
  • [10] Efficient power modeling and software thermal sensing for runtime temperature monitoring
    Wu, Wei
    Jin, Lingling
    Yang, Jun
    Liu, Pu
    Tan, Sheldon X. -D.
    [J]. ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2007, 12 (03)