期刊文献+

通用图形处理器功耗估算模型 被引量:2

Power Estimation Model of General Purpose Graphics Processing Unit
下载PDF
导出
摘要 为精准快速地获得GPU功耗数据,提出一种基于硬件性能计数事件的通用图形处理器(GPGPU)功耗估算方法。通过分析GPGPU程序运行时的功耗分布情况,选择一组与应用程序运行功耗密切相关的硬件性能计数事件集合,使用反向传播人工神经网络分析硬件性能计数事件与实时功耗间的关系,最终建立GPGPU功耗估算模型。实验结果表明,与多元线性回归的功耗估算模型相比,该模型具有更高的估算准确性和通用性。 In order to get the GPU power data quickly and accurately,this paper proposes a General Purpose Graphics Processing Unit(GPGPU) power estimation model based on hardware performance counting events.Through analysing power distribution during GPGPU program running,it selects a set of performance events which are closely related to application program running power.Then it figures out the relationship between hardware performance counting events and realtime power using Back Propagation Atificial Neural Network(BP—ANN).Finally,it builds a GPGPU power estimation model.Experimental results indicate that compared with the Multiple Linear Regression(MLR) power estimation model,the proposed model has higher estimation accuracy and versatility.
作者 王吉军 程华
出处 《计算机工程》 CAS CSCD 北大核心 2017年第2期92-97,104,共7页 Computer Engineering
关键词 通用图形处理器 硬件性能计数事件 反向传播人工神经网络 交叉验证 功耗估算 General Purpose Graphics Processing Unit(GPGPU) hardware performance counting event Back Propagation Atificial Neural Network(BP-ANN) cross-validation power estimation
  • 引文网络
  • 相关文献

参考文献4

二级参考文献40

  • 1TOP500SuperComputer[EB/OL].[2010-11-15].http://www.top500.org/lists/2010/11.
  • 2Collange S,Defour D,Tisserand A.Power Consumption of GPUs from a Software Perspective[C]∥Proc of the9th International Conference on Computational Science,2009:914-923.
  • 3Huang S,Xiao S,Feng W.On the Energy Efficiency of Graphics Processing Units for Scientific Computing[C]∥Proc of the2009IEEE International Symposium on Parallel&Distributed Processing,2009.
  • 4Takizawa H,Sato1K,Kobayashi H.SPRAT:Runtime Processor Selection for Energy-aware Computing[C]∥Proc of the Third International Workshop on Automatic Perform-ance Tuning,2008:386-393.
  • 5AMD Corp.AMD Accelerated Parallel Processing OpenCL Programming Guide[R].2010.
  • 6AMD Fusion Family of APUs Technology Overview[EB/OL].[2011-03-15].http://sites.amd.com/us/fusion/apu/Pages/fusion.aspx.
  • 7Lee B C,Brooks D M.Accurate and Efficient Regression Modeling for Microarchitectural Performance and Power Prediction[C]∥Proc of the12th International Conference on Architectural Support for Programming Languages and Op-erating Systems,2006:185-194.
  • 8AMD Display Library SDK[EB/OL].[2010-03-15].http://developer.amd.com/gpu/adlsdk/Pages/default.aspx.
  • 9Roy K,Prasad S.Low Power CMOS VLSI Circuit Design[M].New York:Wiley Interscience,2000.
  • 10Mukhopadhyay S,Raychowdhury A,Roy K.Accurate Estimation of Total Leakage Current in Scaled CMOS Logic Circuits Based on Compact Current Modeling[C].DAC'03,Anaheim,California,USA,2003:169-174.

共引文献14

同被引文献14

引证文献2

二级引证文献8

相关主题

;
使用帮助 返回顶部