Power-aware parallel loop scheduling method for heterogeneous system

被引：1
|
作者：
Wang G.-B. [1 ]
Yang X.-J. [1 ]
Xu X.-H. [1 ]
Lin Y.-S. [1 ]
Li X. [1 ]
机构：
[1] National Key Laboratory of Parallel and Distributed Processing, College of Computer, National University of Defense Technology
来源：
Ruan Jian Xue Bao/Journal of Software | 2011年 / 22卷 / 09期
关键词：
Heterogeneous system; Loop scheduling; OpenMP; Power optimization;
D O I：
10.3724/SP.J.1001.2011.03883
中图分类号：
学科分类号：
摘要：
Based on the OpenMP-like parallel program, a loop scheduling and dynamic voltage scaling technology is coordinated to optimize system power consumption under the given performance constraint. First, the basic model for power-aware loop scheduling on the heterogeneous system is presented. After that, through theoretical analysis, it has been concluded that the lower bound of energy consumption for parallel loop scheduling on heterogeneous systems, can be used as a baseline to evaluate the efficiency of optimization technology. Furthermore, this paper induces the scheduling problem as a typical integer programming problem and proposes inner-processor loop re-scheduling method to further reduce power consumption. Finally, 10 typical kernel programs on a CPU-GPU heterogeneous system are created. The experimental results demonstrate that the proposed method can effectively reduce the total energy consumption of the whole system and improve the system energy efficiency. ©2011, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
下载
收藏
页码：2222 / 2234
页数：12
相关论文
共 11 条
  • [1] Li K.Q., Performance analysis of power-aware task scheduling algorithms on multiprocessor computers with dynamic voltage and speed, IEEE Trans. on Parallel and Distributed System, 19, 11, pp. 1484-1497, (2008)
  • [2] Dong Y., Chen J., Yang X.J., Deng L., Zhang X.M., Energy-Oriented openmp parallel loop scheduling, Proc. of the 2008 IEEE Int'l Symp. on Parallel and Distributed Processing with Applications (ISPA 2008), pp. 162-169, (2008)
  • [3] Kadayif I., Kandemir M., Karakoy M., An energy saving strategy based on adaptive loop parallelization, Proc. of the 39th Annual Design Automation Conf. (DAC 2002), pp. 195-200, (2002)
  • [4] Kadayif I., Kandemir M., Kolcu I., Exploiting processor workload heterogeneity for reducing energy consumption in chip multiprocessors, Proc. of the Design, Automation and Test in Europe Conf. and Exhibition (DATE 2004), 2, pp. 1158-1163, (2004)
  • [5] Li J., Martinez J.F., Dynamic power-performance adaptation of parallel computation on chip multiprocessors, Proc. of the 12th Int'l Symp. on High-Performance Computer Architecture (HPCA-12), (2006)
  • [6] Takizawa H., Sato K., Kobayashi H., SPRAT: Runtime processor selection for energy-aware computing, Proc. of the 3rd Int'l Workshop on Automatic Performance Tuning, (2008)
  • [7] Luk C.K., Hong S., Kim H., Qilin: Exploiting parallelism on heterogeneous multiprocessors with adaptive mapping, Proc. of the 42nd Annual IEEE/ACM Int'l Symp. on Microarchitecture (MICRO 42), (2009)
  • [8] Huang S., Xiao S., Feng W., On the energy efficiency of graphics processing units for scientific computing, Proc. of the 2009 IEEE Int'l Symp. on Parallel & Distributed Processing (IPDPS 2009), (2009)
  • [9] Collange S., Defour D., Tisserand A., Power consumption of GPUs from a software perspective, Proc. of the 9th Int'l Conf. on Computational Science: Part I, pp. 914-923, (2009)
  • [10] Burd T.D., Brodersen R.W., Design issues for dynamic voltage scaling, Proc. of the 2000 Int'l Symp. on Low Power Electronics and Design, ISLPED 2000, (2000)
12