Earticle

초록

영어

Recently, there have been tremendous interests in the acceleration of general computing applications using a Graphics Processing Unit (GPU). Now the GPU provides the computing powers not only for fast processing of graphics applications, but also for general computationally complex data intensive applications. On the other hand, power and energy consumptions are also becoming important design criteria. Consequently, software designs have to consider the power/energy consumptions together with performance when they are developing software. In this paper, we explore a design space exploration with a commercial GPU: nVidia GTX 660 for investigating the best configuration of a kernel grid structure in a GPU for optimal power or energy consumption.

목차

Abstract
 1. Introduction
 2. Preliminary Work
  2.1. CPU vs GPU
  2.2. GPU Architecture and CUDA
 3. GPU Design Space Exploration
  3.1. Basics of Design Space Exploration
  3.2. Dot Product Application
  3.3. Power/Energy Consumption Measurement in GPU
 4. Experiments for GPU-DSE
  4.1. Experimental Setup
  4.2. Experimental Results
 5. Conclusion
 References

키워드

저자

• Hana Park [ Dept. of Computer Science, Hallym University, Chuncheon, South Korea ]
• Young Woong Ko [ Dept. of Computer Science, Hallym University, Chuncheon, South Korea ]
• Jungmin So [ Dept. of Computer Science, Hallym University, Chuncheon, South Korea ]
• Jeong-Gun Lee [ Dept. of Computer Science, Hallym University, Chuncheon, South Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605