본문 바로가기
  • Home

Workload Characteristics-based L1 Data Cache Switching-off Mechanism for GPUs

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2018, 23(10), pp.1-9
  • DOI : 10.9708/jksci.2018.23.10.001
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : July 25, 2018
  • Accepted : October 17, 2018
  • Published : October 31, 2018

Do Cong Thuan 1 Gwang Bok Kim 2 Cheol Hong Kim 2

1고려대학교
2전남대학교

Accredited

ABSTRACT

Modern graphics processing units (GPUs) have become one of the most attractive platforms in exploiting high thread level parallelism with the support of new programming tools such as CUDA and OpenCL. Recent GPUs has applied cache hierarchy to support irregular memory access patterns; however, L1 data cache (L1D) exhibits poor efficiency in the GPU. This paper shows that the L1D does not always positively affect the applications in terms of performance and energy efficiency for the GPU. The performance of the GPU is even harmed by using the L1D for lots of applications. Our proposed technique exploits the characteristics of the currently-executed applications to predict the performance impact of the L1D on the GPU and then decides whether to continuously use the cache for the application or not. Our experimental results show that the proposed technique improves the GPU performance by 9.4% and saves up to 52.1% of the power consumption in the L1D.

Citation status

* References for papers published after 2022 are currently being built.