Earticle

초록

영어

High-performance conjugate gradient (HPCG) is the latest benchmark adopted by the TOP500 organization, and thus how to optimize the HPCG source code for different heterogeneous computing platforms to achieve a higher floating-point computation rate has already become a new hot issue in HPC field. In the paper, we used the CPU + MIC heterogeneous computing platforms, and successfully ported HPCG to the platform. Through the analysis of HPCG source code and optimization for CPU + MIC platforms, practical significance and the value of further research is put forward. Results of performing the benchmark indicate that the design of optimization methods is reasonable and has facilitated the speedup of HPCG benchmark.

목차

Abstract
 1. Introduction
 2. HPCG: The Benchmark for Supercomputer
 3. Optimization of the Source Code of HPCG for MIC Co-Processor
  3.1. Offload Programming Mode
  3.2. Vectorization
 4. HPCG Acceleration Methods
  4.1. Basic Approach
  4.2. Parameter Tuning
  4.3. Further Acceleration based on MIC
  4.4. Heat Dissipation of MIC Co-Processor
 5. Experimental Test and Analysis
  5.1. Experimental Platform
  5.2. Optimization Results Analysis
 6. Conclusion and Future Work
 References

키워드

저자

• Qingyi Pan [ State Key Laboratory of Plateau Ecology and Agriculture, Department of Computer Technology and Applications, Qinghai University, Xining, China ]
• Xiaoying Wang [ State Key Laboratory of Plateau Ecology and Agriculture, Department of Computer Technology and Applications, Qinghai University, Xining, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605