A Quantitative Analysis on Microarchitectures of Modern CPU-FPGA Platforms

被引:50
作者
Choi, Young-Kyu [1 ]
Cong, Jason [1 ]
Fang, Zhenman [1 ]
Hao, Yuchen [1 ]
Reinman, Glenn [1 ]
Wei, Peng [1 ]
机构
[1] Univ Calif Los Angeles, Ctr Domain Specif Comp, Los Angeles, CA 90095 USA
来源
2016 ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC) | 2016年
关键词
D O I
10.1145/2897937.2897972
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
CPU-FPGA heterogeneous acceleration platforms have shown great potential for continued performance and energy efficiency improvement for modern data centers, and have captured great attention from both academia and industry. However, it is nontrivial for users to choose the right platform among various PCIe and QPI based CPU-FPGA platforms from different vendors. This paper aims to find out what microarchitectural characteristics affect the performance, and how. We conduct our quantitative comparison and in-depth analysis on two representative platforms: QPI-based Intel-Altera HARP with coherent shared memory, and PCIe-based Alpha Data board with private device memory. We provide multiple insights for both application developers and platform designers.
引用
收藏
页数:6
相关论文
共 19 条
  • [1] [Anonymous], 2014, ISCA
  • [2] [Anonymous], 2009, Computer system, V26, P63
  • [3] Brech B., 2015, TECH REP
  • [4] INSTRUCTION SET INNOVATIONS FOR THE CONVEY HC-1 COMPUTER
    Brewer, Tony M.
    [J]. IEEE MICRO, 2010, 30 (02) : 70 - 79
  • [5] Chandramoorthy N., 2015, HPCA
  • [6] Chen Y.-T., 2015, FCCM
  • [7] Cong J., 2013, ISLPED
  • [8] Cook S, 2012, CUDA PROGRAMMING DEV
  • [9] Cota E G., 2015, DAC
  • [10] Fang Z., 2015, ACM TACO