• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 高性能计算 • 上一篇    下一篇

基于国产软硬件的OpenCL计算平台研究

安婷玉1,郭宝宝2   

  1. (1.太原理工大学经济管理学院,太原 山西 030024;2.66133部队,北京 100144)
  • 收稿日期:2019-03-01 修回日期:2019-06-13 出版日期:2019-11-25 发布日期:2019-11-25
  • 基金资助:

    太原理工大学校青年基金(2014QN040)

OpenCL computing platform based
on domestic software and hardware

AN Ting-yu1,GUO Bao-bao2   

  1. (1.College of Economics and Management,Taiyuan University of Technology,Taiyuan 030024;
    2.Troop 66133,Beijing 100144,China)
     
  • Received:2019-03-01 Revised:2019-06-13 Online:2019-11-25 Published:2019-11-25

摘要:

随着智能计算和大数据应用的发展,人们对GPU等加速部件的需求不断增长。基于国产基础软硬件平台运行显控应用做加速计算的需求,研究了OpenCL计算平台的移植和实现途径,就国产软硬件平台进行GPU计算做出了初步探索。研究的计算平台包括Mesa、ROCm、Pocl和Beignet,最后给出了如何将ROCm在国产平台上移植适配的思路和解决方案。

关键词: 国产基础软硬件, OpenCL计算平台, 移植, GPU计算

Abstract:

With the development of intelligent computing and big data applications, the demand for acceleration components such as GPU is increasing. Based on the requirements for accelerated computing by running display and control applications on domestic fundamental software and hardware platforms, this paper studies the portability and implementation of OpenCL computing platforms, and preliminarily explores the GPU computing on domestic software and hardware platforms. The studied computing platforms  include Mesa, ROCm, Pocl and Beignet. Finally, the idea and solution of how to port and adapt ROCm to domestic platforms are given.

 

Key words: domestic foundamental software and hardware, OpenCL computing platform, portability;GPU computing