NSSC OpenIR  > 空间科学部
Customizing the HPL for China accelerator
Gan, Xinbiao; Hu, Yikun; Liu, Jie; Chi, Lihua; Xu, Han; Gong, Chunye; Li, Shengguo; Yan, Yihui
KeywordHpl China Accelerator Dpem Oamm Optvec
AbstractHPL is a Linpack benchmark package widely used in high-performance computing tests. Customizing the HPL is crucial for a heterogeneous system equipped with CPU and the China accelerator because of the complexity of the China accelerator and the specified interface on matrix multiplication built in the China accelerator. Therefore, it is advisable to use delicate partition and encapsulation on matrix (DPEM) to expose a friendly testing configuration. More importantly, we propose the orchestrating algorithm for matrix multiplication (OAMM) to enhance the efficiency of the heterogeneous system composed of CPU and China accelerator. Furthermore, optimization at vectorization (OPTVEC) is applied to shield the architectural details of the vector processing element (VPE) equipped in the China accelerator. The experimental results validate DPEM, OPTVEC and OAMM. OPTVEC optimizations would speed up matrix multiplication more than twofold, moreover OAMM would improve productivity by up to 10% compared to the traditional HPL tested in a heterogeneous system.
Indexed BySCI ; CSCD
Citation statistics
Document Type期刊论文
Corresponding AuthorGan, Xinbiao
Recommended Citation
GB/T 7714
Gan, Xinbiao,Hu, Yikun,Liu, Jie,et al. Customizing the HPL for China accelerator[J]. SCIENCE CHINA-INFORMATION SCIENCES,2018,61(4):42102.
APA Gan, Xinbiao.,Hu, Yikun.,Liu, Jie.,Chi, Lihua.,Xu, Han.,...&Yan, Yihui.(2018).Customizing the HPL for China accelerator.SCIENCE CHINA-INFORMATION SCIENCES,61(4),42102.
MLA Gan, Xinbiao,et al."Customizing the HPL for China accelerator".SCIENCE CHINA-INFORMATION SCIENCES 61.4(2018):42102.
Files in This Item:
File Name/Size DocType Version Access License
201861442102.pdf(1104KB)期刊论文作者接受稿开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gan, Xinbiao]'s Articles
[Hu, Yikun]'s Articles
[Liu, Jie]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gan, Xinbiao]'s Articles
[Hu, Yikun]'s Articles
[Liu, Jie]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gan, Xinbiao]'s Articles
[Hu, Yikun]'s Articles
[Liu, Jie]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.