Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2024, Vol. 18 Issue (6) : 186211    https://doi.org/10.1007/s11704-024-40066-w
Software
WPIA: accelerating DNN warm-up in Web browsers by precompiling WebGL programs
Deyu TIAN1, Yun MA1,2(), Yudong HAN2, Qi YANG1, Haochen YANG1, Gang HUANG1,3
1. Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education,School of Computer Science, Peking University, Beijing 100871, China
2. Institute for Artificial Intelligence, Peking University, Beijing 100871, China
3. National Key Laboratory of Data Space Technology and System, Beijing 100195, China
 Download: PDF(2135 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Corresponding Author(s): Yun MA   
Just Accepted Date: 29 April 2024   Issue Date: 19 June 2024
 Cite this article:   
Deyu TIAN,Yun MA,Yudong HAN, et al. WPIA: accelerating DNN warm-up in Web browsers by precompiling WebGL programs[J]. Front. Comput. Sci., 2024, 18(6): 186211.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-40066-w
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I6/186211
Fig.1  Analysis of the long DNN warm-up time
Fig.2  Overview of WPIA
Fig.3  Merging of two WebGL programs
Fig.4  The warm-up time. The X-axis labels are device IDs (H, D, P, R) and model IDs (#1 ~ #6)
Fig.5  The size of WebGL binaries
1 Google. Background features in google meet, powered by Web ML. See Research.google/blog/background-features-in-google-meet-powered-by website, 2020
2 D, Smilkov N, Thorat Y, Assogba A, Yuan N, Kreeger P, Yu K, Zhang S, Cai E, Nielsen D, Soergel S, Bileschi M, Terry C, Nicholson S N, Gupta S, Sirajuddin D, Sculley R, Monga G, Corrado F B, Viégas M Wattenberg . TensorFlow.js: machine learning for the Web and beyond. In: Proceedings of Machine Learning and Systems 2019. 2019
3 Y, Ma D, Xiang S, Zheng D, Tian X Liu . Moving deep learning into Web browser: how far can we go? In: Proceedings of the World Wide Web Conference. 2019, 1234−1244
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed