Skip to main content
Springer Nature Link
Log in

WPIA: accelerating DNN warm-up in Web browsers by precompiling WebGL programs

  • Letter
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

5 Conclusion

In this paper, we study the long warm-up time of GPU acceleration of DNN inference in Web browsers. We analyzed the reason behind the long warm-up time through a measurement study and revealed that compiling WebGL programs takes most of the warm-up time. Inspired by this finding, we proposed WPIA, an approach that suggests precompiling WebGL programs on the server side to avoid compiling them in Web browsers. WPIA tackles the challenges of precompiling by merging WebGL programs and using a record-and-replay technique. Evaluation experiment results show that WPIA can accelerate the DNN warm-up time to an order of magnitude.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  1. Google. Background features in google meet, powered by Web ML. See Research. https://www.google/blog/background-features-in-google-meet-powered-by website, 2020

  2. Smilkov D, Thorat N, Assogba Y, Yuan A, Kreeger N, Yu P, Zhang K, Cai S, Nielsen E, Soergel D, Bileschi S, Terry M, Nicholson C, Gupta S N, Sirajuddin S, Sculley D, Monga R, Corrado G, Viégas F B, Wattenberg M. TensorFlow.js: machine learning for the Web and beyond. In: Proceedings of Machine Learning and Systems 2019. 2019

  3. Ma Y, Xiang D, Zheng S, Tian D, Liu X. Moving deep learning into Web browser: how far can we go? In: Proceedings of the World Wide Web Conference. 2019, 1234–1244

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant No. 62102009) and the Beijing Outstanding Young Scientist Program (No. BJJWZYJH01201910001004).

Author information

Authors and Affiliations

  1. Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, School of Computer Science, Peking University, Beijing, 100871, China

    Deyu Tian, Yun Ma, Qi Yang, Haochen Yang & Gang Huang

  2. Institute for Artificial Intelligence, Peking University, Beijing, 100871, China

    Yun Ma & Yudong Han

  3. National Key Laboratory of Data Space Technology and System, Beijing, 100195, China

    Gang Huang

Authors
  1. Deyu Tian
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yun Ma
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yudong Han
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Qi Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Haochen Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Gang Huang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yun Ma.

Ethics declarations

Competing interests The authors declare that they have no competing interests or financial conflicts to disclose.

Additional information

Electronic supplementary material Supplementary material is available in the online version of this article at journal.hep.com.cn and link.springer.com.

Electronic Supplementary Material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, D., Ma, Y., Han, Y. et al. WPIA: accelerating DNN warm-up in Web browsers by precompiling WebGL programs. Front. Comput. Sci. 18, 186211 (2024). https://doi.org/10.1007/s11704-024-40066-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11704-024-40066-w