Skip to main content

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture search (NAS) methods have omitted resource utilization, preventing DNNs to take full advantage of the target inference platforms. Modeling resource utilization efficiently and accurately is challenging, especially for widely-used array-based inference accelerators such as Google TPU. In this work, we propose a novel hardware-aware NAS framework that does not only optimize for task accuracy and inference latency, but also for resource utilization. We also propose and validate a new computational model for resource utilization in inference accelerators. By using the proposed NAS framework and the proposed resource utilization model, we achieve \(2.8-4\times \) speedup for DNN inference compared to prior hardware-aware NAS methods while attaining similar or improved accuracy in image classification on CIFAR-10 and Imagenet-100 datasets. (Source code is available at https://github.com/yuezuegu/UBoostNAS).

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The ceil function is defined as \(\left\lceil x \right\rceil =\min \{n\in \mathbb {Z}: n \ge x\}\).

References

  1. Bannon, P., Venkataramanan, G., Sarma, D.D., Talpes, E.: Computer and redundancy solution for the full self-driving computer. In: 2019 IEEE Hot Chips 31 Symposium (HCS), Cupertino, CA, USA, 18–20 August 2019, pp. 1–22. IEEE (2019)

    Google Scholar 

  2. Bender, G., Kindermans, P., Zoph, B., Vasudevan, V., Le, Q.V.: Understanding and simplifying one-shot architecture search. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018, vol. 80, pp. 549–558. PMLR (2018)

    Google Scholar 

  3. Bergstra, J., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for hyper-parameter optimization. In: Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12–14 December 2011, Granada, Spain, pp. 2546–2554 (2011)

    Google Scholar 

  4. Cai, H., Zhu, L., Han, S.: Proxylessnas: direct neural architecture search on target task and hardware. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019)

    Google Scholar 

  5. Chang, J., Zhang, X., Guo, Y., Meng, G., Xiang, S., Pan, C.: DATA: differentiable architecture approximation. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 December 2019, Vancouver, BC, Canada, pp. 874–884 (2019)

    Google Scholar 

  6. Chen, Y., Emer, J.S., Sze, V.: Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. In: 43rd ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2016, Seoul, South Korea, 18–22 June 2016, pp. 367–379. IEEE Computer Society (2016)

    Google Scholar 

  7. Cho, H.: Risa: a reinforced systolic array for depthwise convolutions and embedded tensor reshaping. ACM Trans. Embed. Comput. Syst. 20(5s), 53:1-53:20 (2021)

    Article  Google Scholar 

  8. Choi, K., Hong, D., Yoon, H., Yu, J., Kim, Y., Lee, J.: DANCE: differentiable accelerator/network co-exploration. In: 58th ACM/IEEE Design Automation Conference, DAC 2021, San Francisco, CA, USA, 5–9 December 2021, pp. 337–342. IEEE (2021)

    Google Scholar 

  9. Dai, X., et al.: Chamnet: towards efficient network design through platform-aware model adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 11398–11407. Computer Vision Foundation/IEEE (2019)

    Google Scholar 

  10. Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20–25 June 2009, Miami, Florida, USA, pp. 248–255. IEEE Computer Society (2009)

    Google Scholar 

  11. Désidéri, J.A.: Multiple-gradient descent algorithm (MGDA) for multiobjective optimization. C.R. Math. 350, 313–318 (2012)

    Article  MathSciNet  Google Scholar 

  12. Gordon, A., et al.: Morphnet: fast & simple resource-constrained structure learning of deep networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 1586–1595. Computer Vision Foundation/IEEE Computer Society (2018)

    Google Scholar 

  13. Gupta, S., Akin, B.: Accelerator-aware neural network design using automl. CoRR abs/2003.02838 (2020)

    Google Scholar 

  14. He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 2980–2988. IEEE Computer Society (2017)

    Google Scholar 

  15. Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017)

    Google Scholar 

  16. Jordà, M., Valero-Lara, P., Peña, A.J.: Performance evaluation of cudnn convolution algorithms on NVIDIA volta gpus. IEEE Access 7, 70461–70473 (2019)

    Article  Google Scholar 

  17. Jouppi, N.P., et al.: Ten lessons from three generations shaped Google’s TPUv4i: Industrial product. In: 48th ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2021, Valencia, Spain, 14–18 June 2021, pp. 1–14. IEEE (2021)

    Google Scholar 

  18. Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA 2017, Toronto, ON, Canada, 24–28 June 2017, pp. 1–12. ACM (2017)

    Google Scholar 

  19. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)

    Google Scholar 

  20. Kokkinos, I.: Ubernet: training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 5454–5463. IEEE Computer Society (2017)

    Google Scholar 

  21. Krizhevsky, A.: Learning multiple layers of features from tiny images. Tech. rep. (2009)

    Google Scholar 

  22. Kung, H.T.: Why systolic architectures? Computer 15(1), 37–46 (1982)

    Article  Google Scholar 

  23. Li, S., et al.: Searching for fast model families on datacenter accelerators. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, 19–25 June 2021, pp. 8085–8095. Computer Vision Foundation/IEEE (2021)

    Google Scholar 

  24. Liu, C., et al.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_2

    Chapter  Google Scholar 

  25. Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019)

    Google Scholar 

  26. Marchisio, A., Massa, A., Mrazek, V., Bussolino, B., Martina, M., Shafique, M.: Nascaps: a framework for neural architecture search to optimize the accuracy and hardware efficiency of convolutional capsule networks. In: IEEE/ACM International Conference On Computer Aided Design, ICCAD 2020, San Diego, CA, USA, 2–5 November 2020, pp. 114:1–114:9. IEEE (2020)

    Google Scholar 

  27. Nayman, N., Noy, A., Ridnik, T., Friedman, I., Jin, R., Zelnik-Manor, L.: XNAS: neural architecture search with expert advice. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December, pp. 1975–1985 (2019)

    Google Scholar 

  28. Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018. Proceedings of Machine Learning Research, vol. 80, pp. 4092–4101. PMLR (2018)

    Google Scholar 

  29. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: The 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, The 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, 27 January - 1 February 2019, pp. 4780–4789. AAAI Press (2019)

    Google Scholar 

  30. Samajdar, A., Joseph, J.M., Zhu, Y., Whatmough, P.N., Mattina, M., Krishna, T.: A systematic methodology for characterizing scalability of DNN accelerators using scale-sim. In: IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2020, Boston, MA, USA, 23–25 August 2020, pp. 58–68. IEEE (2020)

    Google Scholar 

  31. Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 4510–4520. Computer Vision Foundation/IEEE Computer Society (2018)

    Google Scholar 

  32. Smithson, S.C., Yang, G., Gross, W.J., Meyer, B.H.: Neural networks designing neural networks: multi-objective hyper-parameter optimization. In: Proceedings of the 35th International Conference on Computer-Aided Design, ICCAD 2016, Austin, TX, USA, 7–10 November 2016, p. 104. ACM (2016)

    Google Scholar 

  33. Stamoulis, D., et al.: Single-path nas: designing hardware-efficient convnets in less than 4 hours. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019. LNCS (LNAI), vol. 11907, pp. 481–497. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-46147-8_29

    Chapter  Google Scholar 

  34. Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 2820–2828. Computer Vision Foundation/IEEE (2019)

    Google Scholar 

  35. Wan, A., et al.: Fbnetv2: differentiable neural architecture search for spatial and channel dimensions. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13–19 June 2020, pp. 12962–12971. Computer Vision Foundation/IEEE (2020)

    Google Scholar 

  36. Williams, S., Waterman, A., Patterson, D.A.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65–76 (2009)

    Article  Google Scholar 

  37. Wu, B., et al.: Fbnet: hardware-aware efficient convnet design via differentiable neural architecture search. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 10734–10742. Computer Vision Foundation/IEEE (2019)

    Google Scholar 

  38. Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019)

    Google Scholar 

  39. Xiong, Y., et al.: Mobiledets: searching for object detection architectures for mobile accelerators. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19–25 June 2021, pp. 3825–3834. Computer Vision Foundation/IEEE (2021)

    Google Scholar 

  40. Xu, Y., et al.: PC-DARTS: partial channel connections for memory-efficient architecture search. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26–30 April 2020. OpenReview.net (2020)

    Google Scholar 

  41. Yang, T.-J., et al.: NetAdapt: platform-aware neural network adaptation for mobile applications. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 289–304. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_18

    Chapter  Google Scholar 

  42. Zhang, L.L., Yang, Y., Jiang, Y., Zhu, W., Liu, Y.: Fast hardware-aware neural architecture search. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR Workshops 2020, Seattle, WA, USA, 14–19 June 2020, pp. 2959–2967. Computer Vision Foundation/IEEE (2020)

    Google Scholar 

  43. Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: a comparative case study and the strength pareto approach. IEEE Trans. Evol. Comput. 3(4), 257–271 (1999)

    Article  Google Scholar 

  44. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017)

    Google Scholar 

  45. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 8697–8710. Computer Vision Foundation/IEEE Computer Society (2018)

    Google Scholar 

Download references

Acknowledgements

The work of Ahmet Caner Yüzügüler was supported by the Hasler Foundation (Switzerland) and Nikolaos Dimitriadis was supported by Swisscom (Switzerland) AG.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ahmet Caner Yüzügüler .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 487 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Yüzügüler, A.C., Dimitriadis, N., Frossard, P. (2022). U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19775-8_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19774-1

  • Online ISBN: 978-3-031-19775-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics