Advertisement

Multiple Algorithms Against Multiple Hardware Architectures: Data-Driven Exploration on Deep Convolution Neural Network

  • Chongyang Xu
  • Zhongzhi Luan
  • Lan Gao
  • Rui WangEmail author
  • Han Zhang
  • Lianyi Zhang
  • Yi Liu
  • Depei Qian
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11783)

Abstract

With the rapid development of deep learning (DL), various convolution neural network (CNN) models have been developed. Moreover, to execute different DL workloads efficiently, many accelerators have been proposed. To guide the design of both CNN models and hardware architectures for a high-performance inference system, we choose five types of CNN models and test them on six processors and measure three metrics. With our experiments, we get two observations and conduct two insights for the design of CNN algorithms and hardware architectures.

Keywords

Convolutional neural network Hardware architecture Performance evaluation 

Notes

Acknowledgements

This work is supported by the National Key Research and Development Program of China under grant 2017YFB0203201. This work is also supported by the NSF of China under grant 61732002.

References

  1. 1.
    Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI 2016 (2016)Google Scholar
  2. 2.
    Adolf, R., Rama, S., Reagen, B., Wei, G.Y., Brooks, D.: Fathom: reference workloads for modern deep learning methods. In: IISWC 2016 (2016)Google Scholar
  3. 3.
    Hauswald, J., et al.: DjiNN and tonic: DNN as a service and its implications for future warehouse scale computers. In: ISCA 2015 (2015)Google Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016) Google Scholar
  5. 5.
    Hinton, G.E., Krizhevsky, A., Sutskever, I.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)Google Scholar
  6. 6.
    Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
  7. 7.
    Ignatov, A., et al.: AI benchmark: Running deep neural networks on android smartphones. In: European Conference on Computer Vision (2018)Google Scholar
  8. 8.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML 2015 (2015)Google Scholar
  9. 9.
    Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: ISCA 2017 (2017)Google Scholar
  10. 10.
    Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  11. 11.
    Liu, S., et al.: Cambricon: an instruction set architecture for neural networks. In: ACM SIGARCH Computer Architecture News (2016)CrossRefGoogle Scholar
  12. 12.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  13. 13.
    Rodrigues, C.F., Riley, G.D., Luján, M.: Fine-grained energy profiling for deep convolutional neural networks on the Jetson TX1. CoRR abs/1803.11151 (2018)Google Scholar
  14. 14.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  16. 16.
    Tao, J.H., et al.: BenchIP: benchmarking intelligence processors. J. Comput. Sci. Technol. 33, 1–23 (2018)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  • Chongyang Xu
    • 1
  • Zhongzhi Luan
    • 1
  • Lan Gao
    • 1
  • Rui Wang
    • 1
    Email author
  • Han Zhang
    • 2
  • Lianyi Zhang
    • 2
  • Yi Liu
    • 1
  • Depei Qian
    • 1
  1. 1.Beihang UniversityBeijingChina
  2. 2.Science and Technology on Special System Simulation LaboratoryBeijing Simulation CenterBeijingChina

Personalised recommendations