Abstract
Nowadays, GPGPU plays an important role in data centers for Deep Learning training. However, GPU might not be suitable for many Deep Learning inference applications, especially for Edge Computing scenarios, due to its high power consumption and high cost. Thus, researchers and engineers have spent a lot of effort on designing edge-side artificial intelligence (AI) processors recently. Because of different edge-side application requirements, edge AI processors are designed with different approaches, which make these processors very diversified. This scenario makes it hard for customers to decide what kind of processors may be more beneficial for their requirements. To provide a selection guidance, this paper proposes a three-dimensional benchmarking methodology and shares the early experience of evaluating three different kinds of edge AI processors (i.e., Edge TPU, NVIDIA Xavier, and NovuTensor) with object detection workloads (i.e., Tiny-YOLO and YOLOv2 with Microsoft COCO dataset). We also characterize a GPU platform (i.e., GTX 1080 Ti) from the three dimensions of accuracy, latency, and energy efficiency. Based on our experimental observations, we find that edge AI processors are able to deliver better energy efficiency (e.g., Edge TPU has the highest energy efficiency in our experiments.), while NovuTensor and Xavier, can also provide comparable performance in latency as GPU. Further, all these edge AI processors can achieve similar accuracy as GPU. The differences among these processors and GPU are less than 3%.
This research is supported in part by National Science Foundation grant CCF#1822987.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Benchmarking Edge Computing. https://medium.com/@aallan/benchmarking-edge-computing-ce3f13942245
DarkFlow. https://github.com/thtrieu/darkflow
Darknet. https://github.com/pjreddie/darknet
Deepstream Reference Applications. https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps
Models Built for Edge TPU. https://coral.withgoogle.com/models/
MS COCO API. https://github.com/cocodataset/cocoapi
NVIDIA Jetson AGX Xavier. https://developer.nvidia.com/embedded/jetson-agx-xavier-developer-kit
Post-Training Integer Quantization. https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-post-training-integer-quantization-b4964a1ea9ba
Chakradhar, S., Sankaradas, M., Jakkula, V., Cadambi, S.: A dynamically configurable coprocessor for convolutional neural networks. In: ACM SIGARCH Computer Architecture News, vol. 38, pp. 247–257. ACM (2010)
Chen, T., et al.: BenchNN: on the broad potential application scope of hardware neural network accelerators. In: 2012 IEEE International Symposium on Workload Characterization (IISWC), pp. 36–45. IEEE (2012)
Chen, Y., Chen, T., Zhiwei, X., Sun, N., Temam, O.: DianNao family: energy-efficient hardware accelerators for machine learning. Communi. ACM 59(11), 105–112 (2016)
Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)
Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification. In: Twenty-Second International Joint Conference on Artificial Intelligence (2011)
Coates, A., Huval, B., Wang, T., Wu, D., Catanzaro, B., Andrew, N.: Deep learning with COTS HPC systems. In: International Conference on Machine Learning, pp. 1337–1345 (2013)
Das, A., Patterson, S., Wittie, M.: Edgebench: benchmarking edge computing platforms. In: 2018 IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion), pp. 175–180. IEEE (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Everingham, M., Gool, L.V., KI Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Han, S., et al.. EIE: efficient inference engine on compressed deep neural network. In: 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp. 243–254. IEEE (2016)
Hao, T., et al.: EdgeAI bench: towards comprehensive end-to-end edge computing benchmarking. In: 2018 Bench Council International Symposium on Benchmarking, Measuring and Optimizing (Bench 2018) (2018)
Hashemi, S., Anthony, N., Tann, H., Bahar, I.R., Reda, S.: Understanding the impact of precision quantization on the accuracy and energy of neural networks. In Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017, pp. 1474–1479. IEEE (2017)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2018)
Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), pp. 1–12. IEEE (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Wick, C.: Deep learning. Informatik-Spektrum 40(1), 103–107 (2016). https://doi.org/10.1007/s00287-016-1013-2
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, Y.-L., Tsung, P.-K., Wu, M.: Techology trend of edge AI. In: 2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), pp. 1–2. IEEE (2018)
Lin, T.-Y., et al.: 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_48
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Lu, C.P., Tang, Y.-S.: Native Tensor Processor, and Partitioning of Tensor Contractions. https://patentscope.wipo.int/search/en/detail.jsf?docId=US225521272&tab=NATIONALBIBLIO
Luo, C., et al.: AIoT bench: towards comprehensive benchmarking mobile and embedded device intelligence. In: 2018 Bench Council International Symposium on Benchmarking, Measuring and Optimizing (Bench 2018) (2018)
Manolakos, E.S., Stamoulias, I.: IP-Cores design for the kNN classifier. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 4133–4136. IEEE (2010)
Nickolls, J., Buck, I., Garland, M.: Scalable parallel programming. In: 2008 IEEE Hot Chips 20 Symposium (HCS), pp. 40–53. IEEE (2008)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Stamoulias, I., Manolakos, E.S.: Parallel architectures for the kNN classifier-design of soft IP cores and FPGA implementations. ACM Trans. Embedded Comput. Syst. (TECS) 13(2), 22 (2013)
Yeh, Y.-J., Li, H.-Y., Hwang, W.-J., Fang, C.-Y.: FPGA implementation of kNN classifier based on wavelet transform and partial distance search. In: Ersbøll, B.K., Pedersen, K.S. (eds.) SCIA 2007. LNCS, vol. 4522, pp. 512–521. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-73040-8_52
Zhang, Q., et al.: A survey on deep learning benchmarks: do we still need new ones? In: 2018 Bench Council International Symposium on Benchmarking, Measuring and Optimizing (Bench 2018) (2018)
Zhao, Z.-Q., Zheng, P., Xu, S.-T., Wu, X.: A review. IEEE Transactions on Neural Networks and Learning Systems, Object Detection with Deep Learning (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hui, Y., Lien, J., Lu, X. (2020). Early Experience in Benchmarking Edge AI Processors with Object Detection Workloads. In: Gao, W., Zhan, J., Fox, G., Lu, X., Stanzione, D. (eds) Benchmarking, Measuring, and Optimizing. Bench 2019. Lecture Notes in Computer Science(), vol 12093. Springer, Cham. https://doi.org/10.1007/978-3-030-49556-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-49556-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-49555-8
Online ISBN: 978-3-030-49556-5
eBook Packages: Computer ScienceComputer Science (R0)