PCamp: Performance comparison of machine learning packages on the edges

USENIX Workshop on Hot Topics in Edge Computing, HotEdge 2018, co-located with USENIX ATC 2018

Volumn , Issue , 2018, Pages

  Zhang, Xingzhou ^a,b   Wang, Yifan ^a,b   Shi, Weisong ^a  

^a WAYNE STATE UNIVERSITY   (United States)

^b UNIVERSITY OF CHINESE ACADEMY OF SCIENCES   (China)

Author keywords

[No Author keywords available]

Indexed keywords

EDGE COMPUTING; MACHINE LEARNING;

COMPUTING PARADIGM; HARDWARE AND SOFTWARE; HUMAN INTERACTIONS; MACHINE INTELLIGENCE; MEMORY FOOTPRINT; PERFORMANCE COMPARISON; SOFTWARE AND HARDWARES; STATE OF THE ART;

DEEP LEARNING;

EID: 85084162686     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (33)

1. Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. Tensorflow: A system for large-scale machine learning. In OSDI, volume 16, pages 265–283, 2016.
2. Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia, pages 675–678. ACM, 2014.
3. Frank Seide and Amit Agarwal. Cntk: Microsoft’s open-source deep-learning toolkit. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 2135–2135. ACM, 2016.
4. Ronan Collobert, Koray Kavukcuoglu, and Clément Farabet. Torch7: A matlab-like environment for machine learning. In BigLearn, NIPS workshop, number EPFL-CONF-192376, 2011.
5. Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274, 2015.
6. W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu. Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5):637–646, Oct 2016.
7. Mahadev Satyanarayanan, Pieter Simoens, Yu Xiao, Padmanabhan Pillai, Zhuo Chen, Kiryong Ha, Wenlu Hu, and Brandon Amos. Edge analytics in the internet of things. IEEE Pervasive Computing, 14(2):24–31, 2015.
8. Qingyang Zhang, Yifan Wang, Xingzhou Zhang, Liangkai Liu, Xiaopei Wu, Weisong Shi, and Hong Zhong. Openvdap: An open vehicular data analytics platform for cavs. In Distributed Computing Systems (ICDCS), 2017 IEEE 38th International Conference on. IEEE, 2018.
9. Kyungmin Lee, Jason Flinn, and Brian D Noble. Gremlin: scheduling interactions in vehicular computing. In Proceedings of the Second ACM/IEEE Symposium on Edge Computing, page 4. ACM, 2017.
10. Bozhao Qi, Lei Kang, and Suman Banerjee. A vehicle-based edge computing platform for transit and human mobility analytics. In Proceedings of the Second ACM/IEEE Symposium on Edge Computing, page 1. ACM, 2017.
11. Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
12. Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
13. Caffe2: A new lightweight, modular, and scalable deep learning framework, 2018.
14. Introduction to tensorflow lite, 2018.
15. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012.
16. Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. Squeezenet: Alexnetlevel accuracy with 50x fewer parameters and¡ 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.
17. Macbook pro. https://www.apple.com/macbook-pro/, 2018.
18. Intel’s fog reference design (intel fognode). https://www.intel.com/content/www/us/en/internet-ofthings/fog-reference-design-overview.html, 2018.
19. Nvidia jetson tx2 (jetson tx2). https://developer.nvidia.com/embedded/buy/jetson-tx2, 2018.
20. Raspberry pi 3 model b+ (raspberry pi). https://www.raspberrypi.org/products/raspberry-pi-3-modelb-plus/, 2018.
21. Huawei nexus 6p (nexus 6p). https://consumer.huawei.com/en/phones/nexus-6p/, 2018.
22. Shaohuai Shi, Qiang Wang, Pengfei Xu, and Xiaowen Chu. Benchmarking state-of-the-art deep learning software tools. In Cloud Computing and Big Data (CCBD), 2016 7th International Conference on, pages 99–104. IEEE, 2016.
23. Soheil Bahrampour, Naveen Ramakrishnan, Lukas Schott, and Mohak Shah. Comparative study of deep learning software frameworks. arXiv preprint arXiv:1511.06435, 2015.
24. Shayan Shams, Richard Platania, Kisung Lee, and Seung-Jong Park. Evaluation of deep learning frameworks over different hpc architectures. In Distributed Computing Systems (ICDCS), 2017 IEEE 37th International Conference on, pages 1389–1396. IEEE, 2017.
25. Steve Lawrence, C Lee Giles, Ah Chung Tsoi, and Andrew D Back. Face recognition: A convolutional neural-network approach. IEEE transactions on neural networks, 8(1):98–113, 1997.
26. Jure Zbontar and Yann LeCun. Stereo matching by training a convolutional neural network to compare image patches. Journal of Machine Learning Research, 17(1-32):2, 2016.
27. Large scale visual recognition challenge 2012 (ilsvrc2012), 2018.
28. Caffe2 model zoo, 2018.
29. Trepn Profiler6.2: Qualcomm innovation center, inc., 2016.
30. Spencer Desrochers, Chad Paradis, and Vincent M Weaver. A validation of dram rapl power measurements. In Proceedings of the Second International Symposium on Memory Systems, pages 455–470. ACM, 2016.
31. Intel power gadget, 2018.
32. Intel computer vision sdk - a brief overview. https://software.intel.com/en-us/blogs/2017/08/31/cv-sdk-abrief-overview, 2018.
33. Vision processing unita dedicated vision processing platform. https://www.movidius.com/solutions/vision-processing-unit, 2018.