Abstract
The Internet of Things is manifested through a large number of low-capability connected devices. This means that for many applications, computation must be offloaded to more capable platforms. While this has typically been cloud datacenters accessed over the Internet, this is not feasible for latency sensitive applications. In this paper we investigate the interplay between three factors that contribute to overall application latency when offloading computations in IoT applications. First, different platforms can reduce computation latency by differing amounts. Second, these platforms can be traditional server-based or emerging network-attached, which exhibit differing data ingestion latencies. Finally, where these platforms are deployed in the network has a significant impact on the network traversal latency. All these factors contributed to overall application latency, and hence the efficacy of computational offload. We show that network-attached acceleration scales better to further network locations and smaller base computation times that traditional server based approaches.
Funding source: Alan Turing Institute
Award Identifier / Grant number: EP/N510129/1
Funding statement: This work was supported in part by The Alan Turing Institute under the UK EPSRC grant EP/N510129/1.
About the authors
Mr. Ryan A. Cooke is a PhD student in the School of Engineering at the University of Warwick, UK, where he also received his M. Eng. degree in Electronic Engineering in 2015.His research interests include reconfigurable computing, and in-network analytics acceleration.
Dr. Suhaib A. Fahmy is Reader in Computer Engineering at the University of Warwick, where his research encompasses reconfigurable computing, high-level system design, and computational acceleration of complex algorithms.He received the M. Eng. degree in information systems engineering and the Ph. D. degree in electrical and electronic engineering from Imperial College London, UK, in 2003 and 2007, respectively. From 2007 to 2009, he was a Research Fellow with Trinity College Dublin and a Visiting Research Engineer with Xilinx Research Labs, Dublin. From 2009 to 2015, he was an Assistant Professor with the School of Computer Engineering, Nanyang Technological University, Singapore.Dr. Fahmy was a recipient of the Best Paper Award at the IEEE Conference on Field Programmable Technology in 2012, the IBM Faculty Award in 2013 and 2017, the Community Award at the International Conference on Field Programmable Logic and Applications, the ACM TODAES Best Paper Award in 2019 and is a senior member of the IEEE and ACM.
References
1. H. M. Hussain, K. Benkrid, A. T. Erdogan, and H. Seker, “Highly parameterized k-means clustering on fpgas: Comparative results with GPPs and GPUs,” in Proceedings of the International Conference on Reconfigurable Computing and FPGAs, no. 1, 2011, pp. 475–480.10.1109/ReConFig.2011.49Search in Google Scholar
2. S. A. Fahmy, K. Vipin, and S. Shreejith, “Virtualized FPGA accelerators for efficient cloud computing,” in Proceedings of the International Conference on Cloud Computing Technology and Science (CloudCom), 2015, pp. 430–435.10.1109/CloudCom.2015.60Search in Google Scholar
3. Y. R. Qu, H. H. Zhang, S. Zhou, and V. K. Prasanna, “Optimizing many-field packet classification on FPGA, multi-core general purpose processor, and GPU,” in ANCS, 2015.Search in Google Scholar
4. A. Fiessler, S. Hager, B. Scheuermann, and A. W. Moore, “HyPaFilter: a versatile hybrid FPGA packet filter,” in ANCS, 2016.10.1145/2881025.2881033Search in Google Scholar
5. T. Soyata, R. Muraleedharan, C. Funai, M. Kwon, and W. Heinzelman, “Cloud-Vision: Real-time face recognition using a mobile-cloudlet-cloud acceleration architecture,” 2012, pp. 000 059–000 066.10.1109/ISCC.2012.6249269Search in Google Scholar
6. S. Yi, Z. Hao, Z. Qin, and Q. Li, “Fog computing: Platform and applications,” in HotWeb, 2016, pp. 73–78.10.1109/HotWeb.2015.22Search in Google Scholar
7. K. Ha, Z. Chen, W. Hu, W. Richter, P. Pillai, and M. Satyanarayanan, “Towards wearable cognitive assistance,” in MobiSys ’14, 2014, pp. 68–81.10.21236/ADA591470Search in Google Scholar
8. N. Zilberman, M. Grosvenor, N. Manihatty-bojan, D. A. Popescu, G. Antichi, S. Galea, A. Moore, R. Watson, and M. Wojcik, “Where has my time gone?” in International Conference on Passive and Active Network Measurement, 2017.10.1007/978-3-319-54328-4_15Search in Google Scholar
9. R. Neugebauer, G. Antichi, J. F. Zazo, S. López-buedo, and A. W. Moore, “Understanding PCIe performance for end host networking,” in SIGCOMM, 2018, pp. 327–341.10.1145/3230543.3230560Search in Google Scholar
10. R. A. Cooke and S. A. Fahmy, “Quantifying the latency benefits of near-edge and in-network FPGA acceleration,” in Proceedings of the International Workshop on Edge Systems, Analytics and Networking (EdgeSys), 2020, pp. 7–12.10.1145/3378679.3394534Search in Google Scholar
11. O. Tomanek, P. Mulinka, and L. Kencl, “Multidimensional cloud latency monitoring and evaluation,” Computer Networks, vol. 107, no. Part 1, pp. 104–120, 2016.10.1016/j.comnet.2016.06.011Search in Google Scholar
12. M. Satyanarayanan, P. Bahl, R. Cáceres, and N. Davies, “The case for VM-based cloudlets in mobile computing,” Pervasive Computing, vol. 8, no. 4, pp. 14–23, 2009.10.1109/MPRV.2009.82Search in Google Scholar
13. Y. Jararweh, L. Tawalbeh, F. Ababneh, and F. Dosari, “Resource efficient mobile computing using cloudlet infrastructure,” in Conference on Mobile Ad-hoc and Sensor Networks, 2013.10.1109/MSN.2013.75Search in Google Scholar
14. K. Gai, M. Qiu, H. Zhao, L. Tao, and Z. Zong, “Dynamic energy-aware cloudlet-based mobile cloud computing model for green computing,” Network and Computer Applications, vol. 59, pp. 46–54, 2016.10.1016/j.jnca.2015.05.016Search in Google Scholar
15. M. Satyanarayanan, P. B. Gibbons, L. Mummert, P. Pillai, P. Simoens, and R. Sukthankar, “Cloudlet-based just-in-time indexing of IoT video,” in GIoTS 2017, 2017.10.1109/GIOTS.2017.8016212Search in Google Scholar
16. B. Van Essen, C. Macaraeg, M. Gokhale, and R. Prenger, “Accelerating a random forest classifier: Multi-core, GP-GPU, or FPGA?” in International Symposium on Field-Programmable Custom Computing Machines, 2012, pp. 232–239.10.1109/FCCM.2012.47Search in Google Scholar
17. A. Putnam, A. M. Caulfield, E. S. Chung, D. Chiou, K. Constantinides, J. Demme, H. Esmaeilzadeh, J. Fowers, G. P. Gopal, J. Gray, M. Haselman, S. Hauck, S. Heil, A. Hormati, J. Y. Kim, S. Lanka, J. Larus, E. Peterson, S. Pope, A. Smith, J. Thong, P. Y. Xiao, and D. Burger, “A reconfigurable fabric for accelerating large-scale datacenter services,” IEEE Micro, vol. 35, no. 3, pp. 10–22, 2015.10.1109/ISCA.2014.6853195Search in Google Scholar
18. D. Firestone, et al. “Azure accelerated networking: SmartNICs in the public cloud,” in NSDI, 2018, pp. 51–64.Search in Google Scholar
19. A. M. Caulfield, E. S. Chung, P. Kaur, J.-y. K. Daniel, L. Todd, and M. Kalin, “A cloud-scale acceleration architecture,” in MICRO, 2016.10.1109/MICRO.2016.7783710Search in Google Scholar
20. M. Asiatici, N. George, K. Vipin, S. A. Fahmy, and P. Ienne, “Virtualized Execution Runtime for FPGA Accelerators in the Cloud,” IEEE Access, vol. 5, pp. 1900–1910, 2017.10.1109/ACCESS.2017.2661582Search in Google Scholar
21. J. Whiteaker, F. Schneider, and R. Teixeira, “Explaining packet delays under virtualization,” ACM SIGCOMM Computer Communication Review, vol. 41, no. 1, pp. 39–44, 2011.10.1145/1925861.1925867Search in Google Scholar
22. R. Shea, F. Wang, H. Wang, and J. Liu, “A deep investigation into network performance in virtual machine based cloud environments,” in INFOCOM, 2014, pp. 1285–1293.10.1109/INFOCOM.2014.6848061Search in Google Scholar
23. L. Chen, S. Patel, H. Shen, and Z. Zhou, “Profiling and understanding virtualization overhead in cloud,” in 2015 44th International Conference on Parallel Processing, Dec. 2015, pp. 31–40.10.1109/ICPP.2015.12Search in Google Scholar
24. Q. Qi and F. Tao, “A smart manufacturing service system based on edge computing, fog computing and cloud computing,” IEEE Access, vol. 7, 2019.10.1109/ACCESS.2019.2923610Search in Google Scholar
25. C.-H. Chen, M.-Y. Lin, and C.-C. Liu, “Edge computing gateway of the industrial internet of things using multiple collaborative microcontrollers,” IEEE Network, vol. 32, pp. 24–32, 2018.10.1109/MNET.2018.1700146Search in Google Scholar
26. A. M. Rahmanu, T. N. Gia, B. Negash, A. Anzanpour, I. Azimi, M. Jiang, and P. Liljeberg, “Exploiting smart e-health gateways at the edge of healthcare internet-of-things: a fog computing approach,” FGCS, vol. 78, pp. 641–658, 2017.10.1016/j.future.2017.02.014Search in Google Scholar
27. X. Zhai, A. A. S. Ali, A. Amira, and F. Bensaali, “MLP neural network based gas classification system on Zynq SoC,” IEEE Access, vol. 4, pp. 8138–8146, 2016.10.1109/ACCESS.2016.2619181Search in Google Scholar
28. M. Urbina, A. Astarloa, J. Lazaro, U. Bidarte, I. Villalta, and M. Rodriguez, “Cyber-physical production system gateway based on a programmable SoC platform,” IEEE Access, vol. 5, 2019.10.1109/ACCESS.2017.2757048Search in Google Scholar
29. Cisco, “The Cisco edge analytics fabric system,” 2016.Search in Google Scholar
30. R. A. Cooke and S. A. Fahmy, “A model for distributed in-network and near-edge computing with heterogeneous hardware,” Future Generation Computer Systems, vol. 105, pp. 395–409, 2020.10.1016/j.future.2019.11.040Search in Google Scholar
31. Y. Tokusashi, H. T. Dang, F. Pedone, R. Soulé, and N. Zilberman, “The case for in-network computing on demand,” in Proceedings of the EuroSys Conference, 2019, pp. 1–16.10.1145/3302424.3303979Search in Google Scholar
32. A. Cartas et al., “A reality check on inference at mobile networks edge,” in Proceedings of the International Workshop on Edge Systems, Analytics and Networking (EdgeSys), 2019, pp. 54–59.10.1145/3301418.3313946Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
