Abstract
Deep learning models are taking place at many artificial intelligence tasks. These models are achieving better results but need more computing power and memory. Therefore, training and inference of deep learning models are made at cloud centers with high-performance platforms. In many applications, it is more beneficial or required to have the inference at the edge near the source of data or action requests avoiding the need to transmit the data to a cloud service and wait for the answer. In many scenarios, transmission of data to the cloud is not reliable or even impossible, or has a high latency with uncertainty about the round-trip delay of the communication, which is not acceptable for applications sensitive to latency with real-time decisions. Other factors like security and privacy of data force the data to stay in the edge. With all these disadvantages, inference is migrating partial or totally to the edge. The problem, is that deep learning models are quite hungry in terms of computation, memory and energy which are not available in today’s edge computing devices. Therefore, artificial intelligence devices are being deployed by different companies with different markets in mind targeting edge computing. In this chapter we describe the actual state of algorithms and models for deep learning and analyze the state of the art of computing devices and platforms to deploy deep learning on edge. We describe the existing computing devices for deep learning and analyze them in terms of different metrics, like performance, power and flexibility. Different technologies are to be considered including GPU, CPU, FPGA and ASIC. We will explain the trends in computing devices for deep learning on edge, what has been researched, and what should we expect from future devices.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N.E., Moshovos, A.: Cnvlutin: ineffectual-neuron-free deep neural network computing. In: 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp. 1–13 (2016). https://doi.org/10.1109/ISCA.2016.11
Aydonat, U., O’Connell, S., Capalija, D., Ling, A.C., Chiu, G.R.: An opencl™deep learning accelerator on arria 10. In: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 55–64. FPGA’17, ACM, New York, NY, USA (2017). https://doi.org/10.1145/3020078.3021738
Cadence: Tensilica DNA Processor IP For AI Inference (Oct 2017). https://ip.cadence.com/uploads/datasheets/TIP_PB_AI_Processor_FINAL.pdf
Chen, Y., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circuits 52(1), 127–138 (2017). https://doi.org/10.1109/JSSC.2016.2616357
Courbariaux, M., Bengio, Y.: Binarynet: training deep neural networks with weights and activations constrained to +1 or \(-\)1. CoRR abs/1602.02830 (2016). http://arxiv.org/abs/1602.02830
Courbariaux, M., Bengio, Y., David, J.: Binaryconnect: training deep neural networks with binary weights during propagations. CoRR abs/1511.00363 (2015). http://arxiv.org/abs/1511.00363
Davies, M., Srinivasa, N., Lin, T., Chinya, G., Cao, Y., Choday, S.H., Dimou, G., Joshi, P., Imam, N., Jain, S., Liao, Y., Lin, C., Lines, A., Liu, R., Mathaikutty, D., McCoy, S., Paul, A., Tse, J., Venkataramanan, G., Weng, Y., Wild, A., Yang, Y., Wang, H.: Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1), 82–99 (2018). https://doi.org/10.1109/MM.2018.112130359
Flex Logic Technologies, Inc.: Flex Logic Improves Deep Learning Performance by 10X with new EFLX4K AI eFPGA Core (June 2018)
Fujii, T., Toi, T., Tanaka, T., Togawa, K., Kitaoka, T., Nishino, K., Nakamura, N., Nakahara, H., Motomura, M.: New generation dynamically reconfigurable processor technology for accelerating embedded AI applications. In: 2018 IEEE Symposium on VLSI Circuits, pp. 41–42 (June 2018). https://doi.org/10.1109/VLSIC.2018.8502438
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Gordon, G., Dunson, D., Dudk, M. (eds.) Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 15, pp. 315–323. PMLR, Fort Lauderdale, FL, USA (11–13 Apr 2011). http://proceedings.mlr.press/v15/glorot11a.html
Guo, K., Zeng, S., Yu, J., Wang, Y., Yang, H.: A survey of FPGA based neural network accelerator. CoRR abs/1712.08934 (2017). http://arxiv.org/abs/1712.08934
Guo, S., Wang, L., Chen, B., Dou, Q., Tang, Y., Li, Z.: Fixcaffe: Training cnn with low precision arithmetic operations by fixed point caffe. In: APPT (2017)
Guo, K., Sui, L., Qiu, J., Yu, J., Wang, J., Yao, S., Han, S., Wang, Y., Yang, H.: Angel-eye: a complete design flow for mapping cnn onto embedded fpga. IEEE Trans. Comput. Aided Des. Integr. Circ. Syst. 37(1), 35–47 (2018). https://doi.org/10.1109/TCAD.2017.2705069
Gyrfalcon Technology: Lightspeeur 2803S Neural Accelerator (Jan 2018)
Gysel, P., Motamedi, M., Ghiasi, S.: Hardware-oriented approximation of convolutional neural networks. In: Proceedings of the 4th International Conference on Learning Representations (2016)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and Huffman coding. In: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2–4 May 2016, Conference Track Proceedings (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Higginbotham, S.: Google Takes Unconventional Route with Homegrown Machine Learning Chips (May 2016)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006). https://doi.org/10.1126/science.1127647
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR abs/1207.0580 (2012)
Intel: Intel Movidius Myriad X VPU (Aug 2017)
Judd, P., Albericio, J., Hetherington, T., Aamodt, T.M., Moshovos, A.: Stripes: Bit-serial deep neural network computing. In: 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 1–12 (Oct 2016). https://doi.org/10.1109/MICRO.2016.7783722
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097–1105. NIPS’12, Curran Associates Inc., USA (2012)
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems 2, pp. 396–404. Morgan-Kaufmann (1990)
Li, F., Liu, B.: Ternary weight networks. CoRR abs/1605.04711 (2016). http://arxiv.org/abs/1605.04711
Linley Group: Ceva NeuPro Accelerates Neural Nets (Jan 2018)
Liu, Y., Yang, C., Jiang, L., Xie, S., Zhang, Y.: Intelligent edge computing for iot-based energy management in smart cities. IEEE Netw. 33(2), 111–117 (2019). https://doi.org/10.1109/MNET.2019.1800254. March
Liu, Z., Dou, Y., Jiang, J., Xu, J., Li, S., Zhou, Y., Xu, Y.: Throughput-optimized FPGA accelerator for deep convolutional neural networks. ACM Trans. Reconfig. Technol. Syst. 10(3), 17:1–17:23 (Jul 2017). https://doi.org/10.1145/3079758
Markakis, E.K., Karras, K., Zotos, N., Sideris, A., Moysiadis, T., Corsaro, A., Alexiou, G., Skianis, C., Mastorakis, G., Mavromoustakis, C.X., Pallis, E.: Exegesis: Extreme edge resource harvesting for a virtualized fog environment. IEEE Communications Magazine 55(7), 173–179 (July 2017). https://doi.org/10.1109/MCOM.2017.1600730
Mavromoustakis, C.X., Batalla, J.M., Mastorakis, G., Markakis, E., Pallis, E.: Socially oriented edge computing for energy awareness in iot architectures. IEEE Commun. Mag. 56(7), 139–145 (2018). https://doi.org/10.1109/MCOM.2018.1700600. July
Nurvitadhi, E., Venkatesh, G., Sim, J., Marr, D., Huang, R., Ong Gee Hock, J., Liew, Y.T., Srivatsan, K., Moss, D., Subhaschandra, S., Boudoukh, G.: Can FPGAs beat GPUs in accelerating next-generation deep neural networks? In: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 5–14. FPGA ’17, ACM, New York, NY, USA (2017). https://doi.org/10.1145/3020078.3021740
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: A deep neural network architecture for real-time semantic segmentation. CoRR abs/1606.02147 (2016). http://arxiv.org/abs/1606.02147
Peres, T., Gonalves, A., Véstias, M.: Faster convolutional neural networks in low density FPGAs using block pruning. In: 15th Annual International Symposium on Applied Reconfigurable Computing (April 2019)
Qiao, Y., Shen, J., Xiao, T., Yang, Q., Wen, M., Zhang, C.: Fpga-accelerated deep convolutional neural networks for high throughput and energy efficiency. Concu. Comput. Pract. Exp. 29(20), e3850–n/a (2017). https://doi.org/10.1002/cpe.3850,e3850cpe.3850
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Inverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation. CoRR abs/1801.04381 (2018). http://arxiv.org/abs/1801.04381
Shin, D., Lee, J., Lee, J., Yoo, H.: 14.2 DNPU: An 8.1tops/w reconfigurable CNN-RNN processor for general-purpose deep neural networks. In: 2017 IEEE International Solid-State Circuits Conference (ISSCC), pp. 240–241 (Feb 2017). https://doi.org/10.1109/ISSCC.2017.7870350
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014). http://arxiv.org/abs/1409.1556
Suda, N., Chandra, V., Dasika, G., Mohanty, A., Ma, Y., Vrudhula, S., Seo, J.s., Cao, Y.: Throughput-optimized opencl-based fpga accelerator for large-scale convolutional neural networks. In: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 16–25. FPGA ’16, ACM, New York, NY, USA (2016). https://doi.org/10.1145/2847263.2847276
Synopsys: DesignWare EV6x Vision Processors (Oct 2017). https://www.synopsys.com/dw/ipdir.php?ds=ev6x-vision-processors
Sze, V., Chen, Y., Yang, T., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. of the IEEE 105(12), 2295–2329 (2017). https://doi.org/10.1109/JPROC.2017.2761740. Dec
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR abs/1602.07261 (2016). http://arxiv.org/abs/1602.07261
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. CoRR abs/1409.4842 (2014). http://arxiv.org/abs/1409.4842
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. CoRR abs/1512.00567 (2015). http://arxiv.org/abs/1512.00567
Tractica: Deep Learning Chipsets (Jan 2019). https://www.tractica.com/research/deep-learning-chipsets/
Valdes Pena, M.D., Rodriguez-Andina, J.J., Manic, M.: The internet of things: the role of reconfigurable platforms. IEEE Ind. Electron. Mag. 11(3), 6–19 (2017). https://doi.org/10.1109/MIE.2017.2724579. Sep
Venieris, S.I., Bouganis, C.: fpgaconvnet: Mapping regular and irregular convolutional neural networks on FPGAs. IEEE Trans. Neural Netw. Learn. Syst. 1–17 (2018). https://doi.org/10.1109/TNNLS.2018.2844093
Véstias, M., Duarte, R.P., Sousa, J.T.d., Neto, H.: Lite-CNN: a high-performance architecture to execute CNNs in low density FPGAs. In: Proceedings of the 28th International Conference on Field Programmable Logic and Applications (2018)
Wang, J., Lou, Q., Zhang, X., Zhu, C., Lin, Y., Chen., D.: Design flow of accelerating hybrid extremely low bit-width neural network in embedded FPGA. In: 28th International Conference on Field-Programmable Logic and Applications (2018)
Xilinx: Versal: the first adaptive compute acceleration platform (acap) (Oct 2018), https://www.xilinx.com/support/documentation/white_papers/wp505-versal-acap.pdf
Yin, S., Ouyang, P., Tang, S., Tu, F., Li, X., Zheng, S., Lu, T., Gu, J., Liu, L., Wei, S.: A high energy efficient reconfigurable hybrid neural network processor for deep learning applications. IEEE J. Solid-State Circ. 53(4), 968–982 (2018). https://doi.org/10.1109/JSSC.2017.2778281. April
Yu, J., Lukefahr, A., Palframan, D., Dasika, G., Das, R., Mahlke, S.: Scalpel: Customizing DNN pruning to the underlying hardware parallelism. In: 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), pp. 548–560 (June 2017). https://doi.org/10.1145/3079856.3080215
Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. CoRR abs/1606.06160 (2016). http://arxiv.org/abs/1606.06160
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Véstias, M. (2020). Processing Systems for Deep Learning Inference on Edge Devices. In: Mastorakis, G., Mavromoustakis, C., Batalla, J., Pallis, E. (eds) Convergence of Artificial Intelligence and the Internet of Things. Internet of Things. Springer, Cham. https://doi.org/10.1007/978-3-030-44907-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-44907-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44906-3
Online ISBN: 978-3-030-44907-0
eBook Packages: EngineeringEngineering (R0)