{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:43:55Z","timestamp":1755798235486},"publisher-location":"Cham","reference-count":53,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030449063"},{"type":"electronic","value":"9783030449070"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-44907-0_9","type":"book-chapter","created":{"date-parts":[[2020,5,6]],"date-time":"2020-05-06T09:04:57Z","timestamp":1588755897000},"page":"213-240","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Processing Systems for Deep Learning Inference on Edge Devices"],"prefix":"10.1007","author":[{"given":"M\u00e1rio","family":"V\u00e9stias","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,7]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"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\u201313 (2016). \nhttps:\/\/doi.org\/10.1109\/ISCA.2016.11","DOI":"10.1109\/ISCA.2016.11"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Aydonat, U., O\u2019Connell, S., Capalija, D., Ling, A.C., Chiu, G.R.: An opencl\u2122deep learning accelerator on arria 10. In: Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 55\u201364. FPGA\u201917, ACM, New York, NY, USA (2017). \nhttps:\/\/doi.org\/10.1145\/3020078.3021738","DOI":"10.1145\/3020078.3021738"},{"key":"9_CR3","unstructured":"Cadence: Tensilica DNA Processor IP For AI Inference (Oct 2017). \nhttps:\/\/ip.cadence.com\/uploads\/datasheets\/TIP_PB_AI_Processor_FINAL.pdf"},{"issue":"1","key":"9_CR4","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"Y Chen","year":"2017","unstructured":"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\u2013138 (2017). \nhttps:\/\/doi.org\/10.1109\/JSSC.2016.2616357","journal-title":"IEEE J. Solid-State Circuits"},{"key":"9_CR5","unstructured":"Courbariaux, M., Bengio, Y.: Binarynet: training deep neural networks with weights and activations constrained to +1 or $$-$$1. CoRR abs\/1602.02830 (2016). \nhttp:\/\/arxiv.org\/abs\/1602.02830"},{"key":"9_CR6","unstructured":"Courbariaux, M., Bengio, Y., David, J.: Binaryconnect: training deep neural networks with binary weights during propagations. CoRR abs\/1511.00363 (2015). \nhttp:\/\/arxiv.org\/abs\/1511.00363"},{"issue":"1","key":"9_CR7","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","volume":"38","author":"M Davies","year":"2018","unstructured":"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\u201399 (2018). \nhttps:\/\/doi.org\/10.1109\/MM.2018.112130359","journal-title":"IEEE Micro"},{"key":"9_CR8","unstructured":"Flex Logic Technologies, Inc.: Flex Logic Improves Deep Learning Performance by 10X with new EFLX4K AI eFPGA Core (June 2018)"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"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\u201342 (June 2018). \nhttps:\/\/doi.org\/10.1109\/VLSIC.2018.8502438","DOI":"10.1109\/VLSIC.2018.8502438"},{"key":"9_CR10","unstructured":"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.\u00a015, pp. 315\u2013323. PMLR, Fort Lauderdale, FL, USA (11\u201313 Apr 2011). \nhttp:\/\/proceedings.mlr.press\/v15\/glorot11a.html"},{"key":"9_CR11","unstructured":"Guo, K., Zeng, S., Yu, J., Wang, Y., Yang, H.: A survey of FPGA based neural network accelerator. CoRR abs\/1712.08934 (2017). \nhttp:\/\/arxiv.org\/abs\/1712.08934"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"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)","DOI":"10.1007\/978-3-319-67952-5_4"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"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\u201347 (2018). \nhttps:\/\/doi.org\/10.1109\/TCAD.2017.2705069","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"9_CR14","unstructured":"Gyrfalcon Technology: Lightspeeur 2803S Neural Accelerator (Jan 2018)"},{"key":"9_CR15","unstructured":"Gysel, P., Motamedi, M., Ghiasi, S.: Hardware-oriented approximation of convolutional neural networks. In: Proceedings of the 4th International Conference on Learning Representations (2016)"},{"key":"9_CR16","unstructured":"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\u20134 May 2016, Conference Track Proceedings (2016)"},{"key":"9_CR17","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). \nhttp:\/\/arxiv.org\/abs\/1512.03385"},{"key":"9_CR18","unstructured":"Higginbotham, S.: Google Takes Unconventional Route with Homegrown Machine Learning Chips (May 2016)"},{"issue":"5786","key":"9_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006). \nhttps:\/\/doi.org\/10.1126\/science.1127647","journal-title":"Science"},{"key":"9_CR20","unstructured":"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)"},{"key":"9_CR21","unstructured":"Intel: Intel Movidius Myriad X VPU (Aug 2017)"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"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\u201312 (Oct 2016). \nhttps:\/\/doi.org\/10.1109\/MICRO.2016.7783722","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"9_CR23","unstructured":"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\u20131105. NIPS\u201912, Curran Associates Inc., USA (2012)"},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436\u2013444 (2015). \nhttps:\/\/doi.org\/10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"9_CR25","unstructured":"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\u2013404. Morgan-Kaufmann (1990)"},{"key":"9_CR26","unstructured":"Li, F., Liu, B.: Ternary weight networks. CoRR abs\/1605.04711 (2016). \nhttp:\/\/arxiv.org\/abs\/1605.04711"},{"key":"9_CR27","unstructured":"Linley Group: Ceva NeuPro Accelerates Neural Nets (Jan 2018)"},{"issue":"2","key":"9_CR28","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/MNET.2019.1800254","volume":"33","author":"Y Liu","year":"2019","unstructured":"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\u2013117 (2019). \nhttps:\/\/doi.org\/10.1109\/MNET.2019.1800254\n\n. March","journal-title":"IEEE Netw."},{"key":"9_CR29","doi-asserted-by":"publisher","unstructured":"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\u201317:23 (Jul 2017). \nhttps:\/\/doi.org\/10.1145\/3079758","DOI":"10.1145\/3079758"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"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\u2013179 (July 2017). \nhttps:\/\/doi.org\/10.1109\/MCOM.2017.1600730","DOI":"10.1109\/MCOM.2017.1600730"},{"issue":"7","key":"9_CR31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/MCOM.2018.1700600","volume":"56","author":"CX Mavromoustakis","year":"2018","unstructured":"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\u2013145 (2018). \nhttps:\/\/doi.org\/10.1109\/MCOM.2018.1700600\n\n. July","journal-title":"IEEE Commun. Mag."},{"key":"9_CR32","doi-asserted-by":"publisher","unstructured":"Nurvitadhi, E., Venkatesh, G., Sim, J., Marr, D., Huang, R., Ong Gee\u00a0Hock, 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\u201314. FPGA \u201917, ACM, New York, NY, USA (2017). \nhttps:\/\/doi.org\/10.1145\/3020078.3021740","DOI":"10.1145\/3020078.3021740"},{"key":"9_CR33","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: A deep neural network architecture for real-time semantic segmentation. CoRR abs\/1606.02147 (2016). \nhttp:\/\/arxiv.org\/abs\/1606.02147"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Peres, T., Gonalves, A., V\u00e9stias, M.: Faster convolutional neural networks in low density FPGAs using block pruning. In: 15th Annual International Symposium on Applied Reconfigurable Computing (April 2019)","DOI":"10.1007\/978-3-030-17227-5_28"},{"key":"9_CR35","doi-asserted-by":"publisher","unstructured":"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\u2013n\/a (2017). \nhttps:\/\/doi.org\/10.1002\/cpe.3850,e3850cpe.3850","DOI":"10.1002\/cpe.3850,e3850cpe.3850"},{"key":"9_CR36","unstructured":"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). \nhttp:\/\/arxiv.org\/abs\/1801.04381"},{"key":"9_CR37","doi-asserted-by":"publisher","unstructured":"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\u2013241 (Feb 2017). \nhttps:\/\/doi.org\/10.1109\/ISSCC.2017.7870350","DOI":"10.1109\/ISSCC.2017.7870350"},{"key":"9_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014). \nhttp:\/\/arxiv.org\/abs\/1409.1556"},{"key":"9_CR39","doi-asserted-by":"publisher","unstructured":"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\u201325. FPGA \u201916, ACM, New York, NY, USA (2016). \nhttps:\/\/doi.org\/10.1145\/2847263.2847276","DOI":"10.1145\/2847263.2847276"},{"key":"9_CR40","unstructured":"Synopsys: DesignWare EV6x Vision Processors (Oct 2017). \nhttps:\/\/www.synopsys.com\/dw\/ipdir.php?ds=ev6x-vision-processors"},{"issue":"12","key":"9_CR41","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"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\u20132329 (2017). \nhttps:\/\/doi.org\/10.1109\/JPROC.2017.2761740\n\n. Dec","journal-title":"Proc. of the IEEE"},{"key":"9_CR42","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR abs\/1602.07261 (2016). \nhttp:\/\/arxiv.org\/abs\/1602.07261"},{"key":"9_CR43","unstructured":"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). \nhttp:\/\/arxiv.org\/abs\/1409.4842"},{"key":"9_CR44","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. CoRR abs\/1512.00567 (2015). \nhttp:\/\/arxiv.org\/abs\/1512.00567"},{"key":"9_CR45","unstructured":"Tractica: Deep Learning Chipsets (Jan 2019). \nhttps:\/\/www.tractica.com\/research\/deep-learning-chipsets\/"},{"issue":"3","key":"9_CR46","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/MIE.2017.2724579","volume":"11","author":"MD Valdes Pena","year":"2017","unstructured":"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\u201319 (2017). \nhttps:\/\/doi.org\/10.1109\/MIE.2017.2724579\n\n. Sep","journal-title":"IEEE Ind. Electron. Mag."},{"key":"9_CR47","doi-asserted-by":"publisher","unstructured":"Venieris, S.I., Bouganis, C.: fpgaconvnet: Mapping regular and irregular convolutional neural networks on FPGAs. IEEE Trans. Neural Netw. Learn. Syst. 1\u201317 (2018). \nhttps:\/\/doi.org\/10.1109\/TNNLS.2018.2844093","DOI":"10.1109\/TNNLS.2018.2844093"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"V\u00e9stias, 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)","DOI":"10.1109\/FPL.2018.00075"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"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)","DOI":"10.1109\/FPL.2018.00035"},{"key":"9_CR50","unstructured":"Xilinx: Versal: the first adaptive compute acceleration platform (acap) (Oct 2018), \nhttps:\/\/www.xilinx.com\/support\/documentation\/white_papers\/wp505-versal-acap.pdf"},{"issue":"4","key":"9_CR51","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/JSSC.2017.2778281","volume":"53","author":"S Yin","year":"2018","unstructured":"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\u2013982 (2018). \nhttps:\/\/doi.org\/10.1109\/JSSC.2017.2778281\n\n. April","journal-title":"IEEE J. Solid-State Circ."},{"key":"9_CR52","doi-asserted-by":"publisher","unstructured":"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\u2013560 (June 2017). \nhttps:\/\/doi.org\/10.1145\/3079856.3080215","DOI":"10.1145\/3079856.3080215"},{"key":"9_CR53","unstructured":"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). \nhttp:\/\/arxiv.org\/abs\/1606.06160"}],"container-title":["Internet of Things","Convergence of Artificial Intelligence and the Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-44907-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,6]],"date-time":"2020-05-06T09:08:22Z","timestamp":1588756102000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-44907-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030449063","9783030449070"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-44907-0_9","relation":{},"ISSN":["2199-1073","2199-1081"],"issn-type":[{"type":"print","value":"2199-1073"},{"type":"electronic","value":"2199-1081"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}