{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:48:58Z","timestamp":1756000138030,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030186555"},{"type":"electronic","value":"9783030186562"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-18656-2_20","type":"book-chapter","created":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T22:20:47Z","timestamp":1557786047000},"page":"267-280","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Heterogeneous and Reconfigurable Embedded Architecture for Energy-Efficient Execution of Convolutional Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2701-5881","authenticated-orcid":false,"given":"Konstantin","family":"L\u00fcbeck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1615-507X","authenticated-orcid":false,"given":"Oliver","family":"Bringmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,25]]},"reference":[{"issue":"11","key":"20_CR1","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Buttou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). \n                      https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"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 (NIPS 2012), Lake Tahoe, NV, pp. 1097\u20131105 (2012)","key":"20_CR2"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. \n                      arXiv:1409.1556\n                      \n                     (2014)","key":"20_CR3"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015). \n                      https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. \n                      arXiv:1709.01507\n                      \n                     (2017)","key":"20_CR5","DOI":"10.1109\/CVPR.2018.00745"},{"unstructured":"ImageNet Large Scale Visual Recognition Challenge 2017 Results (ILSVRC2017). \n                      http:\/\/image-net.org\/challenges\/LSVRC\/2017\/results\n                      \n                    . Accessed 19 Nov 2018","key":"20_CR6"},{"unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database. \n                      http:\/\/yann.lecun.com\/exdb\/mnist\n                      \n                    . Accessed 29 Oct 2018","key":"20_CR7"},{"doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. \n                      arXiv:1408.5093\n                      \n                     (2014)","key":"20_CR8","DOI":"10.1145\/2647868.2654889"},{"unstructured":"Nvidia cuDNN. \n                      https:\/\/developer.nvidia.com\/cudnn\n                      \n                    . Accessed 2 Nov 2018","key":"20_CR9"},{"unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. \n                      http:\/\/tensorflow.org\n                      \n                    . Accessed 14 Nov 2018","key":"20_CR10"},{"unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: Proceedings of the NIPS 2017 Workshop Autodiff, Long Beach, CA (2017)","key":"20_CR11"},{"unstructured":"Nvidia Titan RTX. \n                      https:\/\/www.nvidia.com\/en-us\/titan\/titan-rtx\n                      \n                    . Accessed 20 Feb 2019","key":"20_CR12"},{"doi-asserted-by":"publisher","unstructured":"Chen, T., et al.: DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. In: Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2014), Salt Lake City, UT, pp. 269\u2013284 (2014). \n                      https:\/\/doi.org\/10.1145\/2541940.2541967","key":"20_CR13","DOI":"10.1145\/2541940.2541967"},{"doi-asserted-by":"publisher","unstructured":"Tanomoto, M., Takamaeda-Yamazaki, S., Yao, J., Nakashima, Y.: A CGRA-based approach for accelerating convolutional neural networks. In: Proceedings of the 2015 IEEE 9th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSOC 2015), Turin, pp. 73\u201380 (2015). \n                      https:\/\/doi.org\/10.1109\/MCSoC.2015.41","key":"20_CR14","DOI":"10.1109\/MCSoC.2015.41"},{"doi-asserted-by":"publisher","unstructured":"Shi, R., et al.: A locality aware convolutional neural networks accelerator. In: Proceedings of the 2015 Euromicro Conference on Digital System Design, Funchal, pp. 591\u2013598 (2015). \n                      https:\/\/doi.org\/10.1109\/DSD.2015.70","key":"20_CR15","DOI":"10.1109\/DSD.2015.70"},{"doi-asserted-by":"publisher","unstructured":"Fan, X., Li, H., Cao, W., Wang, L.: DT-CGRA: dual-track coarse-grained reconfigurable architecture for stream applications. In: Proceedings of the 2016 26th International Conference on Field Programmable Logic and Applications (FPL), Lausanne, pp. 1\u20139 (2016). \n                      https:\/\/doi.org\/10.1109\/FPL.2016.7577309","key":"20_CR16","DOI":"10.1109\/FPL.2016.7577309"},{"doi-asserted-by":"publisher","unstructured":"Jafri, S.M.A.H., Hemani, A., Kolin, P., Abbas, N.: MOCHA: morphable locality and compression aware architecture for convolutional neural networks. In: Proceedings of the 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Orlando, FL, pp. 276\u2013286 (2007). \n                      https:\/\/doi.org\/10.1109\/IPDPS.2017.59","key":"20_CR17","DOI":"10.1109\/IPDPS.2017.59"},{"issue":"1","key":"20_CR18","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"YH Chen","year":"2017","unstructured":"Chen, Y.H., 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), 137\u2013138 (2017). \n                      https:\/\/doi.org\/10.1109\/JSSC.2016.2616357","journal-title":"IEEE J. Solid-State Circuits"},{"doi-asserted-by":"publisher","unstructured":"Zhao, B., Wang, M., Liu, M.: An energy-efficient coarse grained spatial architecture for convolutional neural networks AlexNet. IEICE Electron. Express 14(15), 20170595 (2017). \n                      https:\/\/doi.org\/10.1587\/elex.14.20170595","key":"20_CR19","DOI":"10.1587\/elex.14.20170595"},{"doi-asserted-by":"publisher","unstructured":"Shin, D., Lee, J., Lee, J., Yoo, H. J.: DNPU: an 8.1TOPS\/W reconfigurable CNN-RNN processor for general-purpose deep neural networks. In: Proceedings of the in 2017 IEEE International Solid-State Circuits Conference (ISSCC), pp. 240\u2013241, San Francisco, CA (2017). \n                      https:\/\/doi.org\/10.1109\/ISSCC.2017.7870350","key":"20_CR20","DOI":"10.1109\/ISSCC.2017.7870350"},{"issue":"1","key":"20_CR21","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSI.2017.2735490","volume":"65","author":"L Du","year":"2018","unstructured":"Du, L., et al.: A reconfigurable streaming deep convolutional neural network accelerator for Internet of Things. IEEE Trans. Circuits Syst. I Regular Papers 65(1), 198\u2013208 (2018). \n                      https:\/\/doi.org\/10.1109\/TCSI.2017.2735490","journal-title":"IEEE Trans. Circuits Syst. I Regular Papers"},{"doi-asserted-by":"publisher","unstructured":"Chakradhar, S., Sankaradas, M., Jakkula, V., Cadambi, S.: A dynamically configurable coprocessor for convolutional neural networks. In: Proceedings of the 37th Annual International Symposium on Computer Architecture (ISCA 2010), Saint-Malo, pp. 247\u2013257 (2010). \n                      https:\/\/doi.org\/10.1145\/1815961.1815993","key":"20_CR22","DOI":"10.1145\/1815961.1815993"},{"doi-asserted-by":"publisher","unstructured":"Zhang, C., Li, P., Sun, G., Xiao, B., Cong, J.: Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2015), Monterey, CA, pp. 161\u2013170 (2015). \n                      https:\/\/doi.org\/10.1145\/2684746.2689060","key":"20_CR23","DOI":"10.1145\/2684746.2689060"},{"doi-asserted-by":"publisher","unstructured":"Qiu, J., et al.: Going deeper with embedded FPGA platform for convolutional neural network. In: Proceedings of the 2016 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2016), Monterey, CA, pp. 26\u201335 (2016). \n                      https:\/\/doi.org\/10.1145\/2847263.2847265","key":"20_CR24","DOI":"10.1145\/2847263.2847265"},{"doi-asserted-by":"publisher","unstructured":"Gokhale, V., Zaidy, A., Chang, A.X.M., Culurciello, E.: Snowflake: an efficient hardware accelerator for convolutional neural networks. In: Proceedings of the 2017 IEEE International Symposium on Circuits and Systems (ISCAS), Baltimore, MD, pp. 1\u20134 (2017). \n                      https:\/\/doi.org\/10.1109\/ISCAS.2017.8050809","key":"20_CR25","DOI":"10.1109\/ISCAS.2017.8050809"},{"doi-asserted-by":"publisher","unstructured":"Hartenstein, R.: A decade of reconfigurable computing: a visionary retrospective. In: Proceedings of the Design, Automation and Test in Europe Conference and Exhibition 2001 (DATE 2001), Munich, pp. 642\u2013649 (2001). \n                      https:\/\/doi.org\/10.1109\/DATE.2001.915091","key":"20_CR26","DOI":"10.1109\/DATE.2001.915091"},{"unstructured":"Xilinx: Zynq UltraScale+ Device Technical Reference Manual, UG1085 v1.7 (2017)","key":"20_CR27"},{"issue":"3","key":"20_CR28","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1524\/itit.2007.49.3.157","volume":"49","author":"T Oppold","year":"2007","unstructured":"Oppold, T., Schweizer, T., Oliveira, J.F., Eisenhardt, S., Kuhn, T., Rosenstiel, W.: CRC - concepts and evaluation of processor-like reconfigurable architectures. Inf. Technol. IT 49(3), 157\u2013164 (2007). \n                      https:\/\/doi.org\/10.1524\/itit.2007.49.3.157","journal-title":"Inf. Technol. IT"},{"doi-asserted-by":"publisher","unstructured":"L\u00fcbeck, K., Morgenstern, D., Schweizer, T., Peterson D., Rosenstiel W., Bringmann O.: Neues Konzept zur Steigerung der Zuverl\u00e4ssigkeit einer ARM-basierten Prozessorarchitektur unter Verwendung eines CGRAs. In: 19. Workshop Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen (MBMV), Freiburg, pp. 46\u201358 (2016). \n                      https:\/\/doi.org\/10.6094\/UNIFR\/10617","key":"20_CR29","DOI":"10.6094\/UNIFR\/10617"},{"key":"20_CR30","volume-title":"Computer Architecture","author":"JL Hennessy","year":"2011","unstructured":"Hennessy, J.L., Patterson, D.A.: Computer Architecture, 5th edn. Morgan Kaufmann Publisher Inc., San Francisco (2011)","edition":"5"},{"issue":"1","key":"20_CR31","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry-standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 45\u201355 (1998). \n                      https:\/\/doi.org\/10.1109\/99.660313","journal-title":"IEEE Comput. Sci. Eng."},{"unstructured":"Pico-CNN. \n                      https:\/\/github.com\/ekut-es\/pico-cnn\n                      \n                    . Accessed 27 Feb 2019","key":"20_CR32"},{"unstructured":"CRC Configurator. \n                      https:\/\/github.com\/ekut-es\/crc_configurator\n                      \n                    . Accessed 27 Feb 2019","key":"20_CR33"},{"unstructured":"Jia, Y.: Training LeNet on MNIST with Caffe. \n                      http:\/\/caffe.berkeleyvision.org\/gathered\/examples\/mnist.html\n                      \n                    . Accessed 20 Feb 2019","key":"20_CR34"},{"unstructured":"System Management Interface Forum, PMBus Power System Management Protocol Specification Part II - Command Language, Revision 1.2 (2010)","key":"20_CR35"},{"unstructured":"Nvidia, Whitepaper NVIDIA Tegra K1 A New Era in Mobile Computing, V1.0 (2013)","key":"20_CR36"}],"container-title":["Lecture Notes in Computer Science","Architecture of Computing Systems \u2013 ARCS 2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-18656-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T10:37:08Z","timestamp":1558348628000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-18656-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030186555","9783030186562"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-18656-2_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Architecture of Computing Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 May 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 May 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arcs2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/arcs2019.itec.kit.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"40","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"24","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"60% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3.75","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}