{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:30:48Z","timestamp":1775273448100,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030816407","type":"print"},{"value":"9783030816414","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-81641-4_5","type":"book-chapter","created":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T13:05:01Z","timestamp":1626267901000},"page":"87-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Assessing the Configuration Space of the Open Source NVDLA Deep Learning Accelerator on a Mainstream MPSoC Platform"],"prefix":"10.1007","author":[{"given":"Alessandro","family":"Veronesi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Bertozzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milos","family":"Krstic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,15]]},"reference":[{"issue":"8","key":"5_CR1","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/JPROC.2019.2921977","volume":"107","author":"J Chen","year":"2019","unstructured":"Chen, J., Ran, X.: Deep learning with edge computing: a review. Proc. IEEE 107(8), 1655\u201316674 (2019). https:\/\/doi.org\/10.1109\/JPROC.2019.2921977","journal-title":"Proc. IEEE"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"DiCecco, R., Lacey, G., Vasiljevic, J., Chow, P., Taylor, G., Areibi, S.: Caffeinated FPGAs: FPGA framework for convolutional neural networks. In: Proceedings of the 2016 International Conference on FPT, pp. 265\u2013268 (2016). https:\/\/doi.org\/10.1109\/FPT.2016.7929549","DOI":"10.1109\/FPT.2016.7929549"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Farshchi, F., Huang, Q., Yun, H.: Integrating NVIDIA deep learning accelerator (NVDLA) with RISC-V SoC on FireSim. arXiv preprint (2019). arXiv:1903.06495v2","DOI":"10.1109\/EMC249363.2019.00012"},{"key":"5_CR4","unstructured":"Genc, H., et al.: Gemmini: an agile systolic array generator enabling systematic evaluations of deep-learning architectures. arXiv preprint (2019). arXiv:1911.09925"},{"key":"5_CR5","unstructured":"Gonzalez, A., Hong, C.: A Chipyard Comparison of NVDLA and Gemmini. http:\/\/charleshong3.github.io\/projects\/nvdla_v_gemmini.pdf"},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Guoyu, C., Zhenjiang, P., Shanggong, F., Dawei, W., Jingwen, C., Shengang, Z.: Research on the architecture of edge computing SoC with ultra-low power. In: Proceedings of the 2020 IEEE 3rd International Conference on Electronics Technology (ICET), pp. 54\u201357 (2020). https:\/\/doi.org\/10.1109\/ICET49382.2020.9119600","DOI":"10.1109\/ICET49382.2020.9119600"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 84\u201390 (2012). https:\/\/doi.org\/10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"5_CR8","doi-asserted-by":"publisher","unstructured":"Lin, W., Hsieh, C., Chou, C.: ONNC-based software development platform for configurable NVDLA designs. In: Proceedings of the 2019 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), pp. 1\u20132 (2019). https:\/\/doi.org\/10.1109\/VLSI-DAT.2019.8741778","DOI":"10.1109\/VLSI-DAT.2019.8741778"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Lin, W., et al.: ONNC: a compilation framework connecting ONNX to proprietary deep learning accelerators. In: Proceedings of the 2019 IEEE International Conference on AICAS, pp. 214\u2013218 (2019). https:\/\/doi.org\/10.1109\/AICAS.2019.8771510","DOI":"10.1109\/AICAS.2019.8771510"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Liu, S.-M., Tang, L., Huang, N.-C., Tsai, D.-Y., Yang, M.-X., Wu, K.-C.: Fault-tolerance mechanism analysis on NVDLA-based design using open neural network compiler and quantization calibrator. In: Proceedings of the 2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), pp. 1\u20133 (2020). https:\/\/doi.org\/10.1109\/VLSI-DAT49148.2020.9196335","DOI":"10.1109\/VLSI-DAT49148.2020.9196335"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Lu, L., Liang, Y., Xiao, Q., Yan, S.: Evaluating fast algorithms for convolutional neural networks on FPGAs. In: Proceedings of the 25th IEEE International Symposium on FCCM, pp. 101\u2013108 (2017). https:\/\/doi.org\/10.1109\/FCCM.2017.64","DOI":"10.1109\/FCCM.2017.64"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Luo, S.: Customization of a deep learning accelerator. In: Proceedings of the 2019 International Symposium on VLSI-DAT, pp. 1\u20132 (2019). https:\/\/doi.org\/10.1109\/VLSI-DAT.2019.8741855","DOI":"10.1109\/VLSI-DAT.2019.8741855"},{"key":"5_CR13","unstructured":"Moreau, T., Chen, T., Jiang, Z., Ceze, L., Guestrin, C., Krishnamurthy, A.: VTA: an open hardware-software stack for deep learning. arXiv preprint abs\/1807.04188 (2018)"},{"key":"5_CR14","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, pp. 26\u201335 (2016). https:\/\/doi.org\/10.1145\/2847263.2847265","DOI":"10.1145\/2847263.2847265"},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","volume":"7","author":"A Shawahna","year":"2019","unstructured":"Shawahna, A., Sait, S.M., El-Maleh, A.: FPGA-based accelerators of deep learning networks for learning and classification: a review. IEEE Access 7, 7823\u20137859 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2018.2890150","journal-title":"IEEE Access"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Suda, N., et al.: 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 (2016). https:\/\/doi.org\/10.1145\/2847263.2847276","DOI":"10.1145\/2847263.2847276"},{"issue":"12","key":"5_CR17","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.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295\u20132329 (2017). https:\/\/doi.org\/10.1109\/JPROC.2017.2761740","journal-title":"Proc. IEEE"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2014). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Udupa, P., Mahale, G., Chandrasekharan, K.K., Lee, S.: Accelerating depthwise convolution and pooling operations on z-first storage CNN architectures. In: Proceedings of the 2020 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20135 (2020). https:\/\/doi.org\/10.1109\/ISCAS45731.2020.9180863","DOI":"10.1109\/ISCAS45731.2020.9180863"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Veronesi, A., Krstic, M., Bertozzi, D.: Cross-layer hardware\/software assessment of the open-source NVDLA configurable deep learning accelerator. In: Proceedings of the 28th IFIP\/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), pp. 1\u20136 (2020). https:\/\/doi.org\/10.1109\/VLSI-SOC46417.2020.9344109","DOI":"10.1109\/VLSI-SOC46417.2020.9344109"},{"key":"5_CR21","doi-asserted-by":"publisher","unstructured":"Wang, D., Xu, K., Jiang, D.: PipeCNN: an OpenCL-based open-source FPGA accelerator for convolution neural networks. In: Proceedings of the 2017 International Conference on FPT, pp. 279\u2013282 (2017). https:\/\/doi.org\/10.1109\/FPT.2017.8280160","DOI":"10.1109\/FPT.2017.8280160"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Xu, Z., Abraham, J.: Design of a safe convolutional neural network accelerator. In: Proceedings of the 2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 247\u2013252 (2019). https:\/\/doi.org\/10.1109\/ISVLSI.2019.00053","DOI":"10.1109\/ISVLSI.2019.00053"},{"key":"5_CR23","doi-asserted-by":"publisher","unstructured":"Xu, Z., Abraham, J.: Safety design of a convolutional neural network accelerator with error localization and correction. In: Proceedings of the 2019 IEEE International Test Conference (ITC), pp. 1\u201310 (2019). https:\/\/doi.org\/10.1109\/ITC44170.2019.9000149","DOI":"10.1109\/ITC44170.2019.9000149"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"Yakun, S.S., et al.: Simba: scaling deep-learning inference with multi-chip-module-based architecture. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 14\u201327 (2019). https:\/\/doi.org\/10.1145\/3352460.3358302","DOI":"10.1145\/3352460.3358302"},{"key":"5_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, J., Li, J.: Improving the performance of OpenCL-based FPGA accelerator for convolutional neural network. In: Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 25\u201334 (2017). https:\/\/doi.org\/10.1145\/3020078.3021698","DOI":"10.1145\/3020078.3021698"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, X., et al.: DNNBuilder: an automated tool for building high-performance DNN hardware accelerators for FPGAs. In: Proceedings of the 2018 International Conference on Computer-Aided Design, pp. 1\u20138 (2018). https:\/\/doi.org\/10.1145\/3240765.3240801","DOI":"10.1145\/3240765.3240801"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Zhou, G., Zhou, J., Lin, H.: Research on NVIDIA deep learning accelerator. In: Proceedings of 12th IEEE International Conference on Anti-counterfeiting, Security, and Identification, pp. 192\u2013195 (2018). https:\/\/doi.org\/10.1109\/ICASID.2018.8693202","DOI":"10.1109\/ICASID.2018.8693202"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Zhuge, C., Liu, X., Zhang, X., Gummadi, S., Xiong, J., Chen, D.: Face recognition with hybrid efficient convolution algorithms on FPGAs. In: Proceedings of the 2018 GLSVLSI Great Lakes Symposium on VLSI, pp. 123\u2013128 (2018). https:\/\/doi.org\/10.1145\/3194554.3194597","DOI":"10.1145\/3194554.3194597"},{"key":"5_CR29","unstructured":"Internet: GitHub issue $$\\#110$$: NVDLA running on a FPGA platform. github.com\/nvdla\/hw\/issues"},{"key":"5_CR30","unstructured":"Internet: NVIDIA Jetson modules. www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/"},{"key":"5_CR31","unstructured":"Internet: NVIDIA TensorRT library. developer.nvidia.com\/tensorrt"},{"key":"5_CR32","unstructured":"Internet: NVDLA open source project. nvdla.org"},{"key":"5_CR33","unstructured":"Internet: NVDLA low precision support. github.com\/nvdla\/sw\/blob\/v1.2.0-OC\/LowPrecision.md"},{"key":"5_CR34","unstructured":"Internet: RISC-V Foundation. riscv.org"}],"container-title":["IFIP Advances in Information and Communication Technology","VLSI-SoC: Design Trends"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-81641-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,13]],"date-time":"2025-07-13T22:03:14Z","timestamp":1752444194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-81641-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030816407","9783030816414"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-81641-4_5","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"15 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VLSI-SoC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP\/IEEE International Conference on Very Large Scale Integration - System on a Chip","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salt Lake City, UT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"vlsi-soc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/vlsisoc2020.eng.utah.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}