{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:41:27Z","timestamp":1769848887746,"version":"3.49.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031783760","type":"print"},{"value":"9783031783777","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78377-7_4","type":"book-chapter","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T15:59:20Z","timestamp":1737993560000},"page":"46-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Accelerating Depthwise Separable Convolutions on\u00a0Ultra-Low-Power Devices"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9595-7216","authenticated-orcid":false,"given":"Francesco","family":"Daghero","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6215-8220","authenticated-orcid":false,"given":"Alessio","family":"Burrello","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1369-9688","authenticated-orcid":false,"given":"Massimo","family":"Poncino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9046-5618","authenticated-orcid":false,"given":"Enrico","family":"Macii","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-7071","authenticated-orcid":false,"given":"Daniele","family":"Jahier Pagliari","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Bruschi, N., et\u00a0al.: GVSoC: a highly configurable, fast and accurate full-platform simulator for RISC-V based IoT processors. In: IEEE ICCD (2021)","DOI":"10.1109\/ICCD53106.2021.00071"},{"issue":"8","key":"4_CR2","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1109\/TC.2021.3066883","volume":"70","author":"A Burrello","year":"2021","unstructured":"Burrello, A., et al.: DORY: automatic end-to-end deployment of real-world DNNs on low-cost IoT MCUs. IEEE TECS Comput. 70(8), 1253\u20131268 (2021)","journal-title":"IEEE TECS Comput."},{"key":"4_CR3","unstructured":"Chetlur, S., et\u00a0al.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"3","key":"4_CR5","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TVLSI.2020.3046125","volume":"29","author":"S Colleman","year":"2021","unstructured":"Colleman, S., Verhelst, M.: High-utilization, high-flexibility depth-first CNN coprocessor for image pixel processing on FPGA. IEEE VLSI 29(3), 461\u2013471 (2021)","journal-title":"IEEE VLSI"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Daghero, F., et\u00a0al.: Energy-efficient adaptive machine learning on IoT end-nodes with class-dependent confidence. In: IEEE ICECS (2020)","DOI":"10.1109\/ICECS49266.2020.9294863"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Flamand, E., et\u00a0al.: GAP-8: a RISC-V SoC for AI at the edge of the IoT. In: IEEE ASAP. IEEE (2018)","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Garofalo, A., et al.: PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processors. Philos. Trans. R. Soc. (2020)","DOI":"10.1098\/rsta.2019.0155"},{"key":"4_CR9","unstructured":"Han, S., et\u00a0al.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"4_CR10","unstructured":"Howard, A.G., et\u00a0al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017)"},{"key":"4_CR11","first-page":"711","volume":"3","author":"A Ivanov","year":"2021","unstructured":"Ivanov, A., et al.: Data movement is all you need: a case study on optimizing transformers. MLSys 3, 711\u2013732 (2021)","journal-title":"MLSys"},{"key":"4_CR12","unstructured":"Lai, L., et\u00a0al.: CMSIS-NN: efficient neural network kernels for arm Cortex-M CPUs. arXiv preprint arXiv:1801.06601 (2018)"},{"key":"4_CR13","unstructured":"Lin, J., et\u00a0al.: MCUNetV2: memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352 (2021)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Niu, W., et\u00a0al.: DNNFusion: accelerating deep neural networks execution with advanced operator fusion. In: ACM PLDI 2021, pp. 883\u2013898 (2021)","DOI":"10.1145\/3453483.3454083"},{"key":"4_CR15","unstructured":"ONNX-Runtime-developers: ONNX runtime (2021). https:\/\/onnxruntime.ai\/"},{"issue":"1","key":"4_CR16","first-page":"127","volume":"57","author":"D Rossi","year":"2022","unstructured":"Rossi, D., et al.: Vega: a ten-core SoC for IoTa endnodes with DNN acceleration and cognitive wake-up from MRAM-based state-retentive sleep mode. IEEE JSSC 57(1), 127\u2013139 (2022)","journal-title":"IEEE JSSC"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Sandler, M., et\u00a0al.: MobileNetV2: inverted residuals and linear bottlenecks (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Tillet, P., et\u00a0al.: Triton: an intermediate language and compiler for tiled neural network computations. In: ACM PLDI, pp. 10\u201319 (2019)","DOI":"10.1145\/3315508.3329973"},{"key":"4_CR19","unstructured":"Zhang, Y., et\u00a0al.: Hello edge: keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128 (2017)"}],"container-title":["Lecture Notes in Computer Science","Embedded Computer Systems: Architectures, Modeling, and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78377-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T15:59:27Z","timestamp":1737993567000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78377-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031783760","9783031783777"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78377-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SAMOS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Samos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"samos2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/samos-conference.com\/wp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}