{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:12:35Z","timestamp":1742983955160,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031709463"},{"type":"electronic","value":"9783031709470"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70947-0_7","type":"book-chapter","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:45:27Z","timestamp":1735379127000},"page":"127-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified and\u00a0Energy-Efficient Depthwise Separable Convolution Accelerator"],"prefix":"10.1007","author":[{"given":"Yi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Lou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Lanius","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Freye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johnson","family":"Loh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Gemmeke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,29]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139. Boston, MA, USA (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800\u20131807. Honolulu, HI, USA (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"7_CR3","unstructured":"Howard, AG., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobileNetV2: inverted residuals and linear bottlenecks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510\u20134520. Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848-6856. Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"7_CR7","unstructured":"Tan, M.X., Quoc, V.Le.: EfficientNet: rethinking model scaling for convolutional neural networks (2019)"},{"key":"7_CR8","unstructured":"Vaswani, A., et al.: Attention is all you need. In: 31st Conference on Neural Information Processing Systems, Association of Computational Machinery (2017)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Proceedings of Annual Conference on International Speech Communication Association, pp. 5036\u20135040 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Yu-Hsin., et al.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circ. (JSSC), 127\u2013138 (2017)","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Yue, J.S, et al.: A 3.77 TOPS\/W convolutional neural network processor with priority-driven kernel optimization. IEEE Trans. Circ. Syst. II: Express Briefs, 277\u2013281 (2019)","DOI":"10.1109\/TCSII.2018.2846698"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Chang, K.W., et al.: VWA: hardware efficient vectorwise accelerator for convolutional neural network. IEEE Trans. Circu. Syst. I: Regular Papers, 145\u2013154 (2020)","DOI":"10.1109\/TCSI.2019.2942529"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Tu, F.B., et al.: Deep convolutional neural network architecture with reconfigurable computation patterns. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 2220\u20132233 (2017)","DOI":"10.1109\/TVLSI.2017.2688340"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Anders, M.A., et al.: 2.9 TOPS\/W reconfigurable dense\/sparse matrix-multiply accelerator with unified INT8\/INTI6\/FP16 Datapath in 14NM Tri-Gate CMOS. In: IEEE Symposium on VLSI Circuits, pp. 39\u201340 (2018)","DOI":"10.1109\/VLSIC.2018.8502333"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Kim, H., et al.: Row-streaming dataflow using a chaining buffer and systolic array+ structure. In: IEEE Computer Architecture Letters, pp. 34\u201337 (2021)","DOI":"10.1109\/LCA.2021.3054371"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Wu, X., Ma, Y., Wang, Z.: Efficient inference of large-scale and lightweight convolutional neural networks on FPGA. In: 2020 IEEE 33rd International System-on-Chip Conference (SOCC), pp. 168\u2013173. Las Vegas, NV, USA (2020)","DOI":"10.1109\/SOCC49529.2020.9524773"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"An, F., et al.: A high performance reconfigurable hardware architecture for lightweight convolutional neural network. Electronics (2023)","DOI":"10.3390\/electronics12132847"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Liu, X., Guo, T., Zhao, Z.: A high-performance FPGA-based depthwise separable convolution accelerator. Electronics (2023)","DOI":"10.3390\/electronics12071571"},{"issue":"10","key":"7_CR19","first-page":"4003","volume":"69","author":"L Xuan","year":"2020","unstructured":"Xuan, L., et al.: An FPGA-based energy-efficient reconfigurable depthwise separable convolution accelerator for image recognition. IEEE Trans. Circuits Syst. II Express Briefs 69(10), 4003\u20134007 (2020)","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Wu, D., et al.: A high-performance CNN processor based on FPGA for MobileNets. In: 29th International Conference on Field Programmable Logic and Applications (FPL), pp. 136\u2013143. Barcelona, Spain (2019)","DOI":"10.1109\/FPL.2019.00030"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Xiao, C.H., et al.: FGPA: fine-grained pipelined acceleration for depthwise separable CNN in resource constraint scenarios. IEEE (ISPA\/BDCloud\/SocialCom\/SustainCom), pp. 246\u2013254 (2021)","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00044"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lou, J., Lanius, C., Freye, F., Loh, J., Gemmeke, T.:An energy-efficient and area-efficient depthwise separable convolution accelerator with minimal on-chip memory access. In: IFIP\/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC), pp. 1\u20136. Dubai, United Arab Emirates (2023)","DOI":"10.1109\/VLSI-SoC57769.2023.10321918"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Kung, H.T.: Why Systolic Architectures? Computer, pp. 37\u201346 (1982)","DOI":"10.1109\/MC.1982.1653825"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, Y., Yang, X.: A low memory requirement mobilenets accelerator based on FPGA for auxiliary medical tasks. In: Bioengineering, Basel (2022)","DOI":"10.3390\/bioengineering10010028"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Fan, Z., Hu, W., Guo, H., Liu, F., Xu, D.: Hardware and algorithm co-optimization for pointwise convolution and channel shuffle in ShuffleNet V2. In: 2021 IEEE International Conference on Systems. Man, and Cybernetics (SMC), pp. 3212\u20133217. Melbourne, Australia (2021)","DOI":"10.1109\/SMC52423.2021.9659057"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Ou, J., Li, X., Sun, Y., Shi, Y.: A configurable hardware accelerator based on hybrid dataflow for depthwise separable convolution. In: 4th International Conference on Advances in Computer Technology. Information Science and Communications (CTISC), pp. 1\u20135. Suzhou, China (2022)","DOI":"10.1109\/CTISC54888.2022.9849816"},{"key":"7_CR27","unstructured":"Esser, S.K., McKinstry, J.L., Bablani, D., Appuswamy, R., Modha, D.S.: Learned Step Size Quantization. ArXiv (2019)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Chong, Y.S., et al.: An energy-efficient convolution unit for Depthwise separable convolutional neural networks. In: IEEE International Symposium on Circuits and System (ISCAS), pp. 1\u20135 (2021)","DOI":"10.1109\/ISCAS51556.2021.9401192"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, Z., Li, S., Yu, Z., Li, H.: Accelerating compact convolutional neural networks with multi-threaded data streaming. In: 2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 519\u2013522 (2019)","DOI":"10.1109\/ISVLSI.2019.00099"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Shao, Z., et al.: Memory-efficient CNN accelerator based on interlayer feature map compression. IEEE Trans. Circ. Syst. I: Regular Pap. 668\u2013681 (2021)","DOI":"10.1109\/TCSI.2021.3120312"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Hsiao, S., Tsai, B.: Efficient computation of Depthwise separable convolution in MoblieNet deep neural network models. In: 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), pp. 1\u20132 (2021)","DOI":"10.1109\/ICCE-TW52618.2021.9602973"},{"key":"7_CR32","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.vlsi.2017.02.002","volume":"58","author":"A Stillmaker","year":"2017","unstructured":"Stillmaker, A., Baas, B.M.: Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nm. Integration 58, 74\u201381 (2017)","journal-title":"Integration"},{"key":"7_CR33","doi-asserted-by":"publisher","first-page":"9785","DOI":"10.1109\/ACCESS.2021.3050670","volume":"9","author":"C Latotzke","year":"2021","unstructured":"Latotzke, C., Gemmeke, T.: Efficiency versus accuracy: a review of design techniques for DNN hardware accelerators. IEEE Access 9, 9785\u20139799 (2021)","journal-title":"IEEE Access"}],"container-title":["IFIP Advances in Information and Communication Technology","VLSI-SoC 2023: Innovations for Trustworthy Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70947-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T10:03:16Z","timestamp":1735380196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70947-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031709463","9783031709470"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70947-0_7","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 December 2024","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":"Dubai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Arab Emirates","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"vlsi-soc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/vlsi-soc2023\/home?pli=1","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}