{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:50:36Z","timestamp":1783036236388,"version":"3.54.6"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","award":["nCORE"],"award-info":[{"award-number":["nCORE"]}],"id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1740126"],"award-info":[{"award-number":["1740126"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2020,4,30]]},"abstract":"<jats:p>In this work, we propose a multiplication-less binarized depthwise-separable convolution neural network, called BD-Net. BD-Net is designed to use binarized depthwise separable convolution block as the drop-in replacement of conventional spatial-convolution in deep convolution neural network (DNN). In BD-Net, the computation-expensive convolution operations (i.e., Multiplication and Accumulation) are converted into energy-efficient Addition\/Subtraction operations. For further compressing the model size while maintaining the dominant computation in addition\/subtraction, we propose a brand-new sparse binarization method with a hardware-oriented structured sparsity pattern. To successfully train such sparse BD-Net, we propose and leverage two techniques: (1) a modified group-lasso regularization whose group size is identical to the capacity of basic computing core in accelerator and (2) a weight penalty clipping technique to solve the disharmony issue between weight binarization and lasso regularization. The experiment results show that the proposed sparse BD-Net can achieve comparable or even better inference accuracy, in comparison to the full precision CNN baseline. Beyond that, a BD-Net customized process-in-memory accelerator is designed using SOT-MRAM, which owns characteristics of high channel expansion flexibility and computation parallelism. Through the detailed analysis from both software and hardware perspectives, we provide an intuitive design guidance for software\/hardware co-design of DNN acceleration on mobile embedded systems. Note that this journal submission is the extended version of our previous published paper in ISVLSI 2018 [24].<\/jats:p>","DOI":"10.1145\/3369391","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T22:50:06Z","timestamp":1583189406000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Sparse BD-Net"],"prefix":"10.1145","volume":"16","author":[{"given":"Zhezhi","family":"He","sequence":"first","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University , Tempe, Arizona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, Arizona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaahin","family":"Angizi","sequence":"additional","affiliation":[{"name":"Department of ECE, University of Central Florida, Orlando, Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adnan Siraj","family":"Rakin","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, Arizona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deliang","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,1,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2011. NCSU EDA FreePDK45. Retrieved from: http:\/\/www.eda.ncsu.edu\/wiki\/FreePDK45:Contents.  2011. NCSU EDA FreePDK45. Retrieved from: http:\/\/www.eda.ncsu.edu\/wiki\/FreePDK45:Contents."},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI\u201916)","author":"Renzo"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240799"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196092"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2017.18"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2018.8297291"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317764"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 5145--5153","author":"Banner Ron","year":"2018"},{"key":"e_1_2_1_9_1","unstructured":"Yoshua Bengio et al. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv:1308.3432 (2013).  Yoshua Bengio et al. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv:1308.3432 (2013)."},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the Design, Automation, and Test in Europe Conference (DATE\u201912)","author":"Ke"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the International Symposium on Computer Architecture (ISCA\u201916)","author":"Ping"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 3123--3131","author":"Matthieu"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Dong et al. 2014. NVSim: A circuit-level performance energy and area model for emerging non-volatile memory. In Emerging Memory Technologies. Springer 15--50.  Xiangyu Dong et al. 2014. NVSim: A circuit-level performance energy and area model for emerging non-volatile memory. In Emerging Memory Technologies. Springer 15--50.","DOI":"10.1007\/978-1-4419-9551-3_2"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.42"},{"key":"e_1_2_1_16_1","volume-title":"Proceedings of the International Conference on Simulation of Semiconductor Processes and Devices (SISPAD\u201911)","author":"Fong Xuanyao"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","author":"Song"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 1135--1143","author":"Han Song","year":"2015"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR\u201916)","author":"Kaiming"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Nanoscale Architectures (NANOARCH\u201917)","author":"Zhezhi"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.78"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2018.00103"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2018.00033"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01170"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00102"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMSCS.2018.2836967"},{"key":"e_1_2_1_28_1","volume-title":"Howard et al","author":"Andrew","year":"2017"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 4107--4115","author":"Itay"},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the International Conference on Machine Learning. 448--456","author":"Ioffe Sergey","year":"2015"},{"key":"e_1_2_1_31_1","unstructured":"Felix Juefei-Xu etal 2016. Local binary convolutional neural networks. arXiv preprint arXiv:1608.06049 (2016).  Felix Juefei-Xu et al. 2016. Local binary convolutional neural networks. arXiv preprint arXiv:1608.06049 (2016)."},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 1097--1105","author":"Krizhevsky Alex"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"e_1_2_1_34_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201917)","author":"Shuangchen"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the Design Automation Conference (DAC\u201916)","author":"Li Shuangchen"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201917)","author":"Liang Shiyu"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 806--814","author":"Liu Baoyuan","year":"2015"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"e_1_2_1_40_1","volume-title":"2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or 1. arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016"},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Mishra Asit","year":"2018"},{"key":"e_1_2_1_42_1","unstructured":"Naveen Muralimanohar et al. 2009. CACTI 6.0: A tool to model large caches. HP Laboratories (2009) 22--31.  Naveen Muralimanohar et al. 2009. CACTI 6.0: A tool to model large caches. HP Laboratories (2009) 22--31."},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of the NIPS Workshop","volume":"2011","author":"Yuval"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4753947"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 344--352","author":"Pan Wei","year":"2017"},{"key":"e_1_2_1_46_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 525--542","author":"Mohammad"},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201917)","author":"Vivek"},{"key":"e_1_2_1_49_1","unstructured":"Synopsys Design Compiler. Product Version 14.9.2014. Synopsys Inc. https:\/\/www.synopsys.com\/implementation-and-signoff\/rtl-synthesis-test\/design-compiler-nxt.html.  Synopsys Design Compiler. Product Version 14.9.2014. Synopsys Inc. https:\/\/www.synopsys.com\/implementation-and-signoff\/rtl-synthesis-test\/design-compiler-nxt.html."},{"key":"e_1_2_1_50_1","volume-title":"Ozlem Aslan, Shengjie Wang, Rich Caruana, Abdelrahman Mohamed, Matthai Philipose, and Matt Richardson.","author":"Urban Gregor","year":"2016"},{"key":"e_1_2_1_51_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems Conference. 2074--2082","author":"Wen Wei","year":"2016"},{"key":"e_1_2_1_52_1","first-page":"1009","article-title":"MNSIM: Simulation platform for memristor-based neuromorphic computing system","volume":"37","author":"Xia Lixue","year":"2017","journal-title":"IEEE Trans. Comput.-Aided Des. Integ. Circ. Syst."},{"key":"e_1_2_1_53_1","unstructured":"Shuchang Zhou et al. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint:1606.06160 (2016).  Shuchang Zhou et al. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint:1606.06160 (2016)."},{"key":"e_1_2_1_54_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201917)","author":"Zoph Barret"},{"key":"e_1_2_1_55_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8697--8710","author":"Zoph Barret"}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369391","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369391","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:30Z","timestamp":1750202610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369391"}},"subtitle":["A Multiplication-less DNN with Sparse Binarized Depth-wise Separable Convolution"],"short-title":[],"issued":{"date-parts":[[2020,1,30]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,4,30]]}},"alternative-id":["10.1145\/3369391"],"URL":"https:\/\/doi.org\/10.1145\/3369391","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"value":"1550-4832","type":"print"},{"value":"1550-4840","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,30]]},"assertion":[{"value":"2019-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-01-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}