{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:25:27Z","timestamp":1774124727700,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":82,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322258","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"264-278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":42,"title":["TIE"],"prefix":"10.1145","author":[{"given":"Chunhua","family":"Deng","sequence":"first","affiliation":[{"name":"Rutgers University"}]},{"given":"Fangxuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Xuehai","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Jun","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Rutgers University"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00061"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.11"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195664"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045410"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_7_1","volume-title":"Solid-State Circuits Conference-(ISSCC)","author":"Bankman Daniel","year":"2018","unstructured":"Daniel Bankman, Lita Yang, Bert Moons, Marian Verhelst, and Boris Murmann. 2018. An always-on 3.8 μJ\/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28nm CMOS. In Solid-State Circuits Conference-(ISSCC), 2018 IEEE International. IEEE, 222--224."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446049"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ReConFig.2013.6732285"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541967"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"C. Deng and S. L. Bo Yuan. 2019. Reduced-complexity Deep Neural Network-aided Channel Code Decoder: A Case Study for BCH Decoder. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 1468--1472.","DOI":"10.1109\/ICASSP.2019.8682871"},{"key":"e_1_3_2_1_16_1","volume-title":"PermDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices. In 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 189--202","author":"Deng C.","unstructured":"C. Deng, S. Liao, Y. Xie, K. K. Parhi, X. Qian, and B. Yuan. 2018. PermDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices. In 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 189--202."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124552"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_20_1","volume-title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. arXiv preprint arXiv:1805.03718","author":"Eckert Charles","year":"2018","unstructured":"Charles Eckert, Xiaowei Wang, Jingcheng Wang, Arun Subramaniyan, Ravi Iyer, Dennis Sylvester, David Blaauw, and Reetuparna Das. 2018. Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. arXiv preprint arXiv:1805.03718 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00015"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_2_1_23_1","unstructured":"T. Garipov D. Podoprikhin A. Novikov and D. Vetrov. 2016. Ultimate tensorization: compressing convolutional and FC layers alike. arXiv preprint arXiv:1611.03214 (2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115","author":"Gong Yunchao","year":"2014","unstructured":"Yunchao Gong, Liu Liu, Ming Yang, and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_1_27_1","volume-title":"Trained Quantization and Huffman Coding. international conference on learning representations","author":"Han S.","year":"2016","unstructured":"S. Han, H. Mao, and W. J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. international conference on learning representations (2016)."},{"key":"e_1_3_2_1_28_1","unstructured":"Babak Hassibi and David G Stork. 1993. Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems. 164--171."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_30_1","volume-title":"UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition. arXiv preprint arXiv:1804.06508","author":"Hegde Kartik","year":"2018","unstructured":"Kartik Hegde, Jiyong Yu, Rohit Agrawal, Mengjia Yan, Michael Pellauer, and Christopher W Fletcher. 2018. UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition. arXiv preprint arXiv:1804.06508 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123970"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2017.2732698"},{"key":"e_1_3_2_1_33_1","volume-title":"Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093","author":"Jia Yangqing","year":"2014","unstructured":"Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 (2014)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195661"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001178"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_38_1","unstructured":"Ching-En Lee Yakun Sophia Shao Jie-Fang Zhang Angshuman Parashar Joel Emer Stephen W Keckler and Zhengya Zhang. {n. d.}. Stitch-X: An Accelerator Architecture for Exploiting Unstructured Sparsity in Deep Neural Networks. ({n. d.})."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"S. Liao A. Samiee C. Deng Y. Bai and B. Yuan. 2019. Compressing Deep Neural Networks Using Toeplitz Matrix: Algorithm Design and Fpga Implementation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 1443--1447.","DOI":"10.1109\/ICASSP.2019.8683556"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.31"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001179"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"e_1_3_2_1_44_1","volume-title":"Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025","author":"Luong Minh-Thang","year":"2015","unstructured":"Minh-Thang Luong, Hieu Pham, and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"e_1_3_2_1_46_1","unstructured":"J. Max V. Andrea and Z. Andrew. 2014. Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866 (2014)."},{"key":"e_1_3_2_1_47_1","volume-title":"Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision","author":"Mohammad R.","year":"2016","unstructured":"R. Mohammad, O. Vicente, R. Joseph, and F. Ali. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision. Springer, 525--542."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174258"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056823"},{"key":"e_1_3_2_1_50_1","unstructured":"A. Novikov D. Podoprikhin A. Osokin and D. P. Vetrov. 2015. Tensorizing neural networks. In Advances in Neural Information Processing Systems. 442--450."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.453"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_3_2_1_56_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037746"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195660"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00016"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577315"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080221"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00016"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00068"},{"key":"e_1_3_2_1_69_1","volume-title":"In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems. In 2018 IEEE InternatiOnal SympOsium On High PerfOrmance COmputer Architecture (HPCA)","author":"Song Mingcong","unstructured":"Mingcong Song, Kan Zhong, Jiaqi Zhang, Yang Hu, Duo Liu, Weigong Zhang, Jing Wang, and Tao Li. 2018. In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems. In 2018 IEEE InternatiOnal SympOsium On High PerfOrmance COmputer Architecture (HPCA). IEEE, 92--103."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00015"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00037"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"e_1_3_2_1_73_1","volume-title":"A neural conversational model. arXiv preprint arXiv:1506.05869","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals and Quoc Le. 2015. A neural conversational model. arXiv preprint arXiv:1506.05869 (2015)."},{"key":"e_1_3_2_1_74_1","volume-title":"Wide Compression: Tensor Ring Nets. learning 14, 15","author":"Wang Wenqi","year":"2018","unstructured":"Wenqi Wang, Yifan Sun, Brian Eriksson, Wenlin Wang, and Vaneet Aggarwal. 2018. Wide Compression: Tensor Ring Nets. learning 14, 15 (2018), 13--31."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","unstructured":"Y. Wang J. Lin and Z. Wang. 2017. An Energy-Efficient Architecture for Binary Weight Convolutional Neural Networks. IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2017). 10.1109\/TVLSI.2017.2767624","DOI":"10.1109\/TVLSI.2017.2767624"},{"key":"e_1_3_2_1_76_1","volume-title":"2018 52nd Asilomar Conference on Signals, Systems, and Computers. 782--786","author":"Xie Y.","unstructured":"Y. Xie, C. Deng, S. Liao, and B. Yuan. 2018. Area-efficient K-Nearest Neighbor Design using Stochastic Computing. In 2018 52nd Asilomar Conference on Signals, Systems, and Computers. 782--786."},{"key":"e_1_3_2_1_77_1","volume-title":"Tensor-train recurrent neural networks for video classification. arXiv preprint arXiv:1707.01786","author":"Yang Yinchong","year":"2017","unstructured":"Yinchong Yang, Denis Krompass, and Volker Tresp. 2017. Tensor-train recurrent neural networks for video classification. arXiv preprint arXiv:1707.01786 (2017)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"e_1_3_2_1_79_1","volume-title":"Wide residual networks. arXiv preprint arXiv:1605.07146","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195662"},{"key":"e_1_3_2_1_81_1","volume-title":"Tensor ring decomposition. arXiv preprint arXiv:1606.05535","author":"Zhao Qibin","year":"2016","unstructured":"Qibin Zhao, Guoxu Zhou, Shengli Xie, Liqing Zhang, and Andrzej Cichocki. 2016. Tensor ring decomposition. arXiv preprint arXiv:1606.05535 (2016)."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"}],"event":{"name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona","acronym":"ISCA '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322258","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:06Z","timestamp":1750204446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322258"}},"subtitle":["energy-efficient tensor train-based inference engine for deep neural network"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":82,"alternative-id":["10.1145\/3307650.3322258","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322258","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}