{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:10:37Z","timestamp":1787163037258,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"TSMC"},{"name":"Air Force Research Laboratory","award":["FA8750-18-1-0112"],"award-info":[{"award-number":["FA8750-18-1-0112"]}]},{"name":"MediaTek USA"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304028","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T14:38:43Z","timestamp":1554388723000},"page":"821-834","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":125,"title":["Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations"],"prefix":"10.1145","author":[{"given":"H.T.","family":"Kung","sequence":"first","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley","family":"McDanel","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2474396"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541967"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_4_1","volume-title":"Xception: Deep Learning with Depthwise Separable Convolutions. arXiv preprint arXiv:1610.02357","author":"Chollet Francc","year":"2016","unstructured":"Francc ois Chollet. 2016. Xception: Deep Learning with Depthwise Separable Convolutions. arXiv preprint arXiv:1610.02357 (2016)."},{"key":"e_1_3_2_1_5_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or-1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2017.8280150"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124552"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_10_1","volume-title":"Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration. In CVPR Workshops. 344--352","author":"Lin Xing T.","year":"2017","unstructured":"Xing T. Zhao R. Zhang Z. Srivastava M. B. Tu Z. Gupta R. K. ELin, J. H. 2017. Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration. In CVPR Workshops. 344--352."},{"key":"e_1_3_2_1_11_1","volume-title":"GPU Kernels for Block-Sparse Weights. https:\/\/s3-us-west-2.amazonaws.com\/openai-assets\/blocksparse\/blocksparsepaper.pdf. (2017). {Online","author":"Gray Scott","year":"2018","unstructured":"Scott Gray, Alec Radford, and Diederik Kingma. 2017. GPU Kernels for Block-Sparse Weights. https:\/\/s3-us-west-2.amazonaws.com\/openai-assets\/blocksparse\/blocksparsepaper.pdf. (2017). {Online; accessed 12-January-2018}."},{"key":"e_1_3_2_1_12_1","volume-title":"Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1604.03168","author":"Gysel Philipp","year":"2016","unstructured":"Philipp Gysel, Mohammad Motamedi, and Soheil Ghiasi. 2016. Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1604.03168 (2016)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_17_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_18_1","volume-title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions. arXiv preprint arXiv:1711.09224","author":"Huang Gao","year":"2017","unstructured":"Gao Huang, Shichen Liu, Laurens van der Maaten, and Kilian Q Weinberger. 2017. CondenseNet: An Efficient DenseNet using Learned Group Convolutions. arXiv preprint arXiv:1711.09224 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4634199"},{"key":"e_1_3_2_1_21_1","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. 2014. The CIFAR-10 dataset. (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1982.1653825"},{"key":"e_1_3_2_1_24_1","volume-title":"Sparse Matrix Proceedings","author":"Kung H. T.","year":"1978","unstructured":"H. T. Kung and C. E. Leiserson. 1979. Systolic Arrays (for VLSI). In Sparse Matrix Proceedings 1978. Society for Industrial and Applied Mathematics, 256--282."},{"key":"e_1_3_2_1_25_1","unstructured":"Yann LeCun. 1998. The MNIST database of handwritten digits. http:\/\/yann. lecun. com\/exdb\/mnist\/ (1998)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_27_1","volume-title":"Field Programmable Logic and Applications (FPL), 2016 26th International Conference on. IEEE, 1--9.","author":"Li Huimin","year":"2016","unstructured":"Huimin Li, Xitian Fan, Li Jiao, Wei Cao, Xuegong Zhou, and Lingli Wang. 2016. A high performance FPGA-based accelerator for large-scale convolutional neural networks. In Field Programmable Logic and Applications (FPL), 2016 26th International Conference on. IEEE, 1--9."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045690"},{"key":"e_1_3_2_1_29_1","volume-title":"Neural networks with few multiplications. arXiv preprint arXiv:1510.03009","author":"Lin Zhouhan","year":"2015","unstructured":"Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, and Yoshua Bengio. 2015. Neural networks with few multiplications. arXiv preprint arXiv:1510.03009 (2015)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_3_2_1_31_1","first-page":"3","article-title":"SGDR: stochastic gradient descent with restarts","volume":"10","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. SGDR: stochastic gradient descent with restarts. Learning, Vol. 10 (2016), 3.","journal-title":"Learning"},{"key":"e_1_3_2_1_32_1","volume-title":"Thinet: A filter level pruning method for deep neural network compression. arXiv preprint arXiv:1707.06342","author":"Luo Jian-Hao","year":"2017","unstructured":"Jian-Hao Luo, Jianxin Wu, and Weiyao Lin. 2017. Thinet: A filter level pruning method for deep neural network compression. arXiv preprint arXiv:1707.06342 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"ARM at Risk on AI Chip Marketc. EE Times India (April","author":"Merritt Rick","year":"2018","unstructured":"Rick Merritt. 2018. ARM at Risk on AI Chip Marketc. EE Times India (April 2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Diamos","author":"Narang Sharan","year":"2017","unstructured":"Sharan Narang, Eric Undersander, and Gregory F. Diamos. 2017. Block-Sparse Recurrent Neural Networks. CoRR, Vol. abs\/1711.02782 (2017). arxiv: 1711.02782 http:\/\/arxiv.org\/abs\/1711.02782"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123979"},{"key":"e_1_3_2_1_36_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195660"},{"key":"e_1_3_2_1_40_1","volume-title":"An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747","author":"Ruder Sebastian","year":"2016","unstructured":"Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2009.25"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080221"},{"key":"e_1_3_2_1_43_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_45_1","volume-title":"Cassidy Rathinakumar Appuswamy Alexander Andreopoulos David J","author":"Arthur John V.","unstructured":"John V. Arthur Andrew S. Cassidy Rathinakumar Appuswamy Alexander Andreopoulos David J. Berg Jeffrey L. McKinstry Timothy Melano Davis R. Barch Carmelo di Nolfo Pallab Datta Arnon Amir Brian Taba Myron D. Flickner Steven K. Esser, Paul A. Merolla and Dharmendra S. Modha. 2016. Convolutional networks for fast, energy-efficient neuromorphic computing. National Academy of Sciences (2016)."},{"key":"e_1_3_2_1_46_1","volume-title":"Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA. arXiv preprint arXiv:1808.04311","author":"Wang Junsong","year":"2018","unstructured":"Junsong Wang, Qiuwen Lou, Xiaofan Zhang, Chao Zhu, Yonghua Lin, and Deming Chen. 2018. Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA. arXiv preprint arXiv:1808.04311 (2018)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130625"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Wei Wen Chunpeng Wu Yandan Wang Yiran Chen and Hai Li. 2016. Learning structured sparsity in deep neural networks. In Advances in Neural Information Processing Systems. 2074--2082.","DOI":"10.5555\/3157096.3157329"},{"key":"e_1_3_2_1_49_1","volume-title":"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions. arXiv preprint arXiv:1711.08141","author":"Wu Bichen","year":"2017","unstructured":"Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, and Kurt Keutzer. 2017. Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions. arXiv preprint arXiv:1711.08141 (2017)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062244"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195662"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240801"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"e_1_3_2_1_54_1","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017)."}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","location":"Providence RI USA","acronym":"ASPLOS '19","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304028","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304028","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:53:14Z","timestamp":1750189994000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304028"}},"subtitle":["Column Combining Under Joint Optimization"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":54,"alternative-id":["10.1145\/3297858.3304028","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304028","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}