{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:17:25Z","timestamp":1768425445144,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,23]],"date-time":"2020-06-23T00:00:00Z","timestamp":1592870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["CCF-1908843"],"award-info":[{"award-number":["CCF-1908843"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,23]]},"DOI":"10.1145\/3369583.3392684","type":"proceedings-article","created":{"date-parts":[[2020,6,22]],"date-time":"2020-06-22T03:27:27Z","timestamp":1592796447000},"page":"185-196","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Efficient GPU Memory Management for Nonlinear DNNs"],"prefix":"10.1145","author":[{"given":"Donglin","family":"Yang","sequence":"first","affiliation":[{"name":"University of North Carolina at Charlotte, Charlotte, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dazhao","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte, Charlotte, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"https:\/\/github.com\/NVIDIA\/cnmem","author":"Nvidia","year":"2018","unstructured":"[n.d.]. Nvidia CNMeM. https:\/\/github.com\/NVIDIA\/cnmem, 2018."},{"key":"e_1_3_2_2_2_1","volume-title":"NVIDIA V100 TENSOR CORE GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/v100\/","year":"2020","unstructured":"[n.d.]. NVIDIA V100 TENSOR CORE GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/v100\/, 2020."},{"key":"e_1_3_2_2_3_1","volume-title":"Comparative study of deep learning software frameworks. arXiv:1511.06435","author":"Bahrampour Soheil","year":"2015","unstructured":"Soheil Bahrampour, Naveen Ramakrishnan, Lukas Schott, and Mohak Shah. 2015. Comparative study of deep learning software frameworks. arXiv:1511.06435 (2015)."},{"key":"e_1_3_2_2_4_1","unstructured":"Soheil Bahrampour Naveen Ramakrishnan Lukas Schott and Mohak Shah. 2016. Comparative study of caffe neon theano and torch for deep learning. (2016)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"e_1_3_2_2_6_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_2_7_1","volume-title":"cudnn: Efficient primitives for deep learning. arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078186"},{"key":"e_1_3_2_2_9_1","unstructured":"Jeffrey Dean Greg Corrado Rajat Monga Kai Chen Matthieu Devin Mark Mao Marc'aurelio Ranzato Andrew Senior Paul Tucker Ke Yang et al. 2012. Large scale distributed deep networks. In Advances in neural information processing systems. 1223--1231."},{"key":"e_1_3_2_2_10_1","volume-title":"Compressing deep convolutional networks using vector quantization. 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:1412.6115 (2014)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375634.1375641"},{"key":"e_1_3_2_2_12_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv:1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv:1706.02677 (2017)."},{"key":"e_1_3_2_2_13_1","volume-title":"Nonlinear neural networks: Principles, mechanisms, and architectures. Neural networks","author":"Grossberg Stephen","year":"1988","unstructured":"Stephen Grossberg. 1988. Nonlinear neural networks: Principles, mechanisms, and architectures. Neural networks, Vol. 1, 1 (1988), 17--61."},{"key":"e_1_3_2_2_14_1","first-page":"243","article-title":"EIE: efficient inference engine on compressed deep neural network","volume":"44","author":"Han Song","year":"2016","unstructured":"Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A Horowitz, and William J Dally. 2016. EIE: efficient inference engine on compressed deep neural network. In Proc. of IEEE ISCA, Vol. 44. 243--254.","journal-title":"Proc. of IEEE ISCA"},{"key":"e_1_3_2_2_15_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. 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:1510.00149 (2015)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Brian Kingsbury et al. 2012. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal processing magazine Vol. 29 6 (2012) 82--97.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_2_18_1","volume-title":"Densenet: Implementing efficient convnet descriptor pyramids. arXiv:1404.1869","author":"Iandola Forrest","year":"2014","unstructured":"Forrest Iandola, Matt Moskewicz, Sergey Karayev, Ross Girshick, Trevor Darrell, and Kurt Keutzer. 2014. Densenet: Implementing efficient convnet descriptor pyramids. arXiv:1404.1869 (2014)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926294"},{"key":"e_1_3_2_2_21_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. Technical Report. Citeseer."},{"key":"e_1_3_2_2_22_1","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."},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. of IEEE ICML.","author":"Le Quoc V","year":"2011","unstructured":"Quoc V Le, Jiquan Ngiam, Adam Coates, Abhik Lahiri, Bobby Prochnow, and Andrew Y Ng. 2011. On optimization methods for deep learning. In Proc. of IEEE ICML."},{"key":"e_1_3_2_2_24_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_2_25_1","unstructured":"Yann LeCun Bernhard E Boser John S Denker Donnie Henderson Richard E Howard Wayne E Hubbard and Lawrence D Jackel. 1990. Handwritten digit recognition with a back-propagation network. In Advances in neural information processing systems. 396--404."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_2_27_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024--8035."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"e_1_3_2_2_29_1","volume-title":"Learning representations by back-propagating errors. nature","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature, Vol. 323, 6088 (1986), 533--536."},{"key":"e_1_3_2_2_30_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_2_31_1","volume-title":"Proc. of IEEE IPDPS. IEEE, 200--209","author":"Shriram SB","year":"2019","unstructured":"SB Shriram, Anshuj Garg, and Purushottam Kulkarni. 2019. Dynamic Memory Management for GPU-Based Training of Deep Neural Networks. In Proc. of IEEE IPDPS. IEEE, 200--209."},{"key":"e_1_3_2_2_32_1","volume-title":"Very deep convolutional networks for large-scale image recognition. 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:1409.1556 (2014)."},{"key":"e_1_3_2_2_33_1","unstructured":"I Sutskever O Vinyals and QV Le. 2014. Sequence to sequence learning with neural networks. (2014) 3104--3112."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_2_36_1","unstructured":"Christian Szegedy Alexander Toshev and Dumitru Erhan. 2013. Deep neural networks for object detection. In Advances in neural information processing systems. 2553--2561."},{"key":"e_1_3_2_2_37_1","unstructured":"Vincent Vanhoucke Andrew Senior and Mark Z Mao. 2011. Improving the speed of neural networks on CPUs. (2011)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303953"}],"event":{"name":"HPDC '20: The 29th International Symposium on High-Performance Parallel and Distributed Computing","location":"Stockholm Sweden","acronym":"HPDC '20","sponsor":["University of Arizona University of Arizona","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369583.3392684","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369583.3392684","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369583.3392684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:58Z","timestamp":1750203898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369583.3392684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,23]]},"references-count":39,"alternative-id":["10.1145\/3369583.3392684","10.1145\/3369583"],"URL":"https:\/\/doi.org\/10.1145\/3369583.3392684","relation":{},"subject":[],"published":{"date-parts":[[2020,6,23]]},"assertion":[{"value":"2020-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}