{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T16:56:31Z","timestamp":1758473791257,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304038","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"835-847","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Split-CNN"],"prefix":"10.1145","author":[{"given":"Tian","family":"Jin","sequence":"first","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"}]},{"given":"Seokin","family":"Hong","sequence":"additional","affiliation":[{"name":"Kyungpook National University & IBM Thomas J. Watson Research Center, Daegu, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"IBM Cloud bandwidth package. https:\/\/www.ibm.com\/cloud\/bandwidth. Accessed: 2019-01--24."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195664"},{"key":"e_1_3_2_1_3_1","volume-title":"Coupling adaptive batch sizes with learning rates. CoRR, abs\/1612.05086","author":"Balles Lukas","year":"2016","unstructured":"Lukas Balles, Javier Romero, and Philipp Hennig. Coupling adaptive batch sizes with learning rates. CoRR, abs\/1612.05086, 2016."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_16"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751226"},{"key":"e_1_3_2_1_6_1","volume-title":"In-place activated batchnorm for memory-optimized training of dnns. CoRR, abs\/1712.02616","author":"Bul\u00f2 Samuel Rota","year":"2017","unstructured":"Samuel Rota Bul\u00f2, Lorenzo Porzi, and Peter Kontschieder. In-place activated batchnorm for memory-optimized training of dnns. CoRR, abs\/1712.02616, 2017."},{"key":"e_1_3_2_1_7_1","volume-title":"Learning both Weights and Connections for Efficient Neural Network. Curran Associates","author":"Cortes C.","year":"2015","unstructured":"C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors. Learning both Weights and Connections for Efficient Neural Network. Curran Associates, Inc., 2015."},{"key":"e_1_3_2_1_8_1","volume-title":"Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1. CoRR, abs\/1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux and Yoshua Bengio. Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1. CoRR, abs\/1602.02830, 2016."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969588"},{"key":"e_1_3_2_1_10_1","volume-title":"A theoretical framework for back-propagation","author":"Cun Yann Le","year":"1988","unstructured":"Yann Le Cun. A theoretical framework for back-propagation, 1988."},{"key":"e_1_3_2_1_11_1","series-title":"Proceedings of Machine Learning Research","first-page":"1504","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"De Soham","year":"2017","unstructured":"Soham De, Abhay Yadav, David Jacobs, and Tom Goldstein. Automated Inference with Adaptive Batches. In Aarti Singh and Jerry Zhu, editors, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, volume 54 of Proceedings of Machine Learning Research, pages 1504--1513, Fort Lauderdale, FL, USA, 20--22 Apr 2017. PMLR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969364"},{"key":"e_1_3_2_1_14_1","volume-title":"Compressing deep convolutional networks using vector quantization. CoRR, abs\/1412.6115","author":"Gong Yunchao","year":"2014","unstructured":"Yunchao Gong, Liu Liu, Ming Yang, and Lubomir D. Bourdev. Compressing deep convolutional networks using vector quantization. CoRR, abs\/1412.6115, 2014."},{"key":"e_1_3_2_1_15_1","volume-title":"Ross B. Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. Accurate, large minibatch SGD: training imagenet in 1 hour. CoRR, abs\/1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1 r, Ross B. Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. Accurate, large minibatch SGD: training imagenet in 1 hour. CoRR, abs\/1706.02677, 2017."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2581122.2544160"},{"key":"e_1_3_2_1_17_1","volume-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs\/1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J. Dally. Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs\/1510.00149, 2015."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/89851.89872"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/645753.668069"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"Piotr Doll\u00e1 r, and Ross B. Girshick. Mask R-CNN. CoRR, abs\/1703.06870","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1 r, and Ross B. Girshick. Mask R-CNN. CoRR, abs\/1703.06870, 2017."},{"key":"e_1_3_2_1_22_1","volume-title":"Deep metric learning using triplet network. CoRR, abs\/1412.6622","author":"Hoffer Elad","year":"2014","unstructured":"Elad Hoffer and Nir Ailon. Deep metric learning using triplet network. CoRR, abs\/1412.6622, 2014."},{"key":"e_1_3_2_1_23_1","volume-title":"Densely connected convolutional networks. CoRR, abs\/1608.06993","author":"Huang Gao","year":"2016","unstructured":"Gao Huang, Zhuang Liu, and Kilian Q. Weinberger. Densely connected convolutional networks. CoRR, abs\/1608.06993, 2016."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2014.6986082"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"e_1_3_2_1_27_1","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. Cifar-10 (canadian institute for advanced research)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_29_1","volume-title":"Fast algorithms for convolutional neural networks. CoRR, abs\/1509.09308","author":"Lavin Andrew","year":"2015","unstructured":"Andrew Lavin. Fast algorithms for convolutional neural networks. CoRR, abs\/1509.09308, 2015."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969830.2969903"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195660"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/65669.104451"},{"key":"e_1_3_2_1_35_1","volume-title":"CoRR","author":"Sermanet Pierre","year":"2013","unstructured":"Pierre Sermanet, David Eigen, Xiang Zhang, Micha\u00eb l Mathieu, Rob Fergus, and Yann LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. CoRR, 2013."},{"key":"e_1_3_2_1_36_1","volume-title":"Very deep convolutional networks for large-scale image recognition. CoRR, abs\/1409.1556","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, abs\/1409.1556, 2014."},{"key":"e_1_3_2_1_37_1","volume-title":"Don't decay the learning rate, increase the batch size. CoRR, abs\/1711.00489","author":"Smith Samuel L.","year":"2017","unstructured":"Samuel L. Smith, Pieter-Jan Kindermans, and Quoc V. Le. Don't decay the learning rate, increase the batch size. CoRR, abs\/1711.00489, 2017."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968934"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_40_1","volume-title":"Improving the speed of neural networks on cpus","author":"Vanhoucke Vincent","year":"2011","unstructured":"Vincent Vanhoucke and Mark Z. Mao. Improving the speed of neural networks on cpus. 2011."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3043055"}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","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"],"location":"Providence RI USA","acronym":"ASPLOS '19"},"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\/3297858.3304038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:14Z","timestamp":1750204394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304038"}},"subtitle":["Splitting Window-based Operations in Convolutional Neural Networks for Memory System Optimization"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":41,"alternative-id":["10.1145\/3297858.3304038","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304038","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"}}]}}