{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T11:57:06Z","timestamp":1792756626446,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T00:00:00Z","timestamp":1570838400000},"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":[[2019,10,12]]},"DOI":"10.1145\/3352460.3358252","type":"proceedings-article","created":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T11:16:45Z","timestamp":1570792605000},"page":"754-768","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":290,"title":["Understanding Reuse, Performance, and Hardware Cost of DNN Dataflow"],"prefix":"10.1145","author":[{"given":"Hyoukjun","family":"Kwon","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasanth","family":"Chatarasi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Pellauer","sequence":"additional","affiliation":[{"name":"NVIDIA, Westford, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angshuman","family":"Parashar","sequence":"additional","affiliation":[{"name":"NVIDIA, Westford, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2017. NVDLA Deep Learning Accelerator. http:\/\/nvdla.org."},{"key":"e_1_3_2_1_2_1","unstructured":"2019. MAESTRO project page. https:\/\/synergy.ece.gatech.edu\/tools\/maestro\/."},{"key":"e_1_3_2_1_3_1","volume-title":"International Symposium on Computer Architecture (ISCA).","author":"Alight V","year":"2018","unstructured":"V Alight, Air Yazdanbakhsh, Kambiz Samadi, H Esmaeilzadeh, and RK Gupta. 2018. Snapea: Predictive early activation for reducing computation in deep convolutional neural networks. In International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_4_1","volume-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv preprint arXiv:1511.06434","author":"Alec Radford Luke Metz","year":"2015","unstructured":"Luke Metz Alec Radford and Soumith Chintala. 2015. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv preprint arXiv:1511.06434 (2015)."},{"key":"e_1_3_2_1_5_1","unstructured":"Dario Amodei Rishita Anubhai Eric Battenberg Carl Case Jared Casper Bryan Catanzaro Jingdong Chen Mike Chrzanowski Adam Coates Greg Diamos et al. 2015. Deep speech 2: End-to-end speech recognition in english and mandarin. arXiv preprint arXiv:1512.02595 (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"Menglong Zhu and Hartwig Adam","author":"Dmitry Kalenichenko Weijun Wang Bo Chen","year":"2017","unstructured":"Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto Andrew G. Howard, Menglong Zhu 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_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158120"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_10_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 578--594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_2_1_12_1","unstructured":"Yu-Hsin Chen Joel Emer and Vivienne Sze. 2018. Eyeriss v2: A Flexible and High-Performance Accelerator for Emerging Deep Neural Networks. arXiv:cs.DC\/1807.07928"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11179-7_36"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093315.3037702"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"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\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/258915.258946"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011172104768"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305243"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_25_1","volume-title":"FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks. In International Symposium on High Performance Computer Architecture (HPCA).","author":"Lu Wenyan","year":"2017","unstructured":"Wenyan Lu, Guihai Yan, Jiajun Li, Shijun Gong, Yinhe Han, and Xiaowei Li. 2017. FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks. In International Symposium on High Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021736"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00020"},{"key":"e_1_3_2_1_28_1","volume-title":"Andrew Howard and Liang-Chieh Chen","author":"Andrey Zhmoginov Mark Sandler Menglong Zhu","year":"2019","unstructured":"Menglong Zhu Andrey Zhmoginov Mark Sandler, Andrew Howard and Liang-Chieh Chen. 2019. MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv preprint arXiv:1801.04381 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"A tool to model large caches. HP laboratories","author":"Muralimanohar Naveen","year":"2009","unstructured":"Naveen Muralimanohar, Rajeev Balasubramonian, and Norman P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP laboratories (2009), 22--31."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.14"},{"key":"e_1_3_2_1_33_1","volume-title":"Polyhedral Optimization of TensorFlow Computation Graphs. In Workshop on Extreme-scale Programming Tools (ESPT).","author":"Pradelle Beno\u00eet","year":"2017","unstructured":"Beno\u00eet Pradelle, Beno\u00eet Meister, M. Baskaran, Jonathan Springer, and Richard Lethin. 2017. Polyhedral Optimization of TensorFlow Computation Graphs. In Workshop on Extreme-scale Programming Tools (ESPT)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_35_1","volume-title":"Ross Girshick and Kaiming He","author":"Zhuowen Tu Saining Xie Piotr Doll\u00c3\u0105r","year":"2017","unstructured":"Piotr Doll\u00c3\u0105r Zhuowen Tu Saining Xie, Ross Girshick and Kaiming He. 2017. Aggregated Residual Transformations for Deep Neural Networks. arXiv preprint arXiv:1611.05431 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.413.0233"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Vivek Sarkar and Nimrod Megiddo. 2000. An analytical model for loop tiling and its solution. In ISPASS. 146--153. https:\/\/doi.org\/10.1109\/ISPASS.2000.842294","DOI":"10.1109\/ISPASS.2000.842294"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.29"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28652-0_6"},{"key":"e_1_3_2_1_41_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_42_1","volume-title":"Very Deep Convolutional Networks For Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR).","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks For Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2897995"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/113445.113449"},{"key":"e_1_3_2_1_46_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_47_1","volume-title":"Accelergy: An Architecture-Level Energy Estimation Methodology for Accelerator Designs. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD).","author":"Emer Yannan","year":"2019","unstructured":"Wu, Yannan N. and Emer, Joel S. and Sze, Vivienne. 2019. Accelergy: An Architecture-Level Energy Estimation Methodology for Accelerator Designs. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD)."},{"key":"e_1_3_2_1_48_1","volume-title":"Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks","author":"Zhang Chen","year":"2018","unstructured":"Chen Zhang, Guangyu Sun, Zhenman Fang, Peipei Zhou, Peichen Pan, and Jason Cong. 2018. Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2018)."}],"event":{"name":"MICRO '52: The 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Columbus OH USA","acronym":"MICRO '52","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE CS"]},"container-title":["Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358252","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352460.3358252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T22:28:20Z","timestamp":1753828100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358252"}},"subtitle":["A Data-Centric Approach"],"short-title":[],"issued":{"date-parts":[[2019,10,12]]},"references-count":48,"alternative-id":["10.1145\/3352460.3358252","10.1145\/3352460"],"URL":"https:\/\/doi.org\/10.1145\/3352460.3358252","relation":{},"subject":[],"published":{"date-parts":[[2019,10,12]]},"assertion":[{"value":"2019-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}