{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:11:09Z","timestamp":1781770269852,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T00:00:00Z","timestamp":1604275200000},"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":[[2020,11,2]]},"DOI":"10.1145\/3400302.3415643","type":"proceedings-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T01:20:55Z","timestamp":1608254455000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["FPGA-based low-batch training accelerator for modern CNNs featuring high bandwidth memory"],"prefix":"10.1145","author":[{"given":"Shreyas K.","family":"Venkataramanaiah","sequence":"first","affiliation":[{"name":"Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han-Sok","family":"Suh","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihui","family":"Yin","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eriko","family":"Nurvitadhi","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aravind","family":"Dasu","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Cao","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-sun","family":"Seo","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,12,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_3_1","first-page":"6243","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tateno Keisuke","year":"2017"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"e_1_3_2_1_5_1","first-page":"1","volume-title":"Mingoo Seok. FPGA-based Acceleration of Binary Neural Network Training with Minimized Off-Chip Memory Access. In IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Chundi Pavan Kumar","year":"2019"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_7_1","volume-title":"Learning multiple layers of features from tiny images. Master's thesis","author":"Krizhevsky A","year":"2009"},{"key":"e_1_3_2_1_8_1","volume-title":"Revisiting small batch training for deep neural networks. arXiv preprint arXiv:1804.07612","author":"Masters Dominic","year":"2019"},{"key":"e_1_3_2_1_9_1","first-page":"1945","volume-title":"Advances in neural information processing systems","author":"Ioffe Sergey","year":"2017"},{"key":"e_1_3_2_1_10_1","volume-title":"Xilinx Whitepaper","author":"Wissolik Mike","year":"2017"},{"key":"e_1_3_2_1_11_1","volume-title":"Intel Whitepaper","author":"Deo Manish","year":"2017"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056824"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.22"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_17_1","volume-title":"Accelerating cnn inference on fpgas: A survey. arXiv preprint arXiv:1806.01683","author":"Abdelouahab Kamel","year":"2018"},{"key":"e_1_3_2_1_18_1","volume-title":"A survey of fpga-based neural network accelerator. arXiv preprint arXiv:1712.08934","author":"Guo Kaiyuan","year":"2017"},{"key":"e_1_3_2_1_19_1","volume-title":"A Scalable Framework for Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters with Weight and Workload Balancing. arXiv preprint arXiv:1901.01007","author":"Geng Tong","year":"2019"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2965154"},{"key":"e_1_3_2_1_21_1","first-page":"107","volume-title":"IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP)","author":"Zhao Wenlai","year":"2016"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3218603.3218625"},{"key":"e_1_3_2_1_23_1","first-page":"255","volume-title":"Zeng and Viktor Prasanna. GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms. In ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Hanqing","year":"2020"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2820016"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2010.2085006"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-005-4961-3"},{"issue":"8","key":"e_1_3_2_1_27_1","first-page":"1911","article-title":"Accelerating Stochastic Gradient Descent Based Matrix Factorization on FPGA","volume":"31","author":"Zhou Shijie","year":"1897","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_28_1","first-page":"166","volume-title":"Jaesun Seo. Automatic Compiler Based FPGA Accelerator for CNN Training. In IEEE International Conference on Field Programmable Logic and Applications (FPL)","author":"Venkataramanaiah Shreyas Kolala","year":"2019"},{"key":"e_1_3_2_1_29_1","first-page":"180","volume-title":"Shimpei Sato. FPGA-Based Training Accelerator Utilizing Sparseness of Convolutional Neural Network. In IEEE International Conference on Field Programmable Logic and Applications (FPL)","author":"Nakahara Hiroki","year":"2019"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/1674-4926\/41\/2\/022403"},{"key":"e_1_3_2_1_31_1","volume-title":"High bandwidth memory (HBM) DRAM. JESD235","author":"Standard JEDEC","year":"2013"},{"key":"e_1_3_2_1_32_1","first-page":"4510","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sandler Mark","year":"2018"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2019.2954780"},{"key":"e_1_3_2_1_34_1","unstructured":"Intel. Intel Stratix 10 MX FPGA Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/programmable\/products\/boards_and_kits\/dev-kits\/altera\/kit-s10-mx.html. Accessed: 2020-04-02.  Intel. Intel Stratix 10 MX FPGA Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/programmable\/products\/boards_and_kits\/dev-kits\/altera\/kit-s10-mx.html. Accessed: 2020-04-02."},{"key":"e_1_3_2_1_35_1","unstructured":"Intel. Intel Stratix 10 GX FPGA Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/programmable\/products\/boards_and_kits\/dev-kits\/altera\/kit-s10-fpga.html. Accessed: 2020-04-02.  Intel. Intel Stratix 10 GX FPGA Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/programmable\/products\/boards_and_kits\/dev-kits\/altera\/kit-s10-fpga.html. Accessed: 2020-04-02."},{"key":"e_1_3_2_1_36_1","volume-title":"NIPS 2017 Autodiff Workshop","author":"Paszke Adam","year":"2017"}],"event":{"name":"ICCAD '20: IEEE\/ACM International Conference on Computer-Aided Design","location":"Virtual Event USA","acronym":"ICCAD '20","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE CS"]},"container-title":["Proceedings of the 39th International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3400302.3415643","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3400302.3415643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:41Z","timestamp":1750195901000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3400302.3415643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,2]]},"references-count":36,"alternative-id":["10.1145\/3400302.3415643","10.1145\/3400302"],"URL":"https:\/\/doi.org\/10.1145\/3400302.3415643","relation":{},"subject":[],"published":{"date-parts":[[2020,11,2]]},"assertion":[{"value":"2020-12-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}