{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:28:23Z","timestamp":1781886503889,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3657392","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["WinoGen: A Highly Configurable Winograd Convolution IP Generator for Efficient CNN Acceleration on FPGA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6740-8413","authenticated-orcid":false,"given":"Mingjun","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1580-6714","authenticated-orcid":false,"given":"Pengjia","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4927-0194","authenticated-orcid":false,"given":"Shuo","family":"Yin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-0482","authenticated-orcid":false,"given":"Shixin","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5989-2998","authenticated-orcid":false,"given":"Beichen","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7442-8957","authenticated-orcid":false,"given":"Chong","family":"Tong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8424-7040","authenticated-orcid":false,"given":"Jianlei","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9195-6619","authenticated-orcid":false,"given":"Tinghuan","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4810","authenticated-orcid":false,"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong Special Administrative Region of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"issue":"4","key":"e_1_3_2_1_1_1","first-page":"532","article-title":"A survey on the optimization of neural network accelerators for micro-ai on-device inference","volume":"11","author":"Mazumder A. N.","year":"2021","unstructured":"A. N. Mazumder, J. Meng, H.-A. Rashid, U. Kallakuri, X. Zhang, J.-S. Seo, and T. Mohsenin, \"A survey on the optimization of neural network accelerators for micro-ai on-device inference,\" IEEE JETCAS, vol. 11, no. 4, pp. 532--547, 2021.","journal-title":"IEEE JETCAS"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240801"},{"issue":"8","key":"e_1_3_2_1_4_1","first-page":"2546","article-title":"FCNNLib: A flexible convolution algorithm library for deep learning on fpgas","volume":"41","author":"Liang Y.","year":"2022","unstructured":"Y. Liang, Q. Xiao, L. Lu, and J. Xie, \"FCNNLib: A flexible convolution algorithm library for deep learning on fpgas,\" IEEE TCAD, vol. 41, no. 8, p. 2546--2559, 2022.","journal-title":"IEEE TCAD"},{"issue":"7","key":"e_1_3_2_1_5_1","first-page":"1442","article-title":"Toward an efficient deep pipelined template-based architecture for accelerating the entire 2-D and 3-D CNNs on FPGA","volume":"39","author":"Shen J.","year":"2019","unstructured":"J. Shen, Y. Huang, M. Wen, and C. Zhang, \"Toward an efficient deep pipelined template-based architecture for accelerating the entire 2-D and 3-D CNNs on FPGA,\" IEEE TCAD, vol. 39, no. 7, pp. 1442--1455, 2019.","journal-title":"IEEE TCAD"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP52443.2021.00045"},{"key":"e_1_3_2_1_7_1","volume-title":"WRA: A 2.2-to-6.3 TOPS highly unified dynamically reconfigurable accelerator using a novel winograd decomposition algorithm for convolutional neural networks,\" IEEE TCAS I","author":"Yang C.","unstructured":"C. Yang, Y. Wang, X. Wang, and L. Geng, \"WRA: A 2.2-to-6.3 TOPS highly unified dynamically reconfigurable accelerator using a novel winograd decomposition algorithm for convolutional neural networks,\" IEEE TCAS I, vol. 66, no. 9, pp. 3480--3493, 2019."},{"key":"e_1_3_2_1_8_1","volume-title":"Siam","volume":"33","author":"Winograd S.","year":"1980","unstructured":"S. Winograd, Arithmetic complexity of computations. Siam, 1980, vol. 33."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"e_1_3_2_1_10_1","volume-title":"Liu et al., \"DWM: A decomposable winograd method for convolution acceleration,\" in Proc. AAAI","author":"Huang D.","unstructured":"D. Huang, X. Zhang, R. Zhang, T. Zhi, D. He, J. Guo, C. Liu, Q. Guo, Z. Du, S. Liu et al., \"DWM: A decomposable winograd method for convolution acceleration,\" in Proc. AAAI, vol. 34, no. 04, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218684"},{"key":"e_1_3_2_1_12_1","unstructured":"Xilinx \"Vitis-ai model zoo \" https:\/\/github.com\/Xilinx\/Vitis-AI\/tree\/master\/model_zoo 2023."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657392","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3657392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:01Z","timestamp":1750295881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":12,"alternative-id":["10.1145\/3649329.3657392","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3657392","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}