{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:24:46Z","timestamp":1767979486334,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"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":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673093","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"241-251","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["High-Performance 3D convolution on the Latest Generation Sunway Processor"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5424-4069","authenticated-orcid":false,"given":"Jialin","family":"Li","sequence":"first","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2967-3434","authenticated-orcid":false,"given":"Zhichen","family":"Feng","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8689-3750","authenticated-orcid":false,"given":"Yaqian","family":"Gao","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6645-0438","authenticated-orcid":false,"given":"Shaobo","family":"Tian","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9089-1587","authenticated-orcid":false,"given":"Haoyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, Beijing, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2363-2070","authenticated-orcid":false,"given":"Huang","family":"Ye","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1348-8124","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Low-memory gemm-based convolution algorithms for deep neural networks. arXiv preprint arXiv:1709.03395","author":"Anderson Andrew","year":"2017","unstructured":"Andrew Anderson, Aravind Vasudevan, Cormac Keane, and David Gregg. 2017. Low-memory gemm-based convolution algorithms for deep neural networks. arXiv preprint arXiv:1709.03395 (2017)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3202518"},{"key":"e_1_3_2_1_3_1","volume-title":"cudnn: Efficient primitives for deep learning. arXiv preprint 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 preprint arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"e_1_3_2_1_5_1","volume-title":"swdnn: A library for accelerating deep learning applications on sunway taihulight. In 2017 IEEE international parallel and distributed processing symposium (IPDPS)","author":"Fang Jiarui","unstructured":"Jiarui Fang, Haohuan Fu, Wenlai Zhao, Bingwei Chen, Weijie Zheng, and Guangwen Yang. 2017. swdnn: A library for accelerating deep learning applications on sunway taihulight. In 2017 IEEE international parallel and distributed processing symposium (IPDPS). IEEE, 615\u2013624."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-016-5588-7"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3024841"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404407"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_11_1","unstructured":"National Supercomputing\u00a0Center in Wuxi. 2016. xMath User Manual v1.0 (in Chinese). http:\/\/www.nsccwx.cn:1337\/uploads\/595bce0bed1b4537994d927ef6be922d.pdf."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980938"},{"key":"e_1_3_2_1_13_1","volume-title":"3D convolutional neural networks for human action recognition","author":"Ji Shuiwang","year":"2012","unstructured":"Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35, 1 (2012), 221\u2013231."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2022.102954"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.51"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975270"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472496"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00087"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3145163"},{"key":"e_1_3_2_1_21_1","volume-title":"swFLOW: A dataflow deep learning framework on sunway taihulight supercomputer. In 2019 IEEE 21st International Conference on High Performance Computing and Communications","author":"Lin Han","unstructured":"Han Lin, Zeng Lin, Jose\u00a0Monsalve Diaz, Mingfan Li, Hong An, and Guang\u00a0R Gao. 2019. swFLOW: A dataflow deep learning framework on sunway taihulight supercomputer. In 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS). IEEE, 2467\u20132475."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472473"},{"key":"e_1_3_2_1_23_1","volume-title":"Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851","author":"Mathieu Michael","year":"2013","unstructured":"Michael Mathieu, Mikael Henaff, and Yann LeCun. 2013. Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851 (2013)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00068"},{"key":"e_1_3_2_1_25_1","volume-title":"C3D: generic features for video analysis. CoRR, abs\/1412.0767 2, 7","author":"Tran Du","year":"2014","unstructured":"Du Tran, Lubomir\u00a0D Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2014. C3D: generic features for video analysis. CoRR, abs\/1412.0767 2, 7 (2014), 8."},{"key":"e_1_3_2_1_26_1","volume-title":"Fast convolutional nets with fbfft: A GPU performance evaluation. arXiv preprint arXiv:1412.7580","author":"Vasilache Nicolas","year":"2014","unstructured":"Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun. 2014. Fast convolutional nets with fbfft: A GPU performance evaluation. arXiv preprint arXiv:1412.7580 (2014)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40047-6_82"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613209"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2699229"},{"key":"e_1_3_2_1_30_1","volume-title":"MG3MConv: Multi-Grained Matrix-Multiplication-Mapping Convolution Algorithm toward the SW26010 Processor. arXiv preprint arXiv:2307.04941","author":"Zheng Wu.","year":"2023","unstructured":"Zheng Wu. 2023. MG3MConv: Multi-Grained Matrix-Multiplication-Mapping Convolution Algorithm toward the SW26010 Processor. arXiv preprint arXiv:2307.04941 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 5776\u20135785","author":"Zhang Jiyuan","year":"2018","unstructured":"Jiyuan Zhang, Franz Franchetti, and Tze\u00a0Meng Low. 2018. High performance zero-memory overhead direct convolutions. In International Conference on Machine Learning. PMLR, 5776\u20135785."},{"key":"e_1_3_2_1_32_1","volume-title":"IFIP International Conference on Network and Parallel Computing. Springer, 316\u2013321","author":"Zhang Yi","year":"2019","unstructured":"Yi Zhang, Bing Shu, Yan Yin, Yawei Zhou, Shaodi Li, and Junmin Wu. 2019. Efficient processing of convolutional neural networks on sw26010. In IFIP International Conference on Network and Parallel Computing. Springer, 316\u2013321."}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673093","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:30:32Z","timestamp":1758648632000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":32,"alternative-id":["10.1145\/3673038.3673093","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673093","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}