{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T15:10:08Z","timestamp":1751037008939,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62234008"],"award-info":[{"award-number":["62234008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735173","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:58:23Z","timestamp":1751032703000},"page":"805-810","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-DOF Fusion: A Flexible Fusion Strategy for Reducing Redundancy in CNN Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3428-9644","authenticated-orcid":false,"given":"Yaqi","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2530-3886","authenticated-orcid":false,"given":"Zikang","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0621-9385","authenticated-orcid":false,"given":"Siyao","family":"Dai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2609-846X","authenticated-orcid":false,"given":"Xuyang","family":"Duan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-0754","authenticated-orcid":false,"given":"Jun","family":"Han","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Rajeev Balasubramonian Andrew\u00a0B Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Xuyi Cai Ying Wang and Lei Zhang. 2022. Optimus: An operator fusion framework for deep neural networks. ACM Transactions on Embedded Computing Systems 22 1 (2022) 1\u201326.","DOI":"10.1145\/3520142"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655922"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_3_3_1_7_2","first-page":"1","volume-title":"Computer vision and pattern recognition","author":"Farhadi Ali","year":"2018","unstructured":"Ali Farhadi and Joseph Redmon. 2018. Yolov3: An incremental improvement. In Computer vision and pattern recognition, Vol.\u00a01804. Springer Berlin\/Heidelberg, Germany, 1\u20136."},{"key":"e_1_3_3_1_8_2","unstructured":"Andrew\u00a0G Howard. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1704.04861 (2017)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580017"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_1_11_2","unstructured":"Sheng-Chun Kao Xiaoyu Huang and Tushar Krishna. 2022. DNNFuser: Generative pre-trained transformer as a generalized mapper for layer fusion in dnn accelerators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2201.11218 (2022)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature 521 7553 (2015) 436\u2013444.","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071098"},{"key":"e_1_3_3_1_15_2","unstructured":"Yury Pisarchyk and Juhyun Lee. 2020. Efficient memory management for deep neural net inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.03288 (2020)."},{"key":"e_1_3_3_1_16_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Emil Talpes Debjit\u00a0Das Sarma Ganesh Venkataramanan Peter Bannon Bill McGee Benjamin Floering Ankit Jalote Christopher Hsiong Sahil Arora Atchyuth Gorti et\u00a0al. 2020. Compute solution for tesla\u2019s full self-driving computer. IEEE Micro 40 2 (2020) 25\u201335.","DOI":"10.1109\/MM.2020.2975764"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Shixuan Zheng Xianjue Zhang Daoli Ou Shibin Tang Leibo Liu Shaojun Wei and Shouyi Yin. 2020. Efficient scheduling of irregular network structures on CNN accelerators. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39 11 (2020) 3408\u20133419.","DOI":"10.1109\/TCAD.2020.3012215"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658698"}],"event":{"name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"New Orleans LA USA","acronym":"GLSVLSI '25"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:38:02Z","timestamp":1751035082000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":19,"alternative-id":["10.1145\/3716368.3735173","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735173","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}