{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:50:15Z","timestamp":1764175815003,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"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":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697788","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T14:23:57Z","timestamp":1741098237000},"page":"170-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Deploying Diffusion Models with Scheduling Space Search and Memory Overflow Prevention Based on Graph Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8421-1242","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"first","affiliation":[{"name":"Fudan Univ., Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0911-0666","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan Univ., Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8758-7239","authenticated-orcid":false,"given":"Hongji","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan Univ., Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0539-8885","authenticated-orcid":false,"given":"EnHao","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9003-8966","authenticated-orcid":false,"given":"Shun","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7571-1914","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan Univ., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-3252","authenticated-orcid":false,"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong Univ., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-2309","authenticated-orcid":false,"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua Univ., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9099-2781","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan Univ., Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis. CoRR abs\/1809.11096","author":"Brock Andrew","year":"2018","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large Scale GAN Training for High Fidelity Natural Image Synthesis. CoRR abs\/1809.11096 (2018). arXiv:1809.11096 http:\/\/arxiv.org\/abs\/1809.11096"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"e_1_3_2_1_3_1","volume-title":"Squeezing large-scale diffusion models for mobile. arXiv preprint arXiv:2307.01193","author":"Choi Jiwoong","year":"2023","unstructured":"Jiwoong Choi, Minkyu Kim, Daehyun Ahn, Taesu Kim, Yulhwa Kim, Dongwon Jo, Hyesung Jeon, Jae-Joon Kim, and Hyungjun Kim. 2023. Squeezing large-scale diffusion models for mobile. arXiv preprint arXiv:2307.01193 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_5_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 5506--5518","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. 2021. I-bert: Integer-only bert quantization. In International conference on machine learning. PMLR, 5506--5518."},{"key":"e_1_3_2_1_8_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_9_1","volume-title":"Efficient spatially sparse inference for conditional gans and diffusion models. Advances in neural information processing systems 35","author":"Li Muyang","year":"2022","unstructured":"Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, and Jun-Yan Zhu. 2022. Efficient spatially sparse inference for conditional gans and diffusion models. Advances in neural information processing systems 35 (2022), 28858--28873."},{"key":"e_1_3_2_1_10_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1--6.","author":"Li Shun","year":"2024","unstructured":"Shun Li, Ruiqi Chen, Enhao Tang, Yajing Liu, Jing Yang, and Kun Wang. 2024. S-LGCN: Software-Hardware Co-Design for Accelerating LightGCN. In 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1--6."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"e_1_3_2_1_12_1","volume-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds. Advances in Neural Information Processing Systems 36","author":"Li Yanyu","year":"2024","unstructured":"Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, and Jian Ren. 2024. Snapfusion: Text-to-image diffusion model on mobile devices within two seconds. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00018"},{"key":"e_1_3_2_1_14_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_16_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_17_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems 35 (2022), 36479--36494."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_20_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_23_1","unstructured":"Geng Yang Yanyue Xie Zhong Jia Xue Sung-En Chang Yanyu Li Peiyan Dong Jie Lei Weiying Xie Yanzhi Wang Xue Lin et al. [n. d.]. SDA: Low-Bit Stable Diffusion Acceleration on Edge FPGAs. ([n. d.])."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530505"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2939726"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"],"location":"Tokyo Japan","acronym":"ASPDAC '25"},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697788","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:53Z","timestamp":1750295873000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":26,"alternative-id":["10.1145\/3658617.3697788","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697788","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}