{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:43:34Z","timestamp":1757627014397,"version":"3.44.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031998539"},{"type":"electronic","value":"9783031998546"}],"license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-99854-6_8","type":"book-chapter","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:09:10Z","timestamp":1756184950000},"page":"114-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CoSF: A $$\\underline{Co}$$-Optimization Framework for\u00a0Operator $$\\underline{S}$$plitting and\u00a0$$\\underline{F}$$usion"],"prefix":"10.1007","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ao","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingqiu","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haining","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujuan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kan","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"8_CR1","unstructured":"Huawei mindspore. https:\/\/www.mindspore.cn\/ens"},{"issue":"1","key":"8_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3520142","volume":"22","author":"X Cai","year":"2022","unstructured":"Cai, X., Wang, Y.: Optimus: an operator fusion framework for deep neural networks. ACM Trans. Embed. Comput. Syst. 22(1), 1\u201326 (2022)","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"8_CR3","unstructured":"Chen, T., Moreau, T., Jiang, Z., Zheng, L., et\u00a0al.: $$TVM$$: an automated end-to-end optimizing compiler for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2018), pp. 578\u2013594 (2018)"},{"key":"8_CR4","unstructured":"Devlin, J., Chang, M.W., et\u00a0al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"issue":"12","key":"8_CR5","doi-asserted-by":"publisher","first-page":"2734","DOI":"10.14778\/3407790.3407857","volume":"13","author":"J Fang","year":"2020","unstructured":"Fang, J., Shen, Y., Wang, Y.: Optimizing DNN computation graph using graph substitutions. Proc. VLDB Endowment 13(12), 2734\u20132746 (2020)","journal-title":"Proc. VLDB Endowment"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"He, K., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR8","unstructured":"Howard, A.G., Zhu, M., et\u00a0al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"8_CR9","first-page":"27","volume":"1","author":"Z Jia","year":"2019","unstructured":"Jia, Z., Thomas, J., Warszawski, T., Gao, M., Zaharia, M., Aiken, A.: Optimizing DNN computation with relaxed graph substitutions. Proc. Mach. Learn. Syst. 1, 27\u201339 (2019)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"8_CR10","first-page":"186","volume":"5","author":"Y Li","year":"2023","unstructured":"Li, Y., et al.: Sirius: harvesting whole-program optimization opportunities for DNNs. Proc. Mach. Learn. Syst. 5, 186\u2013202 (2023)","journal-title":"Proc. Mach. Learn. Syst."},{"issue":"1","key":"8_CR11","first-page":"105","volume":"1","author":"Y Ma","year":"2019","unstructured":"Ma, Y., Yu, D., et al.: Paddlepaddle: an open-source deep learning platform from industrial practice. Front. Data Domputing 1(1), 105\u2013115 (2019)","journal-title":"Front. Data Domputing"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Markidis, S., et\u00a0al.: Nvidia tensor core programmability, performance & precision. In: 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 522\u2013531. IEEE (2018)","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Meng, L., Li, H., Chen, B.C., et\u00a0al.: AdaViT: adaptive vision transformers for efficient image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12309\u201312318 (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Niu, W., Guan, J., Wang, Y., et\u00a0al.: DNNFusion: accelerating deep neural networks execution with advanced operator fusion. In: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, pp. 883\u2013898 (2021)","DOI":"10.1145\/3453483.3454083"},{"key":"8_CR15","unstructured":"Sabne, A.: Xla : Compiling machine learning for peak performance (2020)"},{"key":"8_CR16","unstructured":"Shi, Y., Yang, Z., Xue, J., et\u00a0al.: Welder: scheduling deep learning memory access via tile-graph. In: 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2023), pp. 701\u2013718 (2023)"},{"key":"8_CR17","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"8_CR18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"4","key":"8_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"8_CR20","first-page":"1","volume":"4","author":"J Zhao","year":"2022","unstructured":"Zhao, J., et al.: Apollo: automatic partition-based operator fusion through layer by layer optimization. Proc. Mach. Learn. Syst. 4, 1\u201319 (2022)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et\u00a0al.: AStitch: enabling a new multi-dimensional optimization space for memory-intensive ml training and inference on modern SIMT architectures. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 359\u2013373 (2022)","DOI":"10.1145\/3503222.3507723"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2025: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99854-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:43:47Z","timestamp":1757465027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99854-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"ISBN":["9783031998539","9783031998546"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99854-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"27 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this artticle","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interest"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dresden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}