{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:32:59Z","timestamp":1763724779407,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":11,"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-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3657326","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":["ScaleFold: Reducing AlphaFold Initial Training Time to 10 Hours"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4813-0685","authenticated-orcid":false,"given":"Feiwen","family":"Zhu","sequence":"first","affiliation":[{"name":"NVIDIA, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3351-9584","authenticated-orcid":false,"given":"Arkadiusz","family":"Nowaczynski","sequence":"additional","affiliation":[{"name":"NVIDIA, Warsaw, Masovian, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6796-210X","authenticated-orcid":false,"given":"Rundong","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2344-4811","authenticated-orcid":false,"given":"Jie","family":"Xin","sequence":"additional","affiliation":[{"name":"NVIDIA, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8191-3297","authenticated-orcid":false,"given":"Yifei","family":"Song","sequence":"additional","affiliation":[{"name":"NVIDIA, Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1316-3293","authenticated-orcid":false,"given":"Michal","family":"Marcinkiewicz","sequence":"additional","affiliation":[{"name":"NVIDIA, Warsaw, Masovian, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6504-0121","authenticated-orcid":false,"given":"Sukru Burc","family":"Eryilmaz","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3059-7027","authenticated-orcid":false,"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA, Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5778-4480","authenticated-orcid":false,"given":"Michael","family":"Andersch","sequence":"additional","affiliation":[{"name":"NVIDIA, Berlin, Berlin, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Gustaf Ahdritz Nazim Bouatta Sachin Kadyan Qinghui Xia William Gerecke Timothy J O'Donnell Daniel Berenberg Ian Fisk Niccol\u00f2 Zanichelli Bo Zhang et al. 2022. OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. bioRxiv (2022) 2022--11.","DOI":"10.1101\/2022.11.20.517210"},{"key":"e_1_3_2_1_2_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_1_3_1","unstructured":"Shenggan Cheng Ruidong Wu Zhongming Yu Binrui Li Xiwen Zhang Jian Peng and Yang You. 2022. FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours. (2022)."},{"key":"e_1_3_2_1_4_1","first-page":"16344","article-title":"2022. Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Richard Evans Michael O'Neill Alexander Pritzel Natasha Antropova Andrew Senior Tim Green Augustin \u017d\u00eddek Russ Bates Sam Blackwell Jason Yim et al. 2021. Protein complex prediction with AlphaFold-Multimer. biorxiv (2021) 2021--10.","DOI":"10.1101\/2021.10.04.463034"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00009"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1923-7"},{"key":"e_1_3_2_1_9_1","unstructured":"Deepspeed team and OpenFold team. 2023. DS4Sci_EvoformerAttention: eliminating memory explosion problems for scaling Evoformer-centric structural biology models. https:\/\/deepspeed4science.ai\/2023\/09\/18\/model-showcase-openfold\/"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_11_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"San Francisco CA USA","acronym":"DAC '24"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657326","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3657326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":11,"alternative-id":["10.1145\/3649329.3657326","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3657326","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"}}]}}