{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T02:00:36Z","timestamp":1789178436295,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3613215","type":"proceedings-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T09:47:35Z","timestamp":1700041655000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["FORGE: Pre-Training Open Foundation Models for Science"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-5520","authenticated-orcid":false,"given":"Junqi","family":"Yin","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5308-914X","authenticated-orcid":false,"given":"Sajal","family":"Dash","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0099-1559","authenticated-orcid":false,"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5289-7460","authenticated-orcid":false,"given":"Mallikarjun","family":"Shankar","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SciBERT: Pretrained Contextualized Embeddings for Scientific Text. CoRR abs\/1903.10676","author":"Beltagy Iz","year":"2019","unstructured":"Iz Beltagy , Arman Cohan , and Kyle Lo. 2019. SciBERT: Pretrained Contextualized Embeddings for Scientific Text. CoRR abs\/1903.10676 ( 2019 ). arXiv:1903.10676 http:\/\/arxiv.org\/abs\/1903.10676 Iz Beltagy, Arman Cohan, and Kyle Lo. 2019. SciBERT: Pretrained Contextualized Embeddings for Scientific Text. CoRR abs\/1903.10676 (2019). arXiv:1903.10676 http:\/\/arxiv.org\/abs\/1903.10676"},{"key":"e_1_3_2_1_2_1","volume-title":"Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, and Samuel Weinbach.","author":"Black Sid","year":"2022","unstructured":"Sid Black , Stella Biderman , Eric Hallahan , Quentin Anthony , Leo Gao , Laurence Golding , Horace He , Connor Leahy , Kyle McDonell , Jason Phang , Michael Pieler , USVSN Sai Prashanth , Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, and Samuel Weinbach. 2022 . GPT-NeoX-20B: An Open-Source Autore-gressive Language Model . arXiv:2204.06745 [cs.CL] Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, and Samuel Weinbach. 2022. GPT-NeoX-20B: An Open-Source Autore-gressive Language Model. arXiv:2204.06745 [cs.CL]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221121804"},{"key":"e_1_3_2_1_4_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown , Benjamin Mann , Nick Ryder , Melanie Subbiah , Jared D Kaplan , Prafulla Dhariwal , Arvind Neelakantan , Pranav Shyam , Girish Sastry , Amanda Askell , Sandhini Agarwal , Ariel Herbert-Voss , Gretchen Krueger , Tom Henighan , Rewon Child , Aditya Ramesh , Daniel Ziegler , Jeffrey Wu , Clemens Winter , Chris Hesse , Mark Chen , Eric Sigler , Mateusz Litwin , Scott Gray , Benjamin Chess , Jack Clark , Christopher Berner , Sam McCandlish , Alec Radford , Ilya Sutskever , and Dario Amodei . 2020 . Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H . Lin (Eds.) , Vol. 33 . Curran Associates, Inc., virtual , 1877--1901. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., virtual, 1877--1901. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_5_1","volume-title":"cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/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. CoRR abs\/1410.0759 ( 2014 ). arXiv:1410.0759 http:\/\/arxiv.org\/abs\/1410.0759 Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 (2014). arXiv:1410.0759 http:\/\/arxiv.org\/abs\/1410.0759"},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","unstructured":"Elsevier. 2023. SCOPUS. https:\/\/dev.elsevier.com\/. Accessed: 2023-03-27.  Elsevier. 2023. SCOPUS. https:\/\/dev.elsevier.com\/. Accessed: 2023-03-27."},{"key":"e_1_3_2_1_8_1","volume-title":"Transformers: State-of-the-art Natural Language Processing. Software. https:\/\/huggingface.co\/transformers\/","author":"Face Hugging","year":"2021","unstructured":"Hugging Face . 2021 . Transformers: State-of-the-art Natural Language Processing. Software. https:\/\/huggingface.co\/transformers\/ Hugging Face. 2021. Transformers: State-of-the-art Natural Language Processing. Software. https:\/\/huggingface.co\/transformers\/"},{"key":"e_1_3_2_1_9_1","first-page":"3","volume-title":"NOVEMBER 2022","year":"2023","unstructured":"Green500. 2023 . NOVEMBER 2022 . https:\/\/www.top500.org\/lists\/green500\/2022\/11\/. Accessed : 2023- 3 - 28 . Green500. 2023. NOVEMBER 2022. https:\/\/www.top500.org\/lists\/green500\/2022\/11\/. Accessed: 2023-3-28."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00784-w"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Hoffer Elad","year":"2017","unstructured":"Elad Hoffer , Itay Hubara , and Daniel Soudry . 2017 . Train Longer, Generalize Better: Closing the Generalization Gap in Large Batch Training of Neural Networks . In Proceedings of the 31st International Conference on Neural Information Processing Systems ( Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 1729--1739. Elad Hoffer, Itay Hubara, and Daniel Soudry. 2017. Train Longer, Generalize Better: Closing the Generalization Gap in Large Batch Training of Neural Networks. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 1729--1739."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2203.15556"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.11342"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.12"},{"key":"e_1_3_2_1_15_1","volume-title":"Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang , Youlong Cheng , Ankur Bapna , Orhan Firat , Mia Xu Chen , Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019 . GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Curran Associates Inc., Red Hook, NY, USA. Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_16_1","volume-title":"Scaling Laws for Neural Language Models. CoRR abs\/2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan , Sam McCandlish , Tom Henighan , Tom B. Brown , Benjamin Chess , Rewon Child , Scott Gray , Alec Radford , Jeffrey Wu , and Dario Amodei . 2020. Scaling Laws for Neural Language Models. CoRR abs\/2001.08361 ( 2020 ). arXiv:2001.08361 https:\/\/arxiv.org\/abs\/2001.08361 Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling Laws for Neural Language Models. CoRR abs\/2001.08361 (2020). arXiv:2001.08361 https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_1_17_1","volume-title":"MIOpen: An Open Source Library For Deep Learning Primitives. ArXiv abs\/1910.00078","author":"Khan Jehandad","year":"2019","unstructured":"Jehandad Khan , Paul Fultz , Artem Tamazov , Daniel Lowell , C. Liu , Michael Melesse , Murali Nandhimandalam , Kamil Nasyrov , Ilya Perminov , Tejash Shah , Vasilii Filippov , Jing Zhang , J. Zhou , Bragadeesh Natarajan , and Mayank Daga . 2019. MIOpen: An Open Source Library For Deep Learning Primitives. ArXiv abs\/1910.00078 ( 2019 ). Jehandad Khan, Paul Fultz, Artem Tamazov, Daniel Lowell, C. Liu, Michael Melesse, Murali Nandhimandalam, Kamil Nasyrov, Ilya Perminov, Tejash Shah, Vasilii Filippov, Jing Zhang, J. Zhou, Bragadeesh Natarajan, and Mayank Daga. 2019. MIOpen: An Open Source Library For Deep Learning Primitives. ArXiv abs\/1910.00078 (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1045\/november2012-knoth"},{"key":"e_1_3_2_1_19_1","volume-title":"Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda.","author":"Liang Percy","year":"2022","unstructured":"Percy Liang , Rishi Bommasani , Tony Lee , Dimitris Tsipras , Dilara Soylu , Michihiro Yasunaga , Yian Zhang , Deepak Narayanan , Yuhuai Wu , Ananya Kumar , Benjamin Newman , Binhang Yuan , Bobby Yan , Ce Zhang , Christian Cosgrove , Christopher D. Manning , Christopher R\u00e9 , Diana Acosta-Navas , Drew A. Hudson , Eric Zelikman , Esin Durmus , Faisal Ladhak , Frieda Rong , Hongyu Ren , Huaxiu Yao , Jue Wang , Keshav Santhanam , Laurel Orr , Lucia Zheng , Mert Yuksekgonul , Mirac Suzgun , Nathan Kim , Neel Guha , Niladri Chatterji , Omar Khattab , Peter Henderson , Qian Huang , Ryan Chi , Sang Michael Xie , Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda. 2022 . Holistic Evaluation of Language Models . arXiv:2211.09110 [cs.CL] Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher R\u00e9, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda. 2022. Holistic Evaluation of Language Models. arXiv:2211.09110 [cs.CL]"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2020.110135"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac409"},{"key":"e_1_3_2_1_22_1","unstructured":"Sam McCandlish Jared Kaplan Dario Amodei and OpenAI Dota Team. 2018. An Empirical Model of Large-Batch Training. arXiv:1812.06162 [cs.LG]  Sam McCandlish Jared Kaplan Dario Amodei and OpenAI Dota Team. 2018. An Empirical Model of Large-Batch Training. arXiv:1812.06162 [cs.LG]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_24_1","unstructured":"OLCF. 2023. Frontier. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html. Accessed: 2022-3-28.  OLCF. 2023. Frontier. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html. Accessed: 2022-3-28."},{"key":"e_1_3_2_1_25_1","unstructured":"OLCF. 2023. Summit. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html. Accessed: 2023-3-28.  OLCF. 2023. Summit. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html. Accessed: 2023-3-28."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.13139\/OLCF\/1762742"},{"key":"e_1_3_2_1_27_1","volume-title":"Sinclair","author":"Pati Suchita","year":"2021","unstructured":"Suchita Pati , Shaizeen Aga , Nuwan Jayasena , and Matthew D . Sinclair . 2021 . Demystifying BERT: Implications for Accelerator Design . arXiv:2104.08335 [cs.AR] Suchita Pati, Shaizeen Aga, Nuwan Jayasena, and Matthew D. Sinclair. 2021. Demystifying BERT: Implications for Accelerator Design. arXiv:2104.08335 [cs.AR]"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-020-0308-7"},{"key":"e_1_3_2_1_29_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever etal 2018. Improving language understanding by generative pre-training. (2018).  Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"key":"e_1_3_2_1_33_1","unstructured":"Jianlin Su Yu Lu Shengfeng Pan Ahmed Murtadha Bo Wen and Yunfeng Liu. 2022. RoFormer: Enhanced Transformer with Rotary Position Embedding. arXiv:2104.09864 [cs.CL]  Jianlin Su Yu Lu Shengfeng Pan Ahmed Murtadha Bo Wen and Yunfeng Liu. 2022. RoFormer: Enhanced Transformer with Rotary Position Embedding. arXiv:2104.09864 [cs.CL]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402008"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning. 9266--9276","author":"Tay Yi","year":"2020","unstructured":"Yi Tay , Mostafa Dehghani , Gabriel Goh , Amir Rahimi , and Noam Shazeer . 2020 . Sparse Flash Attention: Squeezing more Information out of Sparse Attention Mechanisms . In Proceedings of the 37th International Conference on Machine Learning. 9266--9276 . https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/6628-Paper.pdf Yi Tay, Mostafa Dehghani, Gabriel Goh, Amir Rahimi, and Noam Shazeer. 2020. Sparse Flash Attention: Squeezing more Information out of Sparse Attention Mechanisms. In Proceedings of the 37th International Conference on Machine Learning. 9266--9276. https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/6628-Paper.pdf"},{"key":"e_1_3_2_1_36_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron , Thibaut Lavril , Gautier Izacard , Xavier Martinet , Marie-Anne Lachaux , Timoth\u00e9e Lacroix , Baptiste Rozi\u00e8re , Naman Goyal , Eric Hambro , Faisal Azhar , Aurelien Rodriguez , Armand Joulin , Edouard Grave , and Guillaume Lample . 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 ( 2023 ). Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_37_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 ). 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)."},{"key":"e_1_3_2_1_38_1","unstructured":"Yang You Igor Gitman and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arXiv:1708.03888 [cs.CV]  Yang You Igor Gitman and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arXiv:1708.03888 [cs.CV]"},{"key":"e_1_3_2_1_39_1","unstructured":"Yang You Jing Li Sashank Reddi Jonathan Hseu Sanjiv Kumar Srinadh Bhojanapalli Xiaodan Song James Demmel Kurt Keutzer and Cho-Jui Hsieh. 2020. Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. arXiv:1904.00962 [cs.LG]  Yang You Jing Li Sashank Reddi Jonathan Hseu Sanjiv Kumar Srinadh Bhojanapalli Xiaodan Song James Demmel Kurt Keutzer and Cho-Jui Hsieh. 2020. Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. arXiv:1904.00962 [cs.LG]"}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3613215","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3613215","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3613215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:36:23Z","timestamp":1750163783000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3613215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":39,"alternative-id":["10.1145\/3581784.3613215","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3613215","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}