{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:17:19Z","timestamp":1783351039626,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T00:00:00Z","timestamp":1782604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry of Research, Technology and Space (BMFTR)","award":["01LK2313A SMARTWEATHER21-SCC-2"],"award-info":[{"award-number":["01LK2313A SMARTWEATHER21-SCC-2"]}]},{"name":"KIT Center MathSEE","award":["FAST-DREAM Bridge PhD"],"award-info":[{"award-number":["FAST-DREAM Bridge PhD"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3815572.3815765","type":"proceedings-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:44:02Z","timestamp":1782495842000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Combining Domain and Tensor Parallelism to Train Multi-billion-parameter AI Weather Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1197-5493","authenticated-orcid":false,"given":"Deifilia","family":"Kieckhefen","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2233-1041","authenticated-orcid":false,"given":"Markus","family":"G\u00f6tz","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany and Helmholtz AI, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7949-1858","authenticated-orcid":false,"given":"Lars Helge","family":"Heyen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5065-469X","authenticated-orcid":false,"given":"Achim","family":"Streit","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-2022","authenticated-orcid":false,"given":"Charlotte","family":"Debus","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06185-3"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-17-261-2024"},{"key":"e_1_3_2_1_4_1","unstructured":"Cristian Bodnar Wessel P. Bruinsma Ana Lucic Megan Stanley Anna Vaughan Johannes Brandstetter Patrick Garvan Maik Riechert Jonathan A. Weyn Haiyu Dong Jayesh K. Gupta Kit Thambiratnam Alexander T. Archibald Chun-Chieh Wu Elizabeth Heider Max Welling Richard E. Turner and Paris Perdikaris. 2024. A Foundation Model for the Earth System. arXiv:2405.13063 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2405.13063"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML'23)","author":"Bonev Boris","year":"2023","unstructured":"Boris Bonev, Thorsten Kurth, Christian Hundt, Jaideep Pathak, Maximilian Baust, Karthik Kashinath, and Anima Anandkumar. 2023. Spherical Fourier neural operators: learning stable dynamics on the sphere. In Proceedings of the 40th International Conference on Machine Learning (ICML'23). JMLR.org, Honolulu, Hawaii, USA, Article 117, 18 pages. https:\/\/proceedings.mlr.press\/v202\/bonev23a\/bonev23a.pdf"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Lei Chen Xiaohui Zhong Feng Zhang Yuan Cheng Yinghui Xu Yuan Qi and Hao Li. 2023. FuXi: A cascade machine learning forecasting system for 15-day global weather forecast. arXiv:2306.12873 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2306.12873","DOI":"10.1038\/s41612-023-00512-1"},{"key":"e_1_3_2_1_7_1","unstructured":"Si-An Chen Chun-Liang Li Nate Yoder Sercan O. Arik and Tomas Pfister. 2023. TSMixer: An All-MLP Architecture for Time Series Forecasting. arXiv:2303.06053 [cs.LG] https:\/\/arxiv.org\/abs\/2303.06053"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00556-1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080248"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-11-3999-2018"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599533"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/qj.3803"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-16-779-2023"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.2151\/jmsj.2020-005"},{"key":"e_1_3_2_1_16_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","journal-title":"ICLR"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611979022.4"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp-19-3515-2019"},{"key":"e_1_3_2_1_19_1","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. arXiv:2001.08361 [cs.LG] https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_1_20_1","unstructured":"Ryan Keisler. 2022. Forecasting Global Weather with Graph Neural Networks. arXiv:2202.07575 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2202.07575"},{"key":"e_1_3_2_1_21_1","unstructured":"Nitish Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak Peter Tang. 2017. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv:1609.04836 [cs.LG] https:\/\/arxiv.org\/abs\/1609.04836"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432261.3432263"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Deifilia Kieckhefen. 2026. jigsaw_pasc26. doi:10.5281\/zenodo.19109059","DOI":"10.5281\/zenodo.19109059"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592979.3593412"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592979.3593412"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi2336"},{"key":"e_1_3_2_1_28_1","volume-title":"Ana Prieto Nemesio, Peter D. Dueben, Andrew Brown, Florian Pappenberger, and Florence Rabier.","author":"Lang Simon","year":"2024","unstructured":"Simon Lang, Mihai Alexe, Matthew Chantry, Jesper Dramsch, Florian Pinault, Baudouin Raoult, Mariana C. A. Clare, Christian Lessig, Michael Maier-Gerber, Linus Magnusson, Zied Ben Bouall\u00e8gue, Ana Prieto Nemesio, Peter D. Dueben, Andrew Brown, Florian Pappenberger, and Florence Rabier. 2024. AIFS - ECMWF's data-driven forecasting system. arXiv:2406.01465 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2406.01465"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263591"},{"key":"e_1_3_2_1_30_1","unstructured":"Christian Lessig Ilaria Luise Bing Gong Michael Langguth Scarlet Stadtler and Martin Schultz. 2023. AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning. arXiv:2308.13280 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2308.13280"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Tung Nguyen Rohan Shah Hritik Bansal Troy Arcomano Romit Maulik Veerab-hadra Kotamarthi Ian Foster Sandeep Madireddy and Aditya Grover. 2024. Scaling transformer neural networks for skillful and reliable medium-range weather forecasting. arXiv:2312.03876 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2312.03876","DOI":"10.52202\/079017-2196"},{"key":"e_1_3_2_1_33_1","unstructured":"Thomas Nils Nipen H\u00e5vard Homleid Haugen Magnus Sikora Ingstad Even Marius Nordhagen Aram Farhad Shafiq Salihi Paulina Tedesco Ivar Ambj\u00f8rn Seierstad J\u00f8rn Kristiansen Simon Lang Mihai Alexe Jesper Dramsch Baudouin Raoult Gert Mertes and Matthew Chantry. 2024. Regional data-driven weather modeling with a global stretched-grid. arXiv:2409.02891 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2409.02891"},{"key":"e_1_3_2_1_34_1","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00d6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: an imperative style, high-performance deep learning library. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_36_1","volume-title":"Peter Dueben, Carla Bromberg, Jared Sisk, Luke Barrington, Aaron Bell, and Fei Sha.","author":"Rasp Stephan","year":"2024","unstructured":"Stephan Rasp, Stephan Hoyer, Alexander Merose, Ian Langmore, Peter Battaglia, Tyler Russel, Alvaro Sanchez-Gonzalez, Vivian Yang, Rob Carver, Shreya Agrawal, Matthew Chantry, Zied Ben Bouallegue, Peter Dueben, Carla Bromberg, Jared Sisk, Luke Barrington, Aaron Bell, and Fei Sha. 2024. WeatherBench 2: A benchmark for the next generation of data-driven global weather models. arXiv:2308.15560 [physics.ao-ph] https:\/\/arxiv.org\/abs\/2308.15560"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1029\/2020MS002405"},{"key":"e_1_3_2_1_38_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv:1909.08053 [cs.CL] https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS-D-11-00094.1"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-17-8873-2024"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","author":"Tolstikhin Ilya","year":"2021","unstructured":"Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. MLP-mixer: an all-MLP architecture for vision. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 1857, 12 pages. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/cba0a4ee5ccd02fda0fe3f9a3e7b89fe-Paper.pdf"},{"key":"e_1_3_2_1_42_1","volume-title":"van de Geijn and Jerrell Watts","author":"Robert","year":"1995","unstructured":"Robert A. van de Geijn and Jerrell Watts. 1995. SUMMA: Scalable Universal Matrix Multiplication Algorithm. Technical Report. Computer Science Dept. Taylor Hall 2.124 Austin, TX, USA."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00007"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Nils Wedi Peter Bauer Willem Deconinck Michail Diamantakis M. Hamrud Christian Kuehnlein S. Malardel Kristian Mogensen G. Mozdzynski and Piotr Smolarkiewicz. 2015. The modelling infrastructure of the Integrated Forecasting System: Recent advances and future challenges. doi:10.21957\/thtpwp67e","DOI":"10.21957\/thtpwp67e"},{"key":"e_1_3_2_1_46_1","unstructured":"Masafumi Yamazaki Akihiko Kasagi Akihiro Tabuchi Takumi Honda Masahiro Miwa Naoto Fukumoto Tsuguchika Tabaru Atsushi Ike and Kohta Nakashima. 2019. Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds. arXiv:1903.12650 [cs.LG] https:\/\/arxiv.org\/abs\/1903.12650"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"}],"event":{"name":"PASC '26: Platform for Advanced Scientific Computing Conference","location":"Bern Switzerland","acronym":"PASC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3815572.3815765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:49:31Z","timestamp":1783349371000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3815572.3815765"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,28]]},"references-count":47,"alternative-id":["10.1145\/3815572.3815765","10.1145\/3815572"],"URL":"https:\/\/doi.org\/10.1145\/3815572.3815765","relation":{},"subject":[],"published":{"date-parts":[[2026,6,28]]},"assertion":[{"value":"2026-06-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}