{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T14:18:30Z","timestamp":1758637110579,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"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":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624235","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"1576-1587","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["RDARuntime: An OS for AI Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-2684","authenticated-orcid":false,"given":"Benjamin","family":"Glick","sequence":"first","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5699-6117","authenticated-orcid":false,"given":"Arjun","family":"Sabnis","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1555-8387","authenticated-orcid":false,"given":"Renate","family":"Kempf","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7116-1506","authenticated-orcid":false,"given":"Arnav","family":"Goel","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2058-9299","authenticated-orcid":false,"given":"Aarti","family":"Lalwani","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3514-9616","authenticated-orcid":false,"given":"Guoyao","family":"Feng","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8946-0000","authenticated-orcid":false,"given":"Kiran","family":"Ranganath","sequence":"additional","affiliation":[{"name":"SambaNova Systems Inc, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"volume-title":"Retrieved","year":"2023","key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. Accelerated Computing with a Reconfigurable Dataflow Architecture. Retrieved July 29, 2023 from https:\/\/sambanova.ai\/wp-content\/uploads\/2021\/04\/SambaNova_Accelerated-Computing-with-a-Reconfigurable-Dataflow-Architecture_Whitepaper_English.pdf"},{"volume-title":"Retrieved","year":"2023","key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. Data Plane Development Kit. Retrieved July 29, 2023 from https:\/\/github.com\/DPDK\/dpdk"},{"volume-title":"Retrieved","year":"2023","key":"e_1_3_2_2_3_1","unstructured":"[n. d.]. SambaNova DataScale\u00ae SN30. Retrieved September 14, 2023 from https:\/\/sambanova.ai\/wp-content\/uploads\/2022\/09\/SambaNova_DataSheet_DataScale_SN30_09132022_EN-1.pdf"},{"key":"e_1_3_2_2_4_1","volume-title":"JUNE 2023","author":"HIGHLIGHTS","year":"2023","unstructured":"[n. d.]. TOP500 HIGHLIGHTS - JUNE 2023. Retrieved July 29, 2023 from https:\/\/www.top500.org\/lists\/top500\/2023\/06\/highs\/"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0263150"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.10.012"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/EWSDN.2014.33"},{"key":"e_1_3_2_2_8_1","volume-title":"Retrieved","author":"Chatterjee Ranen","year":"2023","unstructured":"Ranen Chatterjee, Ravinder Kumar, Raghunath Shenbagam, Maran Wilson, Conrad\u00a0Alexander Turlik, Arnav Goel, Arjun Sabnis, and Yannan Chen. 2023. Elevated Isolation of Reconfigurable Data Flow Resources in Cloud Computing. Retrieved July 31, 2023 from https:\/\/patentimages.storage.googleapis.com\/c3\/26\/ee\/3a19bad1548112\/US20230205585A1.pdf Patent No. US20230205585A1, Filed December 12, 2022, Issued June 29, 2023."},{"key":"e_1_3_2_2_9_1","volume-title":"Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform. arXiv e-prints","author":"Chen Chi-Chung","year":"2018","unstructured":"Chi-Chung Chen, Chia-Lin Yang, and Hsiang-Yun Cheng. 2018. Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform. arXiv e-prints (2018), arXiv\u20131809."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297156.3297242"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3057203"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00007"},{"key":"e_1_3_2_2_13_1","first-page":"666","article-title":". Runtime Patching of Configuration Files","volume":"16","author":"Grohoski Gregory\u00a0Frederick","year":"2022","unstructured":"Gregory\u00a0Frederick Grohoski, Manish\u00a0K Shah, Raghu Prabhakar, Mark Luttrell, Ravinder Kumar, Kin\u00a0Hing Leung, Ranen Chatterjee, Sumti Jairath, David\u00a0Alan Koeplinger, Ram Sivaramakrishnan, 2022. Runtime Patching of Configuration Files. US Patent App. 16\/996,666.","journal-title":"US Patent App."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of Machine Learning and Systems, A.\u00a0Talwalkar, V.\u00a0Smith, and M.\u00a0Zaharia (Eds.). Vol.\u00a01. 1\u201313","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia, Matei Zaharia, and Alex Aiken. 2019. Beyond Data and Model Parallelism for Deep Neural Networks.. In Proceedings of Machine Learning and Systems, A.\u00a0Talwalkar, V.\u00a0Smith, and M.\u00a0Zaharia (Eds.). Vol.\u00a01. 1\u201313. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2019\/file\/b422680f3db0986ddd7f8f126baaf0fa-Paper.pdf"},{"key":"e_1_3_2_2_15_1","unstructured":"Peishi Jiang Nis Meinert Helga Jord\u00e3o Constantin Weisser Simon Holgate Alexander Lavin Bj\u00f6rn L\u00fctjens Dava Newman Haruko Wainwright Catherine Walker and Patrick Barnard. 2021. Digital Twin Earth \u2013 Coasts: Developing a fast and physics-informed surrogate model for coastal floods via neural operators. arxiv:2110.07100\u00a0[physics.ao-ph]"},{"key":"e_1_3_2_2_16_1","volume-title":"1998 USENIX Annual Technical Conference (USENIX ATC 98)","author":"Kamp Poul-Henning","year":"1998","unstructured":"Poul-Henning Kamp. 1998. Malloc (3) revisited. In 1998 USENIX Annual Technical Conference (USENIX ATC 98)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"David Kirk 2007. NVIDIA CUDA software and GPU parallel computing architecture. In ISMM Vol.\u00a07. 103\u2013104.","DOI":"10.1145\/1296907.1296909"},{"volume-title":"PyTorch Distributed: Experiences on Accelerating Data Parallel Training. Proceedings of the VLDB Endowment 13","author":"Li Shen","key":"e_1_3_2_2_18_1","unstructured":"Shen Li, Yanli Zhao, Rohan Varma, Omkar Salpekar, Pieter Noordhuis, Teng Li, Adam Paszke, Jeff Smith, Brian Vaughan, Pritam Damania, [n. d.]. PyTorch Distributed: Experiences on Accelerating Data Parallel Training. Proceedings of the VLDB Endowment 13, 12 ([n. d.])."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/860375.860383"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37959-8_2"},{"key":"e_1_3_2_2_21_1","volume-title":"Retrieved","author":"Misra Anand","year":"2021","unstructured":"Anand Misra, Arnav Goel, Qi Zheng, Raghunath Shenbagam, and Ravinder Kumar. 2021. Time-Multiplexed use of Reconfigurable Hardware. Retrieved July 31, 2023 from https:\/\/patentimages.storage.googleapis.com\/a0\/ac\/0c\/06792e61002e09\/US20220269534A1.pdf Patent No. US20220269534A1, Filed February 25, 2021, Issued August 25, 2022."},{"key":"e_1_3_2_2_22_1","volume-title":"Retrieved","author":"Misra Anand","year":"2022","unstructured":"Anand Misra, Conrad\u00a0Alexander Turlik, Maran Wilson, Anand Vayyala, Raghu Shenbagam, Ranen Chatterjee, Pushkar\u00a0Shridar Nandkar, and Shivam Raikundalia. 2022. Hot-plug events in a pool of reconfigurable data flow resources. Retrieved July 31, 2023 from https:\/\/patentimages.storage.googleapis.com\/c3\/26\/ee\/3a19bad1548112\/US20230205585A1.pdf Patent No. US11487694B1, Filed December 17, 2021, Issued November 1, 2022."},{"key":"e_1_3_2_2_23_1","volume-title":"SambaNova launches Second-Gen DataScale System. HPCWire","author":"Peckham Oliver","year":"2022","unstructured":"Oliver Peckham. 2022. SambaNova launches Second-Gen DataScale System. HPCWire (2022). https:\/\/www.hpcwire.com\/2022\/09\/14\/sambanova-launches-second-gen-datascale-system\/"},{"key":"e_1_3_2_2_24_1","volume-title":"Retrieved","author":"Raumann Martin\u00a0Russell","year":"2021","unstructured":"Martin\u00a0Russell Raumann, Qi Zheng, Bandish\u00a0B Shah, Ravinder Kumar, Kin\u00a0Hing Leung, Sumti Jairath, and Gregory\u00a0Frederick Grohoski. 2021. Dataflow all-reduce for reconfigurable processor systems. Retrieved July 31, 2023 from https:\/\/patentimages.storage.googleapis.com\/c3\/26\/ee\/3a19bad1548112\/US20230205585A1.pdf Patent No. US11237880B1, Filed July 19, 2021, Issued February 1, 2022."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465281"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/aaec9c"},{"key":"e_1_3_2_2_27_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. [n. d.]. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. ([n. d.])."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155334"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDGC.2012.6449892"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-79774-4_2"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00014"},{"key":"e_1_3_2_2_32_1","volume-title":"Pytorch FSDP: experiences on scaling fully sharded data parallel. arXiv preprint arXiv:2304.11277","author":"Zhao Yanli","year":"2023","unstructured":"Yanli Zhao, Andrew Gu, Rohan Varma, Liang Luo, Chien-Chin Huang, Min Xu, Less Wright, Hamid Shojanazeri, Myle Ott, Sam Shleifer, 2023. Pytorch FSDP: experiences on scaling fully sharded data parallel. arXiv preprint arXiv:2304.11277 (2023)."}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","acronym":"SC-W 2023","location":"Denver CO USA"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624235","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:03:40Z","timestamp":1755745420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":32,"alternative-id":["10.1145\/3624062.3624235","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624235","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}