{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:47:37Z","timestamp":1783036057982,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3773656.3773659","type":"proceedings-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:22:11Z","timestamp":1767954131000},"page":"19-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1479-4310","authenticated-orcid":false,"given":"Pedro","family":"Valero-Lara","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5448-4667","authenticated-orcid":false,"given":"Aaron","family":"Young","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3546-2382","authenticated-orcid":false,"given":"Thomas","family":"Naughton III","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4365-6416","authenticated-orcid":false,"given":"Christian","family":"Engelmann","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9350-1688","authenticated-orcid":false,"given":"Al","family":"Geist","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6647-2690","authenticated-orcid":false,"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-5178","authenticated-orcid":false,"given":"William F.","family":"Godoy","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. Hugging Face. https:\/\/huggingface.co\/. [Online; accessed 18-March-2025]."},{"key":"e_1_3_3_2_3_2","unstructured":"2025. Ollama. https:\/\/ollama.com\/. [Online; accessed 18-March-2025]."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-70734-4_16"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"M.\u00a0Scot Breitenfeld Houjun Tang Huihuo Zheng Jordan Henderson and Suren Byna. 2025. HDF5 in the exascale era: Delivering efficient and scalable parallel I\/O for exascale applications. Int. J. High Perform. Comput. Appl. 39 1 (2025) 65\u201378. 10.1177\/10943420241288244","DOI":"10.1177\/10943420241288244"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/PDCAT46702.2019.00033"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58144-2_8"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40744-4_2"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTERWORKSHOPS61563.2024.00029"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Matthew\u00a0T. Dearing Yiheng Tao Xingfu Wu Zhiling Lan and Valerie Taylor. 2025. Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes. CoRR abs\/2505.02184 (2025). 10.48550\/ARXIV.2505.02184 arXiv:https:\/\/arXiv.org\/abs\/2505.02184","DOI":"10.48550\/ARXIV.2505.02184"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Jack\u00a0J. Dongarra. 2002. Basic Linear Algebra Subprograms Technical (Blast) Forum Standard (2). Int. J. High Perform. Comput. Appl. 16 2 (2002) 115\u2013199.","DOI":"10.1177\/10943420020160020101"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Jack\u00a0J. Dongarra Victor Eijkhout and Henk\u00a0A. van\u00a0der Vorst. 2001. An iterative solver benchmark. Sci. Program. 9 4 (2001) 223\u2013231. 10.1155\/2001\/527931","DOI":"10.1155\/2001\/527931"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605731.3605886"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"William\u00a0F. Godoy Norbert Podhorszki Ruonan Wang Chuck Atkins Greg Eisenhauer Junmin Gu Philip\u00a0E. Davis Jong Choi Kai Germaschewski Kevin\u00a0A. Huck Axel Huebl Mark Kim James Kress Tahsin\u00a0M. Kur\u00e7 Qing Liu Jeremy Logan Kshitij Mehta George Ostrouchov Manish Parashar Franz Poeschel David Pugmire Eric Suchyta Keichi Takahashi Nick Thompson Seiji Tsutsumi Lipeng Wan Matthew Wolf Kesheng Wu and Scott Klasky. 2020. ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management. SoftwareX 12 (2020) 100561. 10.1016\/J.SOFTX.2020.100561","DOI":"10.1016\/J.SOFTX.2020.100561"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624278"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"William\u00a0F. Godoy Pedro Valero-Lara Keita Teranishi Prasanna Balaprakash and Jeffrey\u00a0S. Vetter. 2024. Large language model evaluation for high-performance computing software development. Concurr. Comput. Pract. Exp. 36 26 (2024). 10.1002\/CPE.8269","DOI":"10.1002\/CPE.8269"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53862-4_6"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Paul\u00a0D. Hovland and Lois\u00a0C. McInnes. 2001. Parallel simulation of compressible flow using automatic differentiation and PETSc. Parallel Comput. 27 4 (2001) 503\u2013519. 10.1016\/S0167-8191(00)00074-0","DOI":"10.1016\/S0167-8191(00)00074-0"},{"key":"e_1_3_3_2_19_2","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Hu Edward\u00a0J.","year":"2022","unstructured":"Edward\u00a0J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363534"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09766-4_95"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Nelson\u00a0F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2024. Lost in the Middle: How Language Models Use Long Contexts. Trans. Assoc. Comput. Linguistics 12 (2024) 157\u2013173. 10.1162\/TACL_A_00638","DOI":"10.1162\/TACL_A_00638"},{"key":"e_1_3_3_2_23_2","volume-title":"29th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2022, Bengaluru, India, December 18-21, 2022","author":"Miniskar Narasinga\u00a0Rao","year":"2022","unstructured":"Narasinga\u00a0Rao Miniskar, Alaul Haque\u00a0Monil Mohammad, alero-Lara Pedro, Frank Liu, and Jeffrey\u00a0S Vetter. 2022. IRIS-BLAS: Towards a Performance Portable and Heterogeneous BLAS Library. In 29th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2022, Bengaluru, India, December 18-21, 2022. IEEE."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624184"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Christian Munley Aaron Jarmusch and Sunita Chandrasekaran. 2024. LLM4VV: Developing LLM-driven testsuite for compiler validation. Future Generation Computer Systems 160 (2024) 1\u201313. 10.1016\/j.future.2024.05.034","DOI":"10.1016\/j.future.2024.05.034"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528929"},{"key":"e_1_3_3_2_27_2","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke Adam","year":"2019","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\u00f6pf, 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_3_2_28_2","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Press Ofir","year":"2022","unstructured":"Ofir Press, Noah\u00a0A. Smith, and Mike Lewis. 2022. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=R8sQPpGCv0"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing\u00a0Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin Artyom Kozhevnikov Ivan Evtimov Joanna Bitton Manish Bhatt Cristian Canton-Ferrer Aaron Grattafiori Wenhan Xiong Alexandre D\u00e9fossez Jade Copet Faisal Azhar Hugo Touvron Louis Martin Nicolas Usunier Thomas Scialom and Gabriel Synnaeve. 2023. Code Llama: Open Foundation Models for Code. CoRR abs\/2308.12950 (2023). 10.48550\/ARXIV.2308.12950 arXiv:https:\/\/arXiv.org\/abs\/2308.12950","DOI":"10.48550\/ARXIV.2308.12950"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624063"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/865018"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Keita Teranishi Harshitha Menon William\u00a0F. Godoy Prasanna Balaprakash David Bau Tal Ben-Nun Abhinav Bhatele Franz Franchetti Michael Franusich Todd Gamblin Giorgis Georgakoudis Tom Goldstein Arjun Guha Steven Hahn Costin Iancu Zheming Jin Terry Jones Tze\u00a0Meng Low Het Mankad Narasinga\u00a0Rao Miniskar Mohammad Alaul\u00a0Haque Monil Daniel Nichols Konstantinos Parasyris Swaroop Pophale Pedro Valero-Lara Jeffrey\u00a0S. Vetter Samuel Williams and Aaron Young. 2025. Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions. arxiv:https:\/\/arXiv.org\/abs\/2505.08135\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2505.08135","DOI":"10.1007\/978-3-032-07612-0_47"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC53243.2021.00050"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMPDP.2019.8671545"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00010"},{"key":"e_1_3_3_2_37_2","unstructured":"Pedro Valero-Lara Alexis Huante Mustafa\u00a0Al Lail William\u00a0F. Godoy Keita Teranishi Prasanna Balaprakash and Jeffrey\u00a0S. Vetter. 2023. Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation. arXiv:https:\/\/arXiv.org\/abs\/2309.07103\u00a0[cs.SE]"},{"key":"e_1_3_3_2_38_2","first-page":"243","volume-title":"Parallel Processing and Applied Mathematics - 12th International Conference, PPAM 2017, Lublin, Poland, September 10-13, 2017, Revised Selected Papers, Part I","author":"Valero-Lara Pedro","year":"2017","unstructured":"Pedro Valero-Lara, Ivan Mart\u00ednez-Perez, Ra\u00fal Sirvent, Xavier Martorell, and Antonio\u00a0J. Pe\u00f1a. 2017. NVIDIA GPUs Scalability to Solve Multiple (Batch) Tridiagonal Systems Implementation of cuThomasBatch. In Parallel Processing and Applied Mathematics - 12th International Conference, PPAM 2017, Lublin, Poland, September 10-13, 2017, Revised Selected Papers, Part I. 243\u2013253."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Pedro Valero-Lara Ivan Mart\u00ednez-P\u00e9rez Ra\u00fal Sirvent Xavier Martorell and Antonio\u00a0J. Pe\u00f1a. 2018. cuThomasBatch and cuThomasVBatch CUDA Routines to compute batch of tridiagonal systems on NVIDIA GPUs. Concurrency and Computation: Practice and Experience 30 24 (2018).","DOI":"10.1002\/cpe.4909"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Valero-Lara Pedro Mart\u00ednez-P\u00e9rez Ivan Sirvent Ra\u00fcl Pe\u00f1a Antonio J. Martorell Xavier and Labarta Jes\u00fas. 2018. Simulating the behavior of the Human Brain on GPUs. Oil Gas Sci. Technol. \u2013 Rev. IFP Energies nouvelles 73 (2018) 63. 10.2516\/ogst\/2018061","DOI":"10.2516\/ogst\/2018061"},{"key":"e_1_3_3_2_41_2","unstructured":"David\u00a0W Walker and Jack\u00a0J Dongarra. 1996. MPI: a standard message passing interface. Supercomputer 12 (1996) 56\u201368."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Anthony Zhou Linnia Hawkins and Pierre Gentine. 2024. Proof-of-concept: Using ChatGPT to Translate and Modernize an Earth System Model from Fortran to Python\/JAX. CoRR abs\/2405.00018 (2024). 10.48550\/ARXIV.2405.00018 arXiv:https:\/\/arXiv.org\/abs\/2405.00018","DOI":"10.48550\/ARXIV.2405.00018"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00027"}],"event":{"name":"SCA\/HPCAsia 2026: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","location":"Osaka Japan","acronym":"SCA\/HPCAsia 2026"},"container-title":["Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:22:16Z","timestamp":1767954136000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773656.3773659"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":42,"alternative-id":["10.1145\/3773656.3773659","10.1145\/3773656"],"URL":"https:\/\/doi.org\/10.1145\/3773656.3773659","relation":{},"subject":[],"published":{"date-parts":[[2026,1,25]]},"assertion":[{"value":"2026-01-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}