{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:37:50Z","timestamp":1780065470142,"version":"3.54.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06637-1","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:24:03Z","timestamp":1732191843000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["chatHPC:\u00a0Empowering HPC users with large language models"],"prefix":"10.1007","volume":"81","author":[{"given":"Junqi","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesse","family":"Hines","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Herron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tirthankar","family":"Ghosal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suzanne","family":"Prentice","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanessa","family":"Lama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"6637_CR1","unstructured":"Hugging Face Hub. (2024). https:\/\/huggingface.co. Accessed 17 Oct 2024"},{"key":"6637_CR2","doi-asserted-by":"publisher","unstructured":"Bran AM, Cox S, Schilter O, Baldassari C, White AD, Schwaller P (2024) ChemCrow: augmenting large-language models with chemistry tools. Nat March Intell. https:\/\/doi.org\/10.1038\/s42256-024-00832-8","DOI":"10.1038\/s42256-024-00832-8"},{"key":"6637_CR3","doi-asserted-by":"crossref","unstructured":"Jiang Z, Liu J, Chen Z, Li Y, Huang J, Huo Y, He P, Gu J, Lyu MR (2024) LILAC: log parsing using LLMs with adaptive parsing cache. https:\/\/arxiv.org\/abs\/2310.01796","DOI":"10.1145\/3643733"},{"key":"6637_CR4","doi-asserted-by":"publisher","DOI":"10.1615\/jmachlearnmodelcomput.2023048607","author":"J Yin","year":"2023","unstructured":"Yin J, Liu S, Reshniak V, Wang X, Zhang G (2023) A scalable transformer model for real-time decision making in neutron scattering experiments. J Mach Learn Model Comput. https:\/\/doi.org\/10.1615\/jmachlearnmodelcomput.2023048607","journal-title":"J Mach Learn Model Comput"},{"key":"6637_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05479-7","author":"J Yin","year":"2023","unstructured":"Yin J, Dash S, Gounley J, Wang F, Tourassi G (2023) Evaluation of pre-training large language models on leadership-class supercomputers. J Supercomput. https:\/\/doi.org\/10.1007\/s11227-023-05479-7","journal-title":"J Supercomput"},{"key":"6637_CR6","doi-asserted-by":"publisher","unstructured":"Yin J, Dash S, Wang F, Shankar M (2023) Forge: pre-training open foundation models for science. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC \u201923. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3581784.3613215","DOI":"10.1145\/3581784.3613215"},{"key":"6637_CR7","doi-asserted-by":"crossref","unstructured":"Yin J, Bose A, Cong G, Lyngaas I, Anthony Q (2024) Comparative study of large language model architectures on frontier. In: 38th IEEE International parallel and distributed processing symposium. https:\/\/doi.ieeecomputersociety.org\/10.1109\/IPDPS57955.2024.00056","DOI":"10.1109\/IPDPS57955.2024.00056"},{"key":"6637_CR8","unstructured":"Chen M, Tworek J, Jun H, Yuan Q, de Oliveira Pinto HP, Kaplan J, Edwards H, Burda Y, Joseph N, Brockman G, Ray A, Puri R, Krueger G, Petrov M, Khlaaf H, Sastry G, Mishkin P, Chan B, Gray S, Ryder N, Pavlov M, Power A, Kaiser L, Bavarian M, Winter C, Tillet P, Such FP, Cummings D, Plappert M, Chantzis F, Barnes E, Herbert-Voss A, Guss WH, Nichol A, Paino A, Tezak N, Tang J, Babuschkin I, Balaji S, Jain S, Saunders W, Hesse C, Carr AN, Leike J, Achiam J, Misra V, Morikawa E, Radford A, Knight M, Brundage M, Murati M, Mayer K, Welinder P, McGrew B, Amodei D, McCandlish S, Sutskever I, Zaremba W (2021) Evaluating large language models trained on code. https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"6637_CR9","doi-asserted-by":"crossref","unstructured":"Nichols D, Davis JH, Xie Z, Rajaram A, Bhatele A (2024) Can large language models write parallel code? https:\/\/arxiv.org\/abs\/2401.12554","DOI":"10.1145\/3625549.3658689"},{"key":"6637_CR10","unstructured":"Jiang Z, Lin H, Zhong Y, Huang Q, Chen Y, Zhang Z, Peng Y, Li X, Xie C, Nong S, Jia Y, He S, Chen H, Bai Z, Hou Q, Yan S, Zhou D, Sheng Y, Jiang Z, Xu H, Wei H, Zhang Z, Nie P, Zou L, Zhao S, Xiang L, Liu Z, Li Z, Jia X, Ye J, Jin X, Liu X (2024) MegaScale: scaling large language model training to more than 10,000 GPUs. In: Proceedings of the 21st USENIX symposium on networked systems design and implementation. https:\/\/www.usenix.org\/system\/files\/nsdi24-jiang-ziheng.pdf"},{"key":"6637_CR11","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R (2022) Training language models to follow instructions with human, feedback. In: 36th Conference on neural information processing systems. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf"},{"key":"6637_CR12","unstructured":"Wang Z, Bi B, Pentyala SK, Ramnath K, Chaudhuri S, Mehrotra S, Zixu Zhu Mao X-B, Asur S, Na, Cheng (2024) A comprehensive survey of LLM alignment techniques: RLHF, RLAIF, PPO, DPO and more. arXiv:2407.16216"},{"key":"6637_CR13","doi-asserted-by":"crossref","unstructured":"Kwon W, Li Z, Zhuang S, Sheng Y, Zheng L, Yu CH, Gonzalez JE, Zhang H, Stoica I (2023) Efficient memory management for large language model serving with PagedAttention. https:\/\/arxiv.org\/abs\/2309.06180","DOI":"10.1145\/3600006.3613165"},{"key":"6637_CR14","unstructured":"Zheng L, Chiang W-L, Sheng Y, Zhuang S, Wu Z, Zhuang Y, Lin Z, Li Z, Li D, Xing EP, Zhang H, Gonzalez JE, Stoica I (2023) Judging LLM-as-a-judge with MT-bench and chatbot arena. https:\/\/arxiv.org\/abs\/2306.05685"},{"key":"6637_CR15","unstructured":"LangChain. https:\/\/github.com\/langchain-ai\/langchain. Accessed 3 Apr 2024"},{"key":"6637_CR16","doi-asserted-by":"publisher","unstructured":"Godoy W, Valero-Lara P, Teranishi K, Balaprakash P, Vetter J (2023) Evaluation of openai codex for hpc parallel programming models kernel generation. In: Proceedings of the 52nd International Conference on Parallel Processing Workshops. ICPP Workshops \u201923, pp 136\u2013144. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3605731.3605886","DOI":"10.1145\/3605731.3605886"},{"key":"6637_CR17","unstructured":"Valero-Lara P, Huante A, Lail MA, Godoy WF, Teranishi K, Balaprakash P, Vetter JS (2023) Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation. https:\/\/arxiv.org\/abs\/2309.07103"},{"key":"6637_CR18","doi-asserted-by":"publisher","unstructured":"Ding X, Chen L, Emani M, Liao C, Lin P-H, Vanderbruggen T, Xie Z, Cerpa A, Du W (2023) Hpc-gpt: integrating large language model for high-performance computing. In: Proceedings of the SC \u201923 workshops of the international conference on high performance computing, network, storage, and analysis, SC-W \u201923. Association for Computing Machinery, New York, NY, USA, pp 951\u2013960. https:\/\/doi.org\/10.1145\/3624062.3624172","DOI":"10.1145\/3624062.3624172"},{"key":"6637_CR19","unstructured":"Chen L, Ahmed NK, Dutta A, Bhattacharjee A, Yu S, Mahmud QI, Abebe W, Phan H, Sarkar A, Butler B, Hasabnis N, Oren G, Vo VA, Munoz JP, Willke TL, Mattson T, Jannesari A (2024) The landscape and challenges of HPC research and LLMs. https:\/\/arxiv.org\/abs\/2402.02018"},{"key":"6637_CR20","unstructured":"Wang Y, Zhong W, Li L, Mi F, Zeng X, Huang W, Shang L, Jiang X, Liu Q (2023) Aligning Large language models with human: a survey. https:\/\/arxiv.org\/abs\/2307.12966"},{"key":"6637_CR21","unstructured":"Rafailov R, Sharma A, Mitchell E, Ermon S, Manning CD, Finn C (2023) Direct preference optimization: your language model is secretly a reward model. https:\/\/arxiv.org\/abs\/2305.18290"},{"key":"6637_CR22","doi-asserted-by":"crossref","unstructured":"Wang Y, Kordi Y, Mishra S, Liu A, Smith NA, Khashabi D, Hajishirzi H (2023) Self-instruct: aligning language models with self-generated instructions. https:\/\/arxiv.org\/abs\/2212.10560","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"6637_CR23","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) LoRA: low-rank adaptation of large language models. https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"6637_CR24","unstructured":"Chavan A, Liu Z, Gupta D, Xing E, Shen Z (2023) One-for-all: generalized LoRA for parameter-efficient fine-tuning. https:\/\/arxiv.org\/abs\/2306.07967"},{"key":"6637_CR25","doi-asserted-by":"publisher","unstructured":"Rasley J, Rajbhandari S, Ruwase O, He Y (2020) Deepspeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201920. Association for Computing Machinery, New York, NY, USA, pp 3505\u20133506. https:\/\/doi.org\/10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"6637_CR26","unstructured":"Yao Z, Aminabadi RY, Ruwase O, Rajbhandari S, Wu X, Awan AA, Rasley J, Zhang M, Li C, Holmes C, Zhou Z, Wyatt M, Smith M, Kurilenko L, Qin H, Tanaka M, Che S, Song SL, He Y (2023) DeepSpeed-chat: easy, fast and affordable RLHF training of ChatGPT-like models at all scales. https:\/\/arxiv.org\/abs\/2308.01320"},{"key":"6637_CR27","unstructured":"Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, K\u00fcttler H, Lewis M, Yih W-T, Rockt\u00e4schel T, Riedel S, Kiela D (2021) Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in neural information processing systems 33. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/6b493230205f780e1bc26945df7481e5-Paper.pdf"},{"key":"6637_CR28","unstructured":"Wang B, Chen W, Pei H, Xie C, Kang M, Zhang C, Xu C, Xiong Z, Dutta R, Schaeffer R, Truong ST, Arora S, Mazeika M, Hendrycks D, Lin Z, Cheng Y, Koyejo S, Song D, Li B (2024) DecodingTrust: a comprehensive assessment of trustworthiness in GPT models. https:\/\/arxiv.org\/abs\/2306.11698"},{"key":"6637_CR29","unstructured":"Kubeflow. https:\/\/www.kubeflow.org. Accessed 17 Oct 2024"},{"key":"6637_CR30","doi-asserted-by":"crossref","unstructured":"Rajbhandari S, Rasley J, Ruwase O, He Y (2020) Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the international conference for high performance computing, networking, storage and analysis, SC \u201920. IEEE Press, Atlanta, Georgia","DOI":"10.1109\/SC41405.2020.00024"},{"issue":"1","key":"6637_CR31","first-page":"1","volume":"1","author":"G Wang","year":"2023","unstructured":"Wang G, Qin H, Jacobs SA, Holmes C, Rajbhandari S, Ruwase O, Yan F, Yang L, He Y (2023) ZeRO++: extremely efficient collective communication for giant model. Training 1(1):1\u20131","journal-title":"Training"},{"key":"6637_CR32","unstructured":"Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2020) Bertscore: evaluating text generation with bert. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"6637_CR33","unstructured":"Yuan W, Neubig G, Liu P (2021) Bartscore: evaluating generated text as text generation. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW (eds) Advances in neural information processing systems, pp 27263\u201327277. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/e4d2b6e6fdeca3e60e0f1a62fee3d9dd-Paper.pdf"},{"key":"6637_CR34","unstructured":"Liang P, Bommasani R, Lee T, Tsipras D, Soylu D, Yasunaga M, Zhang Y, Narayanan D, Wu Y, Kumar A, Newman B, Yuan B, Yan B, Zhang C, Cosgrove C, Manning CD, R\u00e9 C, Acosta-Navas D, Hudson DA, Zelikman E, Durmus E, Ladhak F, Rong F, Ren H, Yao H, Wang J, Santhanam K, Orr L, Zheng L, Yuksekgonul M, Suzgun M, Kim N, Guha N, Chatterji N, Khattab O, Henderson P, Huang Q, Chi R, Xie SM, Santurkar S, Ganguli S, Hashimoto T, Icard T, Zhang T, Chaudhary V, Wang W, Li X, Mai Y, Zhang Y, Koreeda Y (2022) Holistic evaluation of language models. https:\/\/arxiv.org\/abs\/2211.09110"},{"key":"6637_CR35","doi-asserted-by":"crossref","unstructured":"Manakul P, Liusie A, Gales MJF (2023) SelfCheckGPT: zero-resource black-box hallucination detection for generative large language models. Proceedings of the 2023 conference on empirical methods in natural language processing. https:\/\/aclanthology.org\/2023.emnlp-main.557.pdf","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"6637_CR36","unstructured":"Ganesan K (2018) ROUGE 2.0: updated and improved measures for evaluation of summarization tasks. arXiv. https:\/\/arxiv.org\/abs\/1803.01937"},{"key":"6637_CR37","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota. Association for Computational Linguistics, vol 1, pp 4171\u20134186"},{"key":"6637_CR38","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2019) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp 7871\u20137880","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"6637_CR39","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, Bikel D, Blecher L, Ferrer CC, Chen M, Cucurull G, Esiobu D, Fernandes J, Fu J, Fu W, Fuller B, Gao C, Goswami V, Goyal N, Hartshorn A, Hosseini S, Hou R, Inan H, Kardas M, Kerkez V, Khabsa M, Kloumann I, Korenev A, Koura PS, Lachaux M-A, Lavril T, Lee J, Liskovich D, Lu Y, Mao Y, Martinet X, Mihaylov T, Mishra P, Molybog I, Nie Y, Poulton A, Reizenstein J, Rungta R, Saladi K, Schelten A, Silva R, Smith EM, Subramanian R, Tan XE, Tang B, Taylor R, Williams A, Kuan JX, Xu P, Yan Z, Zarov I, Zhang Y, Fan A, Kambadur M, Narang S, Rodriguez A, Stojnic R, Edunov S, Scialom T (2023) Llama 2: open foundation and fine-tuned chat models. https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"6637_CR40","unstructured":"Prompt Hub. https:\/\/www.prompthub.us\/resources\/llm-latency-benchmark-report. Accessed 25 Mar 2024"},{"key":"6637_CR41","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10256836","author":"L Gao","year":"2023","unstructured":"Gao L, Tow J, Abbasi B, Biderman S, Black S, DiPofi A, Foster C, Golding L, Hsu J, Le Noac\u2019h A, Li H, McDonell K, Muennighoff N, Ociepa C, Phang J, Reynolds L, Schoelkopf H, Skowron A, Sutawika L, Tang E, Thite A, Wang B, Wang K, Zou A (2023) A framework for few-shot language model evaluation. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.10256836 (https:\/\/zenodo.org\/records\/10256836)","journal-title":"Zenodo"},{"key":"6637_CR42","unstructured":"Edge D, Trinh H, Cheng N, Bradley J, Chao A, Mody A, Truitt S, Larson J (2024) From local to global: a graph RAG approach to query-focused summarization. arXiv:2404.16130"},{"key":"6637_CR43","doi-asserted-by":"publisher","unstructured":"Lange J, Papatheodore T, Thomas T, Effler C, Haun A, Cunningham C, Fenske K, Ferreira\u00a0da Silva R, Maheshwari K, Yin J, Dash S, Eisenbach M, Hagerty N, Joo B, Holmen J, Norman M, Dietz D, Beck T, Oral S, Atchley S, Roth P (2023) Evaluating the cloud for capability class leadership, workloads. https:\/\/doi.org\/10.2172\/2000306","DOI":"10.2172\/2000306"},{"key":"6637_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2022.101707","volume":"62","author":"S Partee","year":"2022","unstructured":"Partee S, Ellis M, Rigazzi A, Shao AE, Bachman S, Marques G, Robbins B (2022) Using machine learning at scale in numerical simulations with smartsim: an application to ocean climate modeling. J Comput Sci 62:101707. https:\/\/doi.org\/10.1016\/j.jocs.2022.101707","journal-title":"J Comput Sci"},{"key":"6637_CR45","doi-asserted-by":"publisher","unstructured":"Yin J, Wang F, Shankar MA (2023) Deepthermo: deep learning accelerated parallel Monte Carlo sampling for thermodynamics evaluation of high entropy alloys. In: 2023 IEEE International parallel and distributed processing symposium (IPDPS), pp 333\u2013343. https:\/\/doi.org\/10.1109\/IPDPS54959.2023.00041","DOI":"10.1109\/IPDPS54959.2023.00041"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06637-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06637-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06637-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:05:33Z","timestamp":1732194333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06637-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6637"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06637-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"194"}}