{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:44:13Z","timestamp":1766231053340,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3750720.3757293","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:42:38Z","timestamp":1766230958000},"page":"151-158","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An LLM-enabled Workflow for Understanding and Evolving HPC Scheduling Practices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6045-9239","authenticated-orcid":false,"given":"Anderson","family":"Borch","sequence":"first","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA and Oak Ridge National Laboratory, Oak Ridge, TN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3800-662X","authenticated-orcid":false,"given":"Ketan","family":"Maheshwari","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2441-2048","authenticated-orcid":false,"given":"Justin","family":"Wozniak","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Argonne, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1720-0928","authenticated-orcid":false,"given":"Rafael","family":"Ferreira da Silva","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/XLOOP51963.2020.00006"},{"key":"e_1_3_3_2_3_2","unstructured":"Harvard FASRC. 2020. Slurmmon: Cluster Scheduling Analytics for Slurm. Available at https:\/\/github.com\/fasrc\/slurmmon."},{"key":"e_1_3_3_2_4_2","unstructured":"Dror\u00a0G. Feitelson Larry Rudolph and Uwe Schwiegelshohn. 2014. Job scheduling in multiprogrammed parallel systems. J. Parallel and Distrib. Comput. 74 (2014). Issue 1."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14430233"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Rafael Ferreira\u00a0da Silva Rosa\u00a0M. Badia Deborah Bard Ian\u00a0T. Foster Shantenu Jha and Fr\u00e9d\u00e9ric Suter. 2024. Frontiers in Scientific Workflows: Pervasive Integration with HPC. IEEE Computer 57 8 (2024). 10.1109\/MC.2024.3401542","DOI":"10.1109\/MC.2024.3401542"},{"key":"e_1_3_3_2_7_2","volume-title":"Proceedings of the 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS)","author":"Grondo Tom","year":"2019","unstructured":"Tom Grondo, Swen Boehm, Nate Grimmer, Ian Gyllinsky, and Todd Gamblin. 2019. Flux: Overcoming Scheduling Challenges for Exascale Workflows. In Proceedings of the 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS)."},{"key":"e_1_3_3_2_8_2","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Islam Nazmus\u00a0Sakib","year":"2023","unstructured":"Nazmus\u00a0Sakib Islam and Gokcen Kestor. 2023. Emerging Challenges in HPC Scheduling: A Workload Characterization Study. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)."},{"key":"e_1_3_3_2_9_2","unstructured":"Shantenu Jha Vincent\u00a0R Pascuzzi and Matteo Turilli. 2022. AI-coupled HPC workflows. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.11745 (2022)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Jasper\u00a0Paul J\u00fcrgensen. 2021. Trace reconstruction in system logs for processing with process mining. Procedia Computer Science 180 (2021) 352\u2013357. 10.1016\/j.procs.2021.01.173Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing (ISM 2020).","DOI":"10.1016\/j.procs.2021.01.173"},{"key":"e_1_3_3_2_11_2","unstructured":"Ketan Maheshwari. 2025. Scheduler Analysis via LLM Workflow GitHub Repository and Documentation. https:\/\/github.com\/ketancmaheshwari\/urgent-computing-sched"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.2172\/1984466"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"M.L. Raghavan et\u00a0al. 2014. Aneurysm shape reconstruction from biplane angiograms in the ISUIA collection. Translational stroke research 5 (2014) 252\u2013259.","DOI":"10.1007\/s12975-014-0330-5"},{"key":"e_1_3_3_2_14_2","volume-title":"Proceedings of the Practice and Experience in Advanced Research Computing (PEARC)","author":"Sharma Nika","year":"2021","unstructured":"Nika Sharma, Shane Canon, Shreyas Cholia, Valerie Hendrix, Lavanya Ramakrishnan, and Horst\u00a0D Simon. 2021. Towards Superfacility: A system for orchestrating synchronous compute-data pipelines across distributed facilities. In Proceedings of the Practice and Experience in Advanced Research Computing (PEARC)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAAC49578.2019.00008"},{"key":"e_1_3_3_2_16_2","volume-title":"Proceedings of the International ACM Symposium on High-Performance Parallel and Distributed Computing (HPDC)","author":"Tseng Tin-Yu","year":"2022","unstructured":"Tin-Yu Tseng, Shahar Shudler, and Mattan Erez. 2022. Slurm-Tracer: Characterizing Scheduling Delays and Queue Dynamics in HPC Systems. In Proceedings of the International ACM Symposium on High-Performance Parallel and Distributed Computing (HPDC)."},{"key":"e_1_3_3_2_17_2","unstructured":"Pablo Vazquez Davide Ricci Emilio Luque Rafael Mayo and Jes\u00fas Labarta. 2022. Characterizing workload patterns and resource usage at a large-scale supercomputing center. Concurrency and Computation: Practice and Experience 34 6 (2022)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Justin\u00a0M. Wozniak Timothy\u00a0G. Armstrong Michael Wilde Daniel\u00a0S. Katz Ewing Lusk and Ian\u00a0T. Foster. 2013. Swift\/T: scalable data flow programming for many-task applications. SIGPLAN Not. 48 8 (Feb. 2013) 309\u2013310. 10.1145\/2517327.2442559","DOI":"10.1145\/2517327.2442559"},{"key":"e_1_3_3_2_19_2","unstructured":"Andrew\u00a0J. Younge Shane Canon and Maur\u00edcio Tsugawa. 2021. Running AI and Simulation Workloads Together: The Case for Workflow-Driven Resource Management. Future Generation Computer Systems 122 (2021)."}],"event":{"name":"ICPP Workshops '25: The 54th International Conference on Parallel Processing Workshops","location":"San Diego CA USA","acronym":"ICPP Workshops '25"},"container-title":["Workshop Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750720.3757293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:43:21Z","timestamp":1766231001000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750720.3757293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":18,"alternative-id":["10.1145\/3750720.3757293","10.1145\/3750720"],"URL":"https:\/\/doi.org\/10.1145\/3750720.3757293","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}