{"id":"https://openalex.org/W7116567293","doi":"https://doi.org/10.1145/3750720.3757293","title":"An LLM-enabled Workflow for Understanding and Evolving HPC Scheduling Practices","display_name":"An LLM-enabled Workflow for Understanding and Evolving HPC Scheduling Practices","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116567293","doi":"https://doi.org/10.1145/3750720.3757293"},"language":null,"primary_location":{"id":"doi:10.1145/3750720.3757293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757293","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3750720.3757293","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120297738","display_name":"Anderson Borch","orcid":"https://orcid.org/0009-0009-6045-9239"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anderson Borch","raw_affiliation_strings":["Colorado State University, Fort Collins, CO, USA and Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0009-0009-6045-9239","affiliations":[{"raw_affiliation_string":"Colorado State University, Fort Collins, CO, USA and Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120931117","display_name":"Ketan Maheshwari","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ketan Maheshwari","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0003-3800-662X","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020776475","display_name":"Justin M. Wozniak","orcid":"https://orcid.org/0000-0002-2441-2048"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Wozniak","raw_affiliation_strings":["Argonne National Laboratory, Argonne, USA"],"raw_orcid":"https://orcid.org/0000-0002-2441-2048","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120892132","display_name":"Rafael Ferreira da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira da Silva","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-1720-0928","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120297738"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82897016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.573199987411499,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.573199987411499,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.321399986743927,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.04340000078082085,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7735000252723694},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6732000112533569},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6190000176429749},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.538100004196167},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.49070000648498535},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4745999872684479},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43630000948905945},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009999990463257},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7735000252723694},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6732000112533569},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6190000176429749},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3970000147819519},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3750720.3757293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757293","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3750720.3757293","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757293","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.555048942565918}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1972104482","https://openalex.org/W2999758851","https://openalex.org/W3124379545","https://openalex.org/W3133302186","https://openalex.org/W4239417161","https://openalex.org/W4383100330","https://openalex.org/W4401453588","https://openalex.org/W6968288751"],"related_works":[],"abstract_inverted_index":{"Emerging":[0],"AI-enhanced":[1],"and":[2,44,69,77,89,103,122,130],"near":[3],"real-time":[4],"scientific":[5,142],"workloads":[6],"are":[7],"challenging":[8],"the":[9,83,137],"traditional":[10,95],"assumptions":[11],"of":[12,30,140],"HPC":[13,87,113,123,132],"job":[14,32],"scheduling":[15,74,107],"systems.":[16],"In":[17],"this":[18],"work,":[19],"we":[20],"present":[21],"an":[22],"LLM-enabled,":[23],"portable":[24],"workflow":[25,54],"for":[26],"analyzing":[27],"a":[28,56],"subset":[29],"Slurm":[31],"trace":[33],"data":[34,58],"from":[35],"leadership-class":[36],"supercomputers,":[37],"exemplified":[38],"through":[39],"over":[40],"1.5":[41],"million":[42,46],"jobs":[43],"18":[45],"job-steps":[47],"on":[48],"OLCF\u2019s":[49],"Frontier":[50],"system.":[51],"Our":[52],"hybrid":[53],"integrates":[55],"static":[57],"analysis":[59],"pipeline":[60],"with":[61],"dynamic,":[62],"AI-powered":[63],"components":[64],"to":[65,97,125,135],"generate":[66],"interactive":[67],"dashboards":[68],"automated,":[70],"interpretable":[71],"insights":[72],"into":[73],"behavior,":[75],"efficiency,":[76],"system":[78,114],"usage":[79],"patterns.":[80],"We":[81],"demonstrate":[82],"workflow\u2019s":[84],"portability":[85],"across":[86,112],"systems":[88],"show":[90],"how":[91],"AI-driven":[92],"interpretations":[93],"augment":[94],"visualization":[96],"uncover":[98],"inefficiencies,":[99],"guide":[100],"policy":[101],"evolution,":[102],"support":[104],"more":[105],"responsive":[106],"strategies,":[108],"enabling":[109],"consistent":[110],"analytics":[111],"architectures.":[115],"This":[116],"approach":[117],"enables":[118],"computer":[119],"science":[120],"researchers":[121],"sysadmins":[124],"systematically":[126],"evaluate":[127],"workload":[128],"characteristics":[129],"adapt":[131],"resource":[133],"management":[134],"meet":[136],"evolving":[138],"demands":[139],"modern":[141],"discovery.":[143]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}
