{"id":"https://openalex.org/W4416004484","doi":"https://doi.org/10.1145/3731599.3767587","title":"Integrating and Characterizing HPC Task Runtime Systems for hybrid AI-HPC workloads","display_name":"Integrating and Characterizing HPC Task Runtime Systems for hybrid AI-HPC workloads","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004484","doi":"https://doi.org/10.1145/3731599.3767587"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767587","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":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057270628","display_name":"Andr\u00e9 Merzky","orcid":"https://orcid.org/0000-0002-7228-4327"},"institutions":[{"id":"https://openalex.org/I4210124370","display_name":"Radiant Research (United States)","ror":"https://ror.org/03fz1e596","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124370"]},{"id":"https://openalex.org/I4210135585","display_name":"Radica Systems (China)","ror":"https://ror.org/03qsja474","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210135585"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Andre Merzky","raw_affiliation_strings":["RADICAL-Computing Inc., Wilmington, DE, USA"],"raw_orcid":"https://orcid.org/0000-0002-7228-4327","affiliations":[{"raw_affiliation_string":"RADICAL-Computing Inc., Wilmington, DE, USA","institution_ids":["https://openalex.org/I4210124370","https://openalex.org/I4210135585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964384","display_name":"Mikhail Titov","orcid":"https://orcid.org/0000-0003-2357-7382"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikhail Titov","raw_affiliation_strings":["Brookhaven National Laboratory, Upton, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-2357-7382","affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory, Upton, NY, USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009954932","display_name":"Matteo Turilli","orcid":"https://orcid.org/0000-0003-0527-1435"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Turilli","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA and IE University, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0527-1435","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA and IE University, Madrid, Spain","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038763846","display_name":"Shantenu Jha","orcid":"https://orcid.org/0000-0002-5040-026X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I2799567181","display_name":"Princeton Plasma Physics Laboratory","ror":"https://ror.org/03vn1ts68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I20089843","https://openalex.org/I2799567181","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shantenu Jha","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA; Princeton Plasma Physics Laboratory, Princeton, NJ, USA and Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-5040-026X","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA; Princeton Plasma Physics Laboratory, Princeton, NJ, USA and Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I2799567181"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5331438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2245","last_page":"2256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8500999808311462,"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":0.8500999808311462,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.03720000013709068,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.033799998462200165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7533000111579895},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6432999968528748},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5684999823570251},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.5493999719619751},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.4657000005245209},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44859999418258667},{"id":"https://openalex.org/keywords/runtime-verification","display_name":"Runtime verification","score":0.43479999899864197},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062999844551086},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7533000111579895},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6608999967575073},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C202973057","wikidata":"https://www.wikidata.org/wiki/Q7380130","display_name":"Runtime verification","level":3,"score":0.43479999899864197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C84511453","wikidata":"https://www.wikidata.org/wiki/Q2914952","display_name":"Concurrency control","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767587","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":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767587","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":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1971514365","https://openalex.org/W1983833794","https://openalex.org/W2119023901","https://openalex.org/W2166459269","https://openalex.org/W2172092628","https://openalex.org/W2527672088","https://openalex.org/W2943761765","https://openalex.org/W2946894050","https://openalex.org/W2949221896","https://openalex.org/W2963179050","https://openalex.org/W2963368932","https://openalex.org/W2963919096","https://openalex.org/W2963921579","https://openalex.org/W2974146628","https://openalex.org/W2998852726","https://openalex.org/W3015731845","https://openalex.org/W3100801650","https://openalex.org/W3165027330","https://openalex.org/W3194513155","https://openalex.org/W3196282813","https://openalex.org/W3202628326","https://openalex.org/W4206042161","https://openalex.org/W4388581162","https://openalex.org/W4391141607","https://openalex.org/W4403880903"],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"workflows":[1],"increasingly":[2],"involve":[3],"both":[4],"HPC":[5],"and":[6,13,26,33,47,58,64,86,102,123],"machine-learning":[7],"tasks,":[8],"combining":[9],"MPI-based":[10],"simulations,":[11],"training,":[12],"inference":[14],"in":[15,140],"a":[16,38,143],"single":[17],"execution.":[18,61],"Launchers":[19],"such":[20],"as":[21,142],"Slurm\u2019s":[22],"srun":[23,97],"constrain":[24],"concurrency":[25],"throughput,":[27],"making":[28],"them":[29],"unsuitable":[30],"for":[31,146],"dynamic":[32],"heterogeneous":[34],"workloads.":[35,149],"We":[36],"present":[37],"performance":[39],"study":[40],"of":[41,75],"RADICAL-Pilot":[42],"(RP)":[43],"integrated":[44],"with":[45,91,104,106],"Flux":[46],"Dragon,":[48],"two":[49],"complementary":[50],"runtime":[51,78,138],"systems":[52],"that":[53],"enable":[54],"hierarchical":[55],"resource":[56],"management":[57],"high-throughput":[59],"function":[60],"Using":[62],"synthetic":[63],"production-scale":[65],"workloads":[66],"on":[67,130],"Frontier,":[68],"we":[69],"characterize":[70],"the":[71],"task":[72],"execution":[73],"properties":[74],"RP":[76,141],"across":[77],"configurations.":[79],"RP+Flux":[80,115],"sustains":[81],"up":[82,131],"to":[83,121,132],"930":[84],"tasks/s,":[85],"RP+Flux+Dragon":[87],"exceeds":[88],"1,500":[89],"tasks/s":[90,101],"over":[92],"99.6%":[93],"utilization.":[94],"In":[95],"contrast,":[96],"peaks":[98],"at":[99],"152":[100],"degrades":[103],"scale,":[105],"utilization":[107],"below":[108],"50%.":[109],"For":[110],"IMPECCABLE.v2":[111],"drug":[112],"discovery":[113],"campaign,":[114],"reduces":[116],"makespan":[117],"by":[118],"30\u201360%":[119],"relative":[120],"srun/Slurm":[122],"increases":[124],"throughput":[125],"more":[126],"than":[127],"four":[128],"times":[129],"1,024.":[133],"These":[134],"results":[135],"demonstrate":[136],"hybrid":[137,147],"integration":[139],"scalable":[144],"approach":[145],"AI-HPC":[148]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-11-07T00:00:00"}