{"id":"https://openalex.org/W7130551630","doi":"https://doi.org/10.1109/ictc66702.2025.11389089","title":"Hybrid Simulator Infrastructure to Explore Scalable, Large-Scale Distributed Training Architectures","display_name":"Hybrid Simulator Infrastructure to Explore Scalable, Large-Scale Distributed Training Architectures","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130551630","doi":"https://doi.org/10.1109/ictc66702.2025.11389089"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11389089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11389089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146648163","display_name":"Gyeonggeun Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyeonggeun Jung","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075768400","display_name":"Hans Kasan","orcid":"https://orcid.org/0000-0002-8828-8058"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hans Kasan","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010309237","display_name":"J. Dongun Kim","orcid":"https://orcid.org/0000-0003-0462-6521"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"John Kim","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63582123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1983","last_page":"1984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.42480000853538513,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.42480000853538513,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.050700001418590546,"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":0.04659999907016754,"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/network-topology","display_name":"Network topology","score":0.6977999806404114},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.5771999955177307},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.48190000653266907},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/network-simulation","display_name":"Network simulation","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585999965667725},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C139940560","wikidata":"https://www.wikidata.org/wiki/Q290036","display_name":"Network simulation","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C117729477","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Logical topology","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11389089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11389089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6267285346984863,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2118231264","https://openalex.org/W4360831831","https://openalex.org/W4381886086","https://openalex.org/W4381894573","https://openalex.org/W4388031315","https://openalex.org/W4404954309"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"scale":[2],"of":[3,12,87,95,162],"distributed":[4,146],"training":[5,117,147],"highlights":[6],"the":[7,29,48,107,127,151,163],"need":[8],"for":[9,28,116,131],"accurate":[10],"simulation":[11,55],"interconnects":[13],"and":[14,42,64,110,121,141],"collective":[15,112,142],"communication.":[16],"Existing":[17],"simulators":[18],"provide":[19],"useful":[20],"abstractions":[21],"but":[22,101],"often":[23],"rely":[24],"on":[25],"analytical":[26],"models":[27],"interconnection":[30,78],"networks,":[31],"limiting":[32],"their":[33,65],"ability":[34],"to":[35,156],"capture":[36],"cycle-level":[37],"details":[38],"such":[39],"as":[40],"congestion":[41],"contention":[43],"that":[44,57,74,105],"can":[45,153],"occur":[46],"within":[47],"network.":[49],"In":[50,149],"this":[51],"paper,":[52],"we":[53],"discuss":[54,69],"framework":[56,128,152],"are":[58,124],"commonly":[59],"used":[60],"in":[61,144],"prior":[62],"work":[63],"limitations.":[66],"We":[67],"then":[68],"a":[70,76,82],"hybrid":[71],"simulator":[72,80],"infrastructure":[73],"combines":[75],"cycle-accurate":[77],"network":[79],"with":[81],"system":[83],"level":[84],"(MPI-driving)":[85],"runtime":[86],"SST/Macro":[88],"framework.":[89],"This":[90],"integration":[91],"enables":[92],"realistic":[93],"evaluation":[94],"not":[96],"only":[97],"large-scale":[98,145],"physical":[99],"topologies":[100,104],"also":[102],"logical":[103],"describe":[106],"communication":[108,113],"algorithm":[109],"preserve":[111],"semantics":[114],"required":[115],"workloads.":[118],"Although":[119],"compute":[120,160],"memory":[122],"operations":[123],"modeled":[125],"statically,":[126],"is":[129],"specialized":[130],"network-centric":[132],"studies,":[133],"offering":[134],"valuable":[135],"insights":[136],"into":[137],"contention,":[138],"topology":[139],"scaling,":[140],"performance":[143],"systems.":[148],"addition,":[150],"be":[154],"expanded":[155],"include":[157],"more":[158],"detailed":[159],"model":[161],"endpoints.":[164]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-20T00:00:00"}
