{"id":"https://openalex.org/W4413823921","doi":"https://doi.org/10.1109/icccn65249.2025.11133974","title":"TOPO-X: Co-optimize Flow Scheduling, Topology, and ML Training Parallelism","display_name":"TOPO-X: Co-optimize Flow Scheduling, Topology, and ML Training Parallelism","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4413823921","doi":"https://doi.org/10.1109/icccn65249.2025.11133974"},"language":"en","primary_location":{"id":"doi:10.1109/icccn65249.2025.11133974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn65249.2025.11133974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Computer Communications and Networks (ICCCN)","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/A5024558170","display_name":"Yi Hu","orcid":"https://orcid.org/0000-0001-7115-374X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Xiang Hu","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057313730","display_name":"Han Tian","orcid":"https://orcid.org/0000-0002-3238-8500"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Tian","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059004440","display_name":"Yifang Zhao","orcid":"https://orcid.org/0000-0002-2658-2585"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifang Zhao","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029102289","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0003-3989-0509"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341802","display_name":"Xiang\u2010Yang Li","orcid":"https://orcid.org/0000-0002-6070-6625"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang-Yang Li","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299038171768188},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6706672310829163},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6173549294471741},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5532665252685547},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.43914031982421875},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4133904278278351},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36174142360687256},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3330972194671631},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2523541748523712},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14667406678199768},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13191187381744385},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08406174182891846},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08399662375450134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299038171768188},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6706672310829163},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6173549294471741},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5532665252685547},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.43914031982421875},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4133904278278351},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36174142360687256},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3330972194671631},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2523541748523712},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14667406678199768},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13191187381744385},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08406174182891846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08399662375450134},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn65249.2025.11133974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn65249.2025.11133974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Computer Communications and Networks (ICCCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2119638333","https://openalex.org/W2130531694","https://openalex.org/W2158258775","https://openalex.org/W2164740236","https://openalex.org/W2168595508","https://openalex.org/W2486960733","https://openalex.org/W2798515322","https://openalex.org/W2969388332","https://openalex.org/W2981114289","https://openalex.org/W2991040477","https://openalex.org/W3093671646","https://openalex.org/W3197720002","https://openalex.org/W3205803342","https://openalex.org/W4213060442","https://openalex.org/W4232284301","https://openalex.org/W4380874786","https://openalex.org/W4386412308","https://openalex.org/W4395112660","https://openalex.org/W4401176822"],"related_works":["https://openalex.org/W1595672120","https://openalex.org/W4230999561","https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2014085448","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,142],"large-scale":[4,143],"deep":[5],"neural":[6],"networks":[7],"and":[8,28,35,43,70,92,132],"large":[9],"language":[10],"models":[11],"has":[12],"intensified":[13],"the":[14,107,139],"demand":[15],"for":[16,129],"highly":[17],"efficient":[18],"GPU":[19,134],"clusters.":[20],"However,":[21],"existing":[22],"distributed":[23],"training":[24,68,116,145],"frameworks,":[25],"like":[26],"Fat-tree":[27],"TopoOpt,":[29,110],"struggle":[30],"with":[31],"inefficient":[32],"resource":[33],"utilization":[34],"network":[36,44,62,72,93,97],"bottlenecks.":[37],"They":[38],"often":[39],"optimize":[40],"communication,":[41],"parallelism,":[42,69],"topology":[45],"independently,":[46],"failing":[47],"to":[48,89,137],"leverage":[49],"their":[50],"interdependencies.":[51],"To":[52],"address":[53],"this":[54,76],"gap,":[55],"we":[56],"propose":[57],"TOPO-X,":[58],"a":[59,81,112,126],"novel":[60],"reconfigurable":[61],"framework":[63],"that":[64,104],"co-optimizes":[65],"flow":[66],"scheduling,":[67],"optical":[71,96],"topology.":[73],"By":[74],"formulating":[75],"integrated":[77],"optimization":[78],"challenge":[79],"as":[80,125],"Resource-Constrained":[82],"Project":[83],"Scheduling":[84],"Problem,":[85],"TOPO-X":[86,105,124],"dynamically":[87],"adapts":[88],"changing":[90],"workloads":[91],"conditions":[94],"using":[95],"reconfiguration":[98],"capabilities.":[99],"Our":[100],"experimental":[101],"results":[102],"show":[103],"outperforms":[106],"state-of-the-art":[108],"solution,":[109],"achieving":[111],"2.22\u00d7":[113],"speedup":[114],"in":[115],"iteration":[117],"times":[118],"on":[119],"average.":[120],"These":[121],"findings":[122],"highlight":[123],"promising":[127],"approach":[128],"scalable,":[130],"adaptive,":[131],"high-performance":[133],"clusters":[135],"designed":[136],"meet":[138],"increasing":[140],"demands":[141],"AI":[144],"workloads.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}