{"id":"https://openalex.org/W7160596482","doi":"https://doi.org/10.1109/tpds.2026.3691363","title":"nnScaler-M: Constraint-Guided and Placement-Aware Parallelization Plan Generation for Deep Learning Training","display_name":"nnScaler-M: Constraint-Guided and Placement-Aware Parallelization Plan Generation for Deep Learning Training","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160596482","doi":"https://doi.org/10.1109/tpds.2026.3691363"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2026.3691363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3691363","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","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/A5100370143","display_name":"Jiaan Zhu","orcid":"https://orcid.org/0000-0001-8700-639X"},"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":"Jiaan Zhu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-2985-9361","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473214","display_name":"Qinghe Wang","orcid":"https://orcid.org/0000-0003-2745-8081"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghe Wang","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-2892-4115","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124914884","display_name":"Long Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-9039-8944","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678079","display_name":"Chizheng Fang","orcid":null},"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":"Chizheng Fang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-4936-167X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102982554","display_name":"Zewen Jin","orcid":"https://orcid.org/0000-0002-4762-6559"},"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":"Zewen Jin","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3273-7624","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037054290","display_name":"Youhui Bai","orcid":null},"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":"Youhui Bai","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-6073-7011","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135695615","display_name":"Zhiqi Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqi Lin","raw_affiliation_strings":["ByteDance Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8050-6196","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135651912","display_name":"Cheng Li","orcid":null},"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":"Cheng Li","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7064-6120","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.71529398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"7","first_page":"1691","last_page":"1708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.10869999974966049,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.10869999974966049,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07680000364780426,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.07199999690055847,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/deep-learning","display_name":"Deep learning","score":0.6934999823570251},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5613999962806702},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3131999969482422},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.30809998512268066},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2870999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540999889373779},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6934999823570251},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379999876022339},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2026.3691363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3691363","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3567172094","display_name":null,"funder_award_id":"62572454","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2521757593","https://openalex.org/W2798405286","https://openalex.org/W2883830791","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W2991040477","https://openalex.org/W3012479151","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W3169483174","https://openalex.org/W3177828909","https://openalex.org/W3206832494","https://openalex.org/W4312349930","https://openalex.org/W4385245566","https://openalex.org/W4393406906","https://openalex.org/W4394871790","https://openalex.org/W4394922822","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"As":[0],"deep":[1,48],"neural":[2],"networks":[3],"grow,":[4],"training":[5,197],"increasingly":[6],"relies":[7],"on":[8,117],"handcrafted":[9],"search":[10,64,113,136,148],"spaces":[11,21,65,149],"for":[12,25,42,47,114,170],"efficient":[13,44],"parallelization":[14,45,162,188],"plans.":[15],"However,":[16],"our":[17],"study":[18],"shows":[19],"existing":[20,147],"exclude":[22],"optimal":[23,115],"plans":[24,46,116,163,189],"models":[26,32],"like":[27],"AlphaFold2":[28],"and":[29,73,83,91,98,142,180,200],"large":[30,34],"language":[31],"with":[33,176],"embedding":[35],"tables.":[36],"We":[37],"propose":[38],"nScaler-M,":[39],"a":[40],"framework":[41],"generating":[43],"learning":[49],"training.":[50],"Instead":[51],"of":[52,106],"searching":[53,203],"within":[54],"predefined":[55],"spaces,":[56],"nScaler-M":[57,87,124,144,158,184],"empowers":[58],"domain":[59],"experts":[60],"to":[61,127,130,167,192],"compose":[62,146],"custom":[63],"using":[66],"three":[67],"primitives,":[68,132],"<monospace":[69,74,95,99,177,181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[70,75,96,100,178,182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">op-trans,":[71],"op-assign</monospace>,":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">op-order</monospace>,":[76],"which":[77,102],"capture":[78],"model":[79],"transformation,":[80],"spatial":[81],"assignment,":[82],"temporal":[84],"scheduling.":[85],"Besides,":[86],"captures":[88],"device":[89],"placement":[90],"communication":[92,107],"patterns":[93],"via":[94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">p-mesh</monospace>":[97,179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">c-mesh</monospace>,":[101,183],"enhances":[103],"the":[104,112,135,139],"accuracy":[105],"cost":[108],"estimation,":[109],"ultimately":[110],"supporting":[111],"heterogeneous":[118],"networks.":[119],"To":[120],"avoid":[121],"space":[122],"explosion,":[123],"allows":[125],"constraints":[126],"be":[128],"applied":[129],"these":[131],"effectively":[133],"pruning":[134],"space.":[137],"With":[138],"proposed":[140],"primitives":[141],"constraints,":[143],"can":[145,159,185],"as":[150,152],"well":[151],"new":[153,161],"ones.":[154],"Experiments":[155],"show":[156],"that":[157,164],"find":[160],"achieve":[165],"up":[166,191],"3.5\u00d7":[168],"speedup":[169],"popular":[171],"DNN":[172],"models.":[173],"Additionally,":[174],"equipped":[175],"discover":[186],"optimized":[187],"achieving":[190],"2.79\u00d7":[193],"higher":[194],"throughput":[195],"when":[196],"LLaMA-3":[198],"models,":[199],"introduce":[201],"acceptable":[202],"overhead.":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-09T00:00:00"}