{"id":"https://openalex.org/W2785452945","doi":"https://doi.org/10.1145/3210377.3210394","title":"Integrated Model, Batch, and Domain Parallelism in Training Neural Networks","display_name":"Integrated Model, Batch, and Domain Parallelism in Training Neural Networks","publication_year":2018,"publication_date":"2018-07-11","ids":{"openalex":"https://openalex.org/W2785452945","doi":"https://doi.org/10.1145/3210377.3210394","mag":"2785452945"},"language":"en","primary_location":{"id":"doi:10.1145/3210377.3210394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3210377.3210394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-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/A5103894843","display_name":"Amir Gholami","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Gholami","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013984574","display_name":"Ariful Azad","orcid":"https://orcid.org/0000-0003-1332-8630"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariful Azad","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068071077","display_name":"Peter Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Jin","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035719914","display_name":"Ayd\u0131n Bulu\u00e7","orcid":"https://orcid.org/0000-0001-7253-9038"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aydin Buluc","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103894843"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":10.9994,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.9856507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T12676","display_name":"Machine Learning and ELM","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7833153605461121},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.7701727151870728},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.7603416442871094},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6880772113800049},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6414688229560852},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6105654835700989},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5966617465019226},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5519758462905884},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.4467610716819763},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.43510228395462036},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.42683690786361694},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.41071704030036926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35200512409210205},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33852437138557434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23264911770820618},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1448163092136383},{"id":"https://openalex.org/keywords/numerical-analysis","display_name":"Numerical analysis","score":0.12854593992233276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833153605461121},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.7701727151870728},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.7603416442871094},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6880772113800049},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6414688229560852},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6105654835700989},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5966617465019226},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5519758462905884},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.4467610716819763},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.43510228395462036},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.42683690786361694},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.41071704030036926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35200512409210205},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33852437138557434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23264911770820618},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1448163092136383},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.12854593992233276},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3210377.3210394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3210377.3210394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt8s02j324","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8s02j324","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1884191083","https://openalex.org/W1903029394","https://openalex.org/W2027999075","https://openalex.org/W2056999868","https://openalex.org/W2097117768","https://openalex.org/W2104373803","https://openalex.org/W2131613942","https://openalex.org/W2138243089","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2242218935","https://openalex.org/W2483598939","https://openalex.org/W2559655401","https://openalex.org/W2565436413","https://openalex.org/W2604272474","https://openalex.org/W2613718673","https://openalex.org/W2766577666","https://openalex.org/W2785452945","https://openalex.org/W2962747323","https://openalex.org/W3100417409","https://openalex.org/W6638803421","https://openalex.org/W6639540389","https://openalex.org/W6683722107","https://openalex.org/W6743955621","https://openalex.org/W6756692837"],"related_works":["https://openalex.org/W4240606930","https://openalex.org/W2494130044","https://openalex.org/W1972271823","https://openalex.org/W2003935582","https://openalex.org/W1501159154","https://openalex.org/W4399872414","https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W2040503315","https://openalex.org/W2177166030"],"abstract_inverted_index":{"We":[0,60,106,131],"propose":[1],"a":[2,41,68],"new":[3],"integrated":[4,96],"method":[5,49],"of":[6,16,103,147],"exploiting":[7],"model,":[8],"batch":[9,43,91,150],"and":[10,83,111],"domain":[11,136],"parallelism":[12,82,104],"for":[13,40,80,90],"the":[14,53,74,84,95,108,115,135,143,148],"training":[15],"deep":[17],"neural":[18],"networks":[19],"(DNNs)":[20],"on":[21],"large":[22],"distributed-memory":[23],"computers":[24],"using":[25,45],"minibatch":[26],"stochastic":[27],"gradient":[28],"descent":[29],"(SGD).":[30],"Our":[31,48],"goal":[32],"is":[33,50,77,87],"to":[34],"find":[35],"an":[36],"efficient":[37],"parallelization":[38],"strategy":[39],"fixed":[42],"size":[44],"P":[46,62],"processes.":[47],"inspired":[51],"by":[52],"communication-avoiding":[54],"algorithms":[55],"in":[56,141],"numerical":[57],"linear":[58],"algebra.":[59],"see":[61],"processes":[63],"as":[64],"logically":[65],"divided":[66],"into":[67],"P_r":[69,75],"x":[70],"P_c":[71,85],"grid":[72],"where":[73],"dimension":[76,86],"implicitly":[78,88],"responsible":[79,89],"model/domain":[81],"parallelism.":[92,130],"In":[93],"practice,":[94],"matrix-based":[97],"parallel":[98,137,151],"algorithm":[99],"encapsulates":[100],"these":[101],"types":[102],"automatically.":[105],"analyze":[107],"communication":[109,117],"complexity":[110],"analytically":[112],"demonstrate":[113],"that":[114],"lowest":[116],"costs":[118],"are":[119],"often":[120],"achieved":[121],"neither":[122],"with":[123,127],"pure":[124,128],"model":[125],"nor":[126],"data":[129],"also":[132],"show":[133],"how":[134],"approach":[138],"can":[139],"help":[140],"extending":[142],"theoretical":[144],"scaling":[145],"limit":[146],"typical":[149],"method.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}