{"id":"https://openalex.org/W4405806579","doi":"https://doi.org/10.1631/fitee.2300684","title":"Automatic parallelism strategy generation with minimal memory redundancy","display_name":"Automatic parallelism strategy generation with minimal memory redundancy","publication_year":2024,"publication_date":"2024-12-26","ids":{"openalex":"https://openalex.org/W4405806579","doi":"https://doi.org/10.1631/fitee.2300684"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2300684","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300684","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5050106599","display_name":"Yue Shi","orcid":"https://orcid.org/0000-0002-8899-1018"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanqi Shi","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061876398","display_name":"Peng Liang","orcid":"https://orcid.org/0000-0002-5590-5179"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liang","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981248","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0003-0388-0755"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043045076","display_name":"Linbo Qiao","orcid":"https://orcid.org/0000-0002-8285-2738"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linbo Qiao","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050106599"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26260692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"109","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9983999729156494,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7060111165046692},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6698768734931946},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6469027400016785},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6441558003425598},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.45011106133461},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.41180163621902466},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15338006615638733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060111165046692},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6698768734931946},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6469027400016785},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6441558003425598},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.45011106133461},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.41180163621902466},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15338006615638733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2300684","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300684","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2163605009","https://openalex.org/W2584923503","https://openalex.org/W2883830791","https://openalex.org/W2887551368","https://openalex.org/W2902949074","https://openalex.org/W2947737663","https://openalex.org/W2963341956","https://openalex.org/W2971953675","https://openalex.org/W2973727699","https://openalex.org/W3019389960","https://openalex.org/W3101104221","https://openalex.org/W3204998121","https://openalex.org/W4224308101","https://openalex.org/W4293775467","https://openalex.org/W4317733979","https://openalex.org/W4319453176","https://openalex.org/W4385681149","https://openalex.org/W4386348101","https://openalex.org/W4386709668","https://openalex.org/W6600225990","https://openalex.org/W6600424091","https://openalex.org/W6600466347","https://openalex.org/W6600662749","https://openalex.org/W6604447124"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W2009213655","https://openalex.org/W1501159154","https://openalex.org/W1229628","https://openalex.org/W2105992728","https://openalex.org/W74409296","https://openalex.org/W2468095077","https://openalex.org/W4230999561","https://openalex.org/W1595672120"],"abstract_inverted_index":{"Large-scale":[0],"deep":[1],"learning":[2],"models":[3],"are":[4],"trained":[5],"distributedly":[6],"due":[7],"to":[8,56,93,135,138],"memory":[9,21,46,53,59,122,131],"and":[10,88,106,114,120,153],"computing":[11],"resource":[12],"limitations.":[13],"Few":[14],"existing":[15],"strategy":[16,79],"generation":[17],"approaches":[18],"take":[19],"optimal":[20,38,72],"minimization":[22],"as":[23],"the":[24,42,58,71,77,100,139,145,148],"objective.":[25],"To":[26,69],"fill":[27],"in":[28,64,108,143],"this":[29],"gap,":[30],"we":[31,75],"propose":[32,49],"a":[33,50,65,109],"novel":[34,51],"algorithm":[35,102],"that":[36,127],"generates":[37],"parallelism":[39,73,78,97],"strategies":[40],"with":[41],"constraint":[43],"of":[44,61,133,150],"minimal":[45,121],"redundancy.":[47,123],"We":[48],"redundant":[52],"cost":[54],"model":[55],"calculate":[57],"overhead":[60],"each":[62],"operator":[63],"given":[66],"parallel":[67,111],"strategy.":[68],"generate":[70],"strategy,":[74],"formulate":[76],"search":[80],"problem":[81,87],"into":[82],"an":[83,90],"integer":[84],"linear":[85],"programming":[86],"use":[89],"efficient":[91],"solver":[92],"find":[94],"minimal-memory":[95],"intra-operator":[96],"strategies.":[98],"Furthermore,":[99],"proposed":[101],"has":[103],"been":[104],"extended":[105],"implemented":[107],"multi-dimensional":[110],"training":[112],"framework":[113],"is":[115,156],"characterized":[116],"by":[117],"high":[118],"throughput":[119,149],"Experimental":[124],"results":[125],"demonstrate":[126],"our":[128,151],"approach":[129,152],"achieves":[130],"savings":[132],"up":[134],"67%":[136],"compared":[137],"latest":[140],"Megatron-LM":[141],"strategies;":[142],"contrast,":[144],"gap":[146],"between":[147],"its":[154],"counterparts":[155],"not":[157],"large.":[158]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}