{"id":"https://openalex.org/W2604025065","doi":"https://doi.org/10.1109/tpds.2017.2686384","title":"Improving Execution Concurrency of Large-Scale Matrix Multiplication on Distributed Data-Parallel Platforms","display_name":"Improving Execution Concurrency of Large-Scale Matrix Multiplication on Distributed Data-Parallel Platforms","publication_year":2017,"publication_date":"2017-03-23","ids":{"openalex":"https://openalex.org/W2604025065","doi":"https://doi.org/10.1109/tpds.2017.2686384","mag":"2604025065"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2686384","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5052175650","display_name":"Rong Gu","orcid":"https://orcid.org/0000-0002-1565-9997"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Gu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926294","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-4075-5227"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751736","display_name":"Chen Tian","orcid":"https://orcid.org/0000-0003-2710-7628"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Tian","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025481175","display_name":"Hucheng Zhou","orcid":"https://orcid.org/0000-0002-1894-3897"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hucheng Zhou","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069991775","display_name":"Guanru Li","orcid":"https://orcid.org/0000-0003-4467-7534"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanru Li","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005464184","display_name":"Xudong Zheng","orcid":"https://orcid.org/0000-0002-9056-2116"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zheng","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007538828","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0003-1806-0936"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu Sheng, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.654,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":23,"citation_normalized_percentile":{"value":0.970448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":92},"biblio":{"volume":"28","issue":"9","first_page":"2539","last_page":"2552"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9995,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994,"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/speedup","display_name":"Speedup","score":0.5845549},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5263052},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45502383},{"id":"https://openalex.org/keywords/concurrent-computing","display_name":"Concurrent computing","score":0.4259249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174007},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7516834},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5845549},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5759199},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5536912},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5263052},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5203709},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5049506},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5044166},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45502383},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.4259249},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42497402},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27678505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22512004},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08939427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.074442},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2686384","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61572250"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61602194"}],"datasets":[],"versions":[],"referenced_works_count":32,"referenced_works":["https://openalex.org/W1448681276","https://openalex.org/W1502544429","https://openalex.org/W164687769","https://openalex.org/W1947869163","https://openalex.org/W1969891822","https://openalex.org/W1973262089","https://openalex.org/W1979567624","https://openalex.org/W1997882689","https://openalex.org/W200298483","https://openalex.org/W2013373704","https://openalex.org/W2032839380","https://openalex.org/W2056999868","https://openalex.org/W2078945459","https://openalex.org/W2100830825","https://openalex.org/W2102458936","https://openalex.org/W2112523971","https://openalex.org/W2112651225","https://openalex.org/W2131975293","https://openalex.org/W2135653967","https://openalex.org/W2153820245","https://openalex.org/W2168748809","https://openalex.org/W2169251528","https://openalex.org/W2173213060","https://openalex.org/W2216541755","https://openalex.org/W2220584184","https://openalex.org/W2240529189","https://openalex.org/W2255383145","https://openalex.org/W2399225167","https://openalex.org/W2570467259","https://openalex.org/W2951113132","https://openalex.org/W4297789040","https://openalex.org/W78077100"],"related_works":["https://openalex.org/W4287593139","https://openalex.org/W4239424132","https://openalex.org/W4206811032","https://openalex.org/W3212757063","https://openalex.org/W3099313426","https://openalex.org/W2995605830","https://openalex.org/W2596457687","https://openalex.org/W2086146848","https://openalex.org/W2086123442","https://openalex.org/W1506547947"],"abstract_inverted_index":{"Matrix":[0,89],"multiplication":[1,31,47,100,114],"is":[2,19,36],"a":[3,57,81,93,130,175,179,222],"dominant":[4],"but":[5],"very":[6],"time-consuming":[7],"operation":[8],"in":[9,148],"many":[10],"big":[11],"data":[12,142],"analytic":[13],"applications.":[14],"Thus":[15],"its":[16],"performance":[17,27,61,124],"optimization":[18],"an":[20],"important":[21],"and":[22,41,157,187,207,213,237],"fundamental":[23],"research":[24],"issue.":[25],"The":[26,104,219],"of":[28,67,74,125,132,140,153,167,181],"large-scale":[29,98],"matrix":[30,46,99,113,155,168,183,197],"on":[32,101,185,216],"distributed":[33],"data-parallel":[34,102],"platforms":[35],"determined":[37],"by":[38,144,163,233],"both":[39],"computation":[40,76],"IO":[42,69,118],"costs.":[43],"For":[44,195],"existing":[45,201],"execution":[48,52,60,84,109],"strategies,":[49],"when":[50],"the":[51,65,68,72,75,116,123,138,151,165,192],"concurrency":[53,110,139],"scales":[54],"up":[55],"above":[56,231],"threshold,":[58],"their":[59],"deteriorates":[62],"quickly":[63],"because":[64],"increase":[66],"cost":[70],"outweighs":[71],"decrease":[73],"cost.":[77,119],"This":[78],"paper":[79],"presents":[80],"novel":[82,133],"parallel":[83,94],"strategy":[85,106],"CRMM":[86,105],"(Concurrent":[87],"Replication-based":[88],"Multiplication)":[90],"along":[91,177],"with":[92,115,178,209],"algorithm,":[95],"Marlin,":[96,126],"for":[97,111],"platforms.":[103],"exploits":[107],"higher":[108],"sub-block":[112],"same":[117],"To":[120],"further":[121],"improve":[122],"we":[127],"also":[128,188,226],"propose":[129],"number":[131],"system-level":[134],"optimizations,":[135],"including":[136,203],"increasing":[137],"local":[141],"exchange":[143],"calling":[145],"native":[146],"library":[147,176],"batch,":[149],"reducing":[150,158],"overhead":[152],"block":[154],"transformation,":[156],"disk":[159],"heavy":[160],"shuffle":[161],"operations":[162,184],"exploiting":[164],"semantics":[166],"computation.":[169],"We":[170],"have":[171],"implemented":[172],"Marlin":[173,190,199,229],"as":[174],"set":[180],"related":[182],"Spark":[186,204],"contributed":[189],"to":[191],"open-source":[193],"community.":[194],"large-sized":[196],"multiplication,":[198],"outperforms":[200,230],"systems":[202,232],"MLlib,":[205],"SystemML":[206],"SciDB,":[208],"about":[210,234],"1.29\u00d7,":[211],"3.53\u00d7":[212],"2.21\u00d7":[214],"speedup":[215],"average,":[217],"respectively.":[218,240],"evaluation":[220],"upon":[221],"real-world":[223],"DNN":[224],"workload":[225],"indicates":[227],"that":[228],"12.8\u00d7,":[235],"5.1\u00d7":[236],"27.2\u00d7":[238],"speedup,":[239]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2604025065","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2024-12-08T13:16:54.623891","created_date":"2017-04-07"}