{"id":"https://openalex.org/W2415007423","doi":"https://doi.org/10.1145/2925426.2926278","title":"Optimizing Sparse Matrix-Vector Multiplication for Large-Scale Data Analytics","display_name":"Optimizing Sparse Matrix-Vector Multiplication for Large-Scale Data Analytics","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2415007423","doi":"https://doi.org/10.1145/2925426.2926278","mag":"2415007423"},"language":"en","primary_location":{"id":"doi:10.1145/2925426.2926278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2925426.2926278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","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/A5019212161","display_name":"Daniele Buono","orcid":"https://orcid.org/0009-0002-1433-9104"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniele Buono","raw_affiliation_strings":["IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066195314","display_name":"Fabrizio Petrini","orcid":"https://orcid.org/0000-0002-4977-7107"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabrizio Petrini","raw_affiliation_strings":["IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047885427","display_name":"Fabio Checconi","orcid":"https://orcid.org/0000-0002-7279-8459"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabio Checconi","raw_affiliation_strings":["IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381433","display_name":"Xing Liu","orcid":"https://orcid.org/0000-0001-6531-5001"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Liu","raw_affiliation_strings":["IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061975788","display_name":"Xinyu Que","orcid":"https://orcid.org/0000-0002-4057-3255"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Que","raw_affiliation_strings":["IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113644818","display_name":"Chris Long","orcid":null},"institutions":[{"id":"https://openalex.org/I1330347796","display_name":"United States Department of Defense","ror":"https://ror.org/0447fe631","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Long","raw_affiliation_strings":["US Department of Defense"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Department of Defense","institution_ids":["https://openalex.org/I1330347796"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069592479","display_name":"Tai-Ching Tuan","orcid":null},"institutions":[{"id":"https://openalex.org/I1330347796","display_name":"United States Department of Defense","ror":"https://ror.org/0447fe631","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tai-Ching Tuan","raw_affiliation_strings":["US Department of Defense"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Department of Defense","institution_ids":["https://openalex.org/I1330347796"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976000189781189,"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":0.8391585350036621},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6788570880889893},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6623374223709106},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6590602397918701},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6173860430717468},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5222681164741516},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5039107203483582},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.48276036977767944},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45876187086105347},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.44906938076019287},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3515062630176544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15086302161216736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09119126200675964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391585350036621},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6788570880889893},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6623374223709106},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6590602397918701},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6173860430717468},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5222681164741516},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5039107203483582},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.48276036977767944},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45876187086105347},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44906938076019287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3515062630176544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15086302161216736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09119126200675964},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2925426.2926278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2925426.2926278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W1482680420","https://openalex.org/W1518947877","https://openalex.org/W1572929506","https://openalex.org/W1835670156","https://openalex.org/W1969835518","https://openalex.org/W1975116854","https://openalex.org/W1975414584","https://openalex.org/W1981902599","https://openalex.org/W1987840949","https://openalex.org/W1990832096","https://openalex.org/W2028314260","https://openalex.org/W2035080386","https://openalex.org/W2061919600","https://openalex.org/W2087507944","https://openalex.org/W2093053744","https://openalex.org/W2126004407","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2138621811","https://openalex.org/W2141113219","https://openalex.org/W2141380216","https://openalex.org/W2142496304","https://openalex.org/W2154590891","https://openalex.org/W2161118554","https://openalex.org/W2167868137","https://openalex.org/W2755088640","https://openalex.org/W3103552514","https://openalex.org/W3103560620","https://openalex.org/W4243261006","https://openalex.org/W6628673860","https://openalex.org/W6659374036"],"related_works":["https://openalex.org/W4287593139","https://openalex.org/W3099313426","https://openalex.org/W2086146848","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,82,161],"a":[5,10,24,50,78,122,126,164],"fundamental":[6],"kernel,":[7],"used":[8],"by":[9],"large":[11],"class":[12],"of":[13,35,111,118,136,145,151,169,183],"numerical":[14],"algorithms.":[15,102],"Emerging":[16],"big-data":[17,107],"and":[18],"machine":[19],"learning":[20],"applications":[21],"are":[22],"propelling":[23],"renewed":[25],"interest":[26],"in":[27,84],"SpMV":[28,55,66],"algorithms":[29,56],"that":[30,62,81],"can":[31,172],"tackle":[32],"massive":[33],"amount":[34],"unstructured":[36],"data---rapidly":[37],"approaching":[38],"the":[39,64,73,85,115,119,146,157],"TeraByte":[40],"range---with":[41],"predictable,":[42],"high":[43],"performance.":[44],"In":[45,72,149,167],"this":[46,96],"paper":[47],"we":[48,76,98],"describe":[49],"new":[51],"methodology":[52],"to":[53,91,140,163,177],"design":[54],"for":[57],"shared":[58],"memory":[59,93],"multiprocessors":[60],"(SMPs)":[61],"organizes":[63],"original":[65],"algorithm":[67],"into":[68],"two":[69,101],"distinct":[70],"phases.":[71],"first":[74],"phase":[75],"build":[77],"scaled":[79],"matrix,":[80],"reduced":[83],"second":[86],"phase,":[87],"providing":[88],"numerous":[89],"opportunities":[90],"exploit":[92],"locality.":[94],"Using":[95],"methodology,":[97],"have":[99],"designed":[100],"Our":[103],"experiments":[104],"on":[105,125],"irregular":[106],"matrices":[108,174],"(an":[109],"order":[110,182],"magnitude":[112,184],"larger":[113,185],"than":[114,186],"current":[116],"state":[117],"art)":[120],"show":[121],"quasi-optimal":[123],"scaling":[124],"large-scale":[127],"POWER8":[128,158],"SMP":[129,159],"system,":[130],"with":[131,154,175],"an":[132,141,181],"average":[133],"performance":[134],"speedup":[135],"3.8x,":[137],"when":[138],"compared":[139],"equally":[142],"optimized":[143],"version":[144],"CSR":[147],"algorithm.":[148],"terms":[150,168],"absolute":[152],"performance,":[153],"our":[155],"implementation,":[156],"system":[160],"comparable":[162],"256-node":[165],"cluster.":[166],"size,":[170],"it":[171],"process":[173],"up":[176],"68":[178],"billion":[179],"edges,":[180],"state-of-the-art":[187],"clusters.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}