{"id":"https://openalex.org/W2128853364","doi":"https://doi.org/10.1145/1654059.1654078","title":"Implementing sparse matrix-vector multiplication on throughput-oriented processors","display_name":"Implementing sparse matrix-vector multiplication on throughput-oriented processors","publication_year":2009,"publication_date":"2009-11-14","ids":{"openalex":"https://openalex.org/W2128853364","doi":"https://doi.org/10.1145/1654059.1654078","mag":"2128853364"},"language":"en","primary_location":{"id":"doi:10.1145/1654059.1654078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","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/A5108095852","display_name":"Nathan Bell","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nathan Bell","raw_affiliation_strings":["NVIDIA Research","[NVIDIA Research]"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"[NVIDIA Research]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA Research","[NVIDIA Research]"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"[NVIDIA Research]","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108095852"],"corresponding_institution_ids":["https://openalex.org/I1304085615"],"apc_list":null,"apc_paid":null,"fwci":53.5522,"has_fulltext":false,"cited_by_count":892,"citation_normalized_percentile":{"value":0.99962161,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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/parallel-computing","display_name":"Parallel computing","score":0.8125838041305542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811973512172699},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6962568759918213},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6740840077400208},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6549617052078247},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6060706973075867},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.551969051361084},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4818200170993805},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45015591382980347},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4469604790210724},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.41720306873321533},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33985477685928345},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.13220295310020447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1293809413909912},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07063454389572144}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8125838041305542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811973512172699},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6962568759918213},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6740840077400208},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6549617052078247},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6060706973075867},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.551969051361084},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4818200170993805},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45015591382980347},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4469604790210724},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.41720306873321533},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33985477685928345},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.13220295310020447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1293809413909912},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07063454389572144},{"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/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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1654059.1654078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.1350","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.1350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nvidia.com/docs/IO/77944/sc09-spmv-throughput.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1480928214","https://openalex.org/W1506342804","https://openalex.org/W1568272005","https://openalex.org/W1965122136","https://openalex.org/W1988425770","https://openalex.org/W1990832096","https://openalex.org/W2028499920","https://openalex.org/W2051142108","https://openalex.org/W2063186542","https://openalex.org/W2095292158","https://openalex.org/W2103877122","https://openalex.org/W2119547137","https://openalex.org/W2124007994","https://openalex.org/W2128131218","https://openalex.org/W2130289795","https://openalex.org/W2151285624","https://openalex.org/W2155503253","https://openalex.org/W2167868137","https://openalex.org/W3138798301","https://openalex.org/W4229666556"],"related_works":["https://openalex.org/W2392023973","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2293771254","https://openalex.org/W1835670156","https://openalex.org/W4381050447","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W3147497457","https://openalex.org/W3004823601"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,128],"of":[5,18,28,42,96,145],"singular":[6],"importance":[7],"in":[8,111],"sparse":[9,22,46],"linear":[10,20],"algebra.":[11],"In":[12],"contrast":[13],"to":[14,34,73],"the":[15,32,35,39,77,132],"uniform":[16],"regularity":[17,58],"dense":[19],"algebra,":[21],"operations":[23,47],"encounter":[24],"a":[25,123,146],"broad":[26],"spectrum":[27],"matrices":[29],"ranging":[30],"from":[31],"regular":[33],"highly":[36],"irregular.":[37],"Harnessing":[38],"tremendous":[40],"potential":[41],"throughput-oriented":[43,74],"processors":[44],"for":[45,114],"requires":[48],"that":[49,70,144],"we":[50,88],"expose":[51],"substantial":[52],"fine-grained":[53],"parallelism":[54],"and":[55,62,79,108,117,139],"impose":[56],"sufficient":[57],"on":[59,122,136],"execution":[60],"paths":[61],"memory":[63],"access":[64],"patterns.":[65],"We":[66],"explore":[67],"SpMV":[68],"methods":[69],"are":[71,90],"well-suited":[72],"architectures":[75],"like":[76],"GPU":[78],"which":[80],"exploit":[81],"several":[82],"common":[83],"sparsity":[84],"classes.":[85],"The":[86],"techniques":[87],"propose":[89],"efficient,":[91],"successfully":[92],"utilizing":[93],"large":[94],"percentages":[95],"peak":[97],"bandwidth.":[98],"Furthermore,":[99],"they":[100],"deliver":[101],"excellent":[102],"total":[103],"throughput,":[104],"averaging":[105],"16":[106],"GFLOP/s":[107,110],"10":[109,142],"double":[112],"precision":[113],"structured":[115],"grid":[116],"unstructured":[118],"mesh":[119],"matrices,":[120],"respectively,":[121],"GeForce":[124],"GTX":[125],"285.":[126],"This":[127],"roughly":[129],"2.8":[130],"times":[131,143],"throughput":[133],"previously":[134],"achieved":[135],"Cell":[137],"BE":[138],"more":[140],"than":[141],"quad-core":[147],"Intel":[148],"Clovertown":[149],"system.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":51},{"year":2017,"cited_by_count":46},{"year":2016,"cited_by_count":82},{"year":2015,"cited_by_count":63},{"year":2014,"cited_by_count":80},{"year":2013,"cited_by_count":70},{"year":2012,"cited_by_count":88}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}