{"id":"https://openalex.org/W2558367073","doi":"https://doi.org/10.1109/hpec.2016.7761634","title":"How naive is naive SpMV on the GPU?","display_name":"How naive is naive SpMV on the GPU?","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2558367073","doi":"https://doi.org/10.1109/hpec.2016.7761634","mag":"2558367073"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2016.7761634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2016.7761634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5014594342","display_name":"Markus Steinberger","orcid":"https://orcid.org/0000-0001-5977-8536"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Markus Steinberger","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743883","display_name":"Andreas Derlery","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Derlery","raw_affiliation_strings":["Technische Universitat Graz, Graz, Steiermark, AT"],"affiliations":[{"raw_affiliation_string":"Technische Universitat Graz, Graz, Steiermark, AT","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070162106","display_name":"Rhaleb Zayer","orcid":"https://orcid.org/0000-0002-3452-6276"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rhaleb Zayer","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058028526","display_name":"Hans\u2010Peter Seidel","orcid":"https://orcid.org/0000-0002-1343-8613"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans-Peter Seidel","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014594342"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":1.6052,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83327246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9977999925613403,"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":0.8676314353942871},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.752607524394989},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7205349802970886},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6662516593933105},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6104722619056702},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.5841768980026245},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4435677230358124},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17813077569007874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676314353942871},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.752607524394989},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7205349802970886},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6662516593933105},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6104722619056702},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.5841768980026245},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4435677230358124},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17813077569007874},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec.2016.7761634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2016.7761634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_2351708","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002B-98A5-F","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE High Performance Extreme Computing Conference","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1508286210","https://openalex.org/W1588915715","https://openalex.org/W1981824841","https://openalex.org/W1985938427","https://openalex.org/W1993704253","https://openalex.org/W1995649289","https://openalex.org/W2009654791","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2035278858","https://openalex.org/W2087830284","https://openalex.org/W2088866486","https://openalex.org/W2096813338","https://openalex.org/W2103877122","https://openalex.org/W2124007994","https://openalex.org/W2126004407","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2154118576","https://openalex.org/W2162283062","https://openalex.org/W2183317050","https://openalex.org/W2997945685","https://openalex.org/W4243261006","https://openalex.org/W4285719527","https://openalex.org/W6686667855"],"related_works":["https://openalex.org/W3038415719","https://openalex.org/W2076165488","https://openalex.org/W2392023973","https://openalex.org/W2161462353","https://openalex.org/W2366665520","https://openalex.org/W2176391467","https://openalex.org/W1579918296","https://openalex.org/W2953648974","https://openalex.org/W2040556424","https://openalex.org/W2558367073"],"abstract_inverted_index":{"Sparse":[0],"matrix":[1],"vector":[2],"multiplication":[3,24,27],"(SpMV)":[4],"is":[5,40,178],"the":[6,48,61,73,93,99,127,135,168,171,176,207],"workhorse":[7],"for":[8,22,63,75,98],"a":[9,17,122,149,161],"wide":[10],"range":[11],"of":[12,50,96,129,137,163,170,193],"linear":[13],"algebra":[14],"computations.":[15],"In":[16,32,88,133],"serial":[18,173],"setting,":[19],"naive":[20,44,94,123,150,172,195],"implementations":[21,45,54,156],"direct":[23],"and":[25,55,115,140],"transposed":[26],"achieve":[28],"very":[29],"competitive":[30],"performance.":[31],"parallel":[33,53],"settings,":[34],"especially":[35,205],"on":[36,102,187],"graphics":[37],"hardware,":[38,107],"it":[39,183],"widely":[41],"believed":[42],"that":[43,121,167],"cannot":[46,142],"reach":[47,126],"performance":[49,128],"highly":[51],"tuned":[52],"complex":[56],"data":[57,64,164],"formats.":[58],"Most":[59],"often,":[60],"cost":[62,74,136],"conversion":[65,139],"to":[66,175,185],"these":[67],"specialized":[68],"formats":[69],"as":[70,72,80,109,180,182],"well":[71],"transpose":[76,208],"operations":[77,114,148],"are":[78],"neglected,":[79],"they":[81],"do":[82],"not":[83,179],"arise":[84],"in":[85,105,206],"all":[86],"algorithms.":[87],"this":[89],"paper,":[90],"we":[91,119],"revisit":[92],"implementation":[95,124,151,174],"SpMV":[97,131,147,203],"GPU.":[100],"Relying":[101],"recent":[103],"advances":[104],"GPU":[106,177,202],"such":[108],"fast":[110],"hardware":[111,189],"supported":[112],"atomic":[113],"better":[116],"cache":[117],"performance,":[118],"show":[120],"can":[125,152,197],"state-of-the-art":[130,155,201],"implementations.":[132],"case":[134],"format":[138],"transposition":[141],"be":[143,186],"amortized":[144],"over":[145,160],"many":[146],"even":[153],"outperform":[154],"significantly.":[157],"Experimental":[158],"results":[159],"variety":[162],"sets":[165],"suggest":[166],"adoption":[169],"inferior":[181],"used":[184],"previous":[188],"generations.":[190],"The":[191],"integration":[192],"some":[194],"strategies":[196],"potentially":[198],"speed":[199],"up":[200],"implementations,":[204],"case.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}