{"id":"https://openalex.org/W3022703302","doi":"https://doi.org/10.1145/3380930","title":"Load-balancing Sparse Matrix Vector Product Kernels on GPUs","display_name":"Load-balancing Sparse Matrix Vector Product Kernels on GPUs","publication_year":2020,"publication_date":"2020-03-29","ids":{"openalex":"https://openalex.org/W3022703302","doi":"https://doi.org/10.1145/3380930","mag":"3022703302"},"language":"en","primary_location":{"id":"doi:10.1145/3380930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380930","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","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/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Hartwig Anzt","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany and University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany and University of Tennessee, USA","institution_ids":["https://openalex.org/I102335020","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043131627","display_name":"Terry Cojean","orcid":"https://orcid.org/0000-0002-1560-921X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Terry Cojean","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423433","display_name":"Yen\u2010Chen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen Yen-Chen","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Oak Ridge National Lab, and University of Manchester, UK"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, Oak Ridge National Lab, and University of Manchester, UK","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I28407311","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017361033","display_name":"Goran Flegar","orcid":"https://orcid.org/0000-0002-4154-0420"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Goran Flegar","raw_affiliation_strings":["University of Jaume I, Spain"],"affiliations":[{"raw_affiliation_string":"University of Jaume I, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059984998","display_name":"Pratik Nayak","orcid":"https://orcid.org/0000-0002-7961-1159"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pratik Nayak","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037751512","display_name":"Yu\u2010Hsiang Tsai","orcid":"https://orcid.org/0000-0001-5229-3739"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuhsiang M. Tsai","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005786936","display_name":"Weichung Wang","orcid":"https://orcid.org/0000-0002-6154-7750"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Weichung Wang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5012133869"],"corresponding_institution_ids":["https://openalex.org/I102335020","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":6.3237,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97316103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9947999715805054,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9866999983787537,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147703766822815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6815868616104126},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6643763780593872},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5974913835525513},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5751264095306396},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5111234784126282},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4761003255844116},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46338948607444763},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.450010746717453},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4420577883720398},{"id":"https://openalex.org/keywords/padding","display_name":"Padding","score":0.42756569385528564},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41951465606689453},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3578486442565918},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.22911182045936584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16303327679634094},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1029190719127655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09075948596000671}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147703766822815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6815868616104126},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6643763780593872},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5974913835525513},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5751264095306396},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5111234784126282},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4761003255844116},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46338948607444763},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.450010746717453},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4420577883720398},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.42756569385528564},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41951465606689453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3578486442565918},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.22911182045936584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16303327679634094},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1029190719127655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09075948596000671},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3380930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380930","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},{"id":"pmh:oai:repositori.uji.es:10234/189298","is_oa":false,"landing_page_url":"http://hdl.handle.net/10234/189298","pdf_url":null,"source":{"id":"https://openalex.org/S4306400303","display_name":"Repositori UJI (Universitat Jaume I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I10902133","host_organization_name":"Universitat Jaume I","host_organization_lineage":["https://openalex.org/I10902133"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4579031876","display_name":null,"funder_award_id":"DE-SC0016513","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G532780029","display_name":null,"funder_award_id":"VH-NG-1241","funder_id":"https://openalex.org/F4320320876","funder_display_name":"Helmholtz-Gemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320876","display_name":"Helmholtz-Gemeinschaft","ror":"https://ror.org/0281dp749"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1588915715","https://openalex.org/W1749918898","https://openalex.org/W2009320922","https://openalex.org/W2009654791","https://openalex.org/W2101511474","https://openalex.org/W2109473404","https://openalex.org/W2116721352","https://openalex.org/W2128853364","https://openalex.org/W2167101736","https://openalex.org/W2505509943","https://openalex.org/W2518523798","https://openalex.org/W2559809597","https://openalex.org/W2570841452","https://openalex.org/W2617808919","https://openalex.org/W2766697789","https://openalex.org/W2914631005","https://openalex.org/W2949001633","https://openalex.org/W2965758384","https://openalex.org/W4230252700","https://openalex.org/W4232958218","https://openalex.org/W4376272906"],"related_works":["https://openalex.org/W2359925002","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2293771254","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2914631005","https://openalex.org/W2123154672","https://openalex.org/W2032786851"],"abstract_inverted_index":{"Efficient":[0],"processing":[1],"of":[2,23,65,117,140,190],"Irregular":[3,41],"Matrices":[4],"on":[5],"Single":[6],"Instruction,":[7],"Multiple":[8],"Data":[9],"(SIMD)-type":[10],"architectures":[11],"is":[12,38,134],"a":[13,32,85,98,111,137,172,188],"persistent":[14],"challenge.":[15],"Resolving":[16],"it":[17,109],"requires":[18],"innovations":[19],"in":[20,58,120,151,194],"the":[21,47,63,102,118,129,132,141,145,152,159,184],"development":[22],"data":[24],"formats,":[25],"computational":[26],"techniques,":[27],"and":[28,43,107,131,171],"implementations":[29],"that":[30,114,178],"strike":[31],"balance":[33],"between":[34,128],"thread":[35,49],"divergence,":[36],"which":[37,45],"inherent":[39],"for":[40,77,92,101],"Matrices,":[42],"padding,":[44],"alleviates":[46],"performance-detrimental":[48],"divergence":[50],"but":[51],"introduces":[52],"artificial":[53],"overheads.":[54],"To":[55],"this":[56,59],"end,":[57],"article,":[60],"we":[61,157],"address":[62],"challenge":[64],"designing":[66],"high":[67],"performance":[68,160],"sparse":[69,87],"matrix-vector":[70],"product":[71],"(S":[72],"p":[73,163],"MV)":[74],"kernels":[75,165],"designed":[76],"Nvidia":[78],"Graphics":[79],"Processing":[80],"Units":[81],"(GPUs).":[82],"We":[83,95],"present":[84],"compressed":[86],"row":[88],"(CSR)":[89],"format":[90,106,123],"suitable":[91],"unbalanced":[93],"matrices.":[94],"also":[96],"provide":[97],"load-balancing":[99],"kernel":[100,177],"coordinate":[103],"(COO)":[104],"matrix":[105,119,155,191],"extend":[108],"to":[110],"hybrid":[112],"algorithm":[113],"stores":[115],"part":[116],"SIMD-friendly":[121],"Ellpack":[122],"(ELL)":[124],"format.":[125,196],"The":[126],"ratio":[127],"ELL-":[130],"COO-part":[133],"determined":[135],"using":[136],"theoretical":[138],"analysis":[139],"nonzeros-per-row":[142],"distribution.":[143],"For":[144],"over":[146],"2,800":[147],"test":[148],"matrices":[149,186],"available":[150],"Suite":[153],"Sparse":[154],"collection,":[156],"compare":[158],"against":[161],"S":[162],"MV":[164],"provided":[166],"by":[167,182],"NVIDIA\u2019s":[168],"cuSPARSE":[169],"library":[170],"heavily-tuned":[173],"sliced":[174],"ELL":[175,195],"(SELL-P)":[176],"prevents":[179],"unnecessary":[180],"padding":[181],"considering":[183],"irregular":[185],"as":[187],"combination":[189],"blocks":[192],"stored":[193]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
