{"id":"https://openalex.org/W2007441708","doi":"https://doi.org/10.1109/tpds.2014.2357437","title":"A Family of Bit-Representation-Optimized Formats for Fast Sparse Matrix-Vector Multiplication on the GPU","display_name":"A Family of Bit-Representation-Optimized Formats for Fast Sparse Matrix-Vector Multiplication on the GPU","publication_year":2014,"publication_date":"2014-09-11","ids":{"openalex":"https://openalex.org/W2007441708","doi":"https://doi.org/10.1109/tpds.2014.2357437","mag":"2007441708"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2357437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2357437","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5103180941","display_name":"Wai Teng Tang","orcid":"https://orcid.org/0000-0002-6553-1270"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wai Teng Tang","raw_affiliation_strings":["Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","Institute of High\u2010Performance Computing, Agency for Science, Technology, and Research  Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute of High\u2010Performance Computing, Agency for Science, Technology, and Research  Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080332038","display_name":"Wen Jun Tan","orcid":"https://orcid.org/0000-0003-2204-0639"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wen Jun Tan","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University,,Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University,,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","Institute of High\u2010Performance Computing, Agency for Science, Technology, and Research  Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute of High\u2010Performance Computing, Agency for Science, Technology, and Research  Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055281326","display_name":"Stephen John Turner","orcid":"https://orcid.org/0000-0002-7421-9801"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Stephen John Turner","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University,,Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University,,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore","Department of Computer Science, National University of Singapore, Singapore,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore,","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103180941"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":1.4243,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.81145585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"9","first_page":"2373","last_page":"2385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9991999864578247,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8041775226593018},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6956335306167603},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6834797263145447},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6535236835479736},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6111281514167786},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5454230904579163},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.48201480507850647},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4355802834033966},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35802948474884033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12250947952270508},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06584885716438293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041775226593018},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6956335306167603},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6834797263145447},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6535236835479736},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6111281514167786},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5454230904579163},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.48201480507850647},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4355802834033966},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35802948474884033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12250947952270508},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06584885716438293},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2014.2357437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2357437","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1485394581","display_name":null,"funder_award_id":"102-101-0028","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1518969538","https://openalex.org/W1588915715","https://openalex.org/W1653630692","https://openalex.org/W1884140786","https://openalex.org/W1948792255","https://openalex.org/W1965551736","https://openalex.org/W1981220107","https://openalex.org/W1982733412","https://openalex.org/W1988311079","https://openalex.org/W1990832096","https://openalex.org/W1995649289","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2043105874","https://openalex.org/W2066637933","https://openalex.org/W2072806558","https://openalex.org/W2084446096","https://openalex.org/W2089099677","https://openalex.org/W2091908315","https://openalex.org/W2099625934","https://openalex.org/W2114977680","https://openalex.org/W2119547137","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2132117096","https://openalex.org/W2142356482","https://openalex.org/W2162283062","https://openalex.org/W2518567779","https://openalex.org/W6630991115","https://openalex.org/W6635140808","https://openalex.org/W6647404394","https://openalex.org/W6677187859","https://openalex.org/W6678107477","https://openalex.org/W6680645508"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2983282793","https://openalex.org/W2052993554","https://openalex.org/W2046125858"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,9,28,177],"an":[5,181],"important":[6],"kernel":[7],"that":[8,139,168],"used":[10],"in":[11],"many":[12,67],"iterative":[13],"algorithms":[14],"for":[15,84],"solving":[16],"scientific":[17],"and":[18,69,96,103,133,144,151,162],"engineering":[19],"problems.":[20],"One":[21],"of":[22,26,37,62,66,79,114,160,184],"the":[23,33,38,59,63,112,172],"main":[24],"challenges":[25],"SpMV":[27,48,108],"its":[29,52],"memory-boundedness":[30],"due":[31],"to":[32,46,105,141,156,179],"low":[34],"arithmetic":[35],"intensity":[36],"kernel.":[39],"Although":[40],"compression":[41,68,82,99],"has":[42,54],"been":[43,56],"proposed":[44,91,148],"previously":[45],"improve":[47],"performance":[49],"on":[50,58,88,100,109],"CPUs,":[51],"use":[53],"not":[55],"demonstrated":[57],"GPU":[60],"because":[61],"serial":[64],"nature":[65],"decompression":[70],"schemes.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75,166],"introduce":[76],"a":[77],"family":[78],"bit-representation-optimized":[80],"(BRO)":[81],"formats":[83,92,124,153],"representing":[85],"sparse":[86],"matrices":[87],"GPUs.":[89],"The":[90],"-":[93],"BRO-CSR,":[94],"BRO-ELL":[95,152],"BRO-HYB,":[97],"perform":[98,128],"index":[101],"data":[102],"help":[104],"speed":[106],"up":[107],"GPUs":[110],"through":[111],"reduction":[113],"memory":[115],"traffic.":[116],"We":[117],"also":[118],"propose":[119],"two":[120],"other":[121],"hybrid":[122],"BRO":[123],"which":[125],"can":[126],"potentially":[127],"better":[129],"than":[130],"both":[131],"HYB":[132],"BRO-HYB":[134],"formats.":[135],"Experimental":[136],"results":[137],"demonstrate":[138,167],"compared":[140],"uncompressed":[142],"CSR":[143],"ELLPACK":[145],"formats,":[146],"our":[147],"compressed":[149],"BRO-CSR":[150],"are":[154],"able":[155,178],"achieve":[157,180],"average":[158,182],"speedups":[159],"2\u00d7":[161],"1.4\u00d7":[163],"respectively.":[164],"Furthermore,":[165],"by":[169],"using":[170],"BRO-ELL,":[171],"preconditioned":[173],"conjugate":[174],"gradient":[175],"method":[176],"speedup":[183],"1.3\u00d7":[185],"over":[186],"ELLPACK.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}