{"id":"https://openalex.org/W2327509551","doi":"https://doi.org/10.1177/1094342015593156","title":"A hybrid format for better performance of sparse matrix-vector multiplication on a GPU","display_name":"A hybrid format for better performance of sparse matrix-vector multiplication on a GPU","publication_year":2015,"publication_date":"2015-07-14","ids":{"openalex":"https://openalex.org/W2327509551","doi":"https://doi.org/10.1177/1094342015593156","mag":"2327509551"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015593156","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015593156","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5102191883","display_name":"Dahai Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dahai Guo","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"institutions":[{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Gropp","raw_affiliation_strings":["Department of Computer Science, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Urbana, IL, USA","institution_ids":["https://openalex.org/I183874917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027808971","display_name":"Luke N. Olson","orcid":"https://orcid.org/0000-0002-5283-6104"},"institutions":[{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke N Olson","raw_affiliation_strings":["Department of Computer Science, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Urbana, IL, USA","institution_ids":["https://openalex.org/I183874917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102191883"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"],"apc_list":null,"apc_paid":null,"fwci":2.258,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88532884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":"1","first_page":"103","last_page":"120"},"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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.996999979019165,"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/row","display_name":"Row","score":0.7814990282058716},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.699636697769165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641767024993896},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6368574500083923},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5593027472496033},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5498067736625671},{"id":"https://openalex.org/keywords/row-and-column-spaces","display_name":"Row and column spaces","score":0.5320269465446472},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5174291729927063},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4988243579864502},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.41289883852005005},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3911629021167755},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34805089235305786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23800095915794373},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11509168148040771},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.07596969604492188}],"concepts":[{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.7814990282058716},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.699636697769165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641767024993896},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6368574500083923},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5593027472496033},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5498067736625671},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.5320269465446472},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5174291729927063},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4988243579864502},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.41289883852005005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3911629021167755},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34805089235305786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23800095915794373},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11509168148040771},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.07596969604492188},{"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/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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015593156","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015593156","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W192356505","https://openalex.org/W1965034778","https://openalex.org/W1985263109","https://openalex.org/W1986453598","https://openalex.org/W1990343439","https://openalex.org/W1993704253","https://openalex.org/W2002555321","https://openalex.org/W2035080386","https://openalex.org/W2096813338","https://openalex.org/W2097479462","https://openalex.org/W2101511474","https://openalex.org/W2115215129","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2151285624","https://openalex.org/W2626696598"],"related_works":["https://openalex.org/W2313440505","https://openalex.org/W3123744736","https://openalex.org/W2137691148","https://openalex.org/W1505848319","https://openalex.org/W2905020035","https://openalex.org/W4281399881","https://openalex.org/W3166006430","https://openalex.org/W4281971614","https://openalex.org/W2049180840","https://openalex.org/W3121299875"],"abstract_inverted_index":{"In":[0,92],"this":[1,76,124],"paper,":[2],"we":[3],"present":[4],"a":[5,24,34,59,64,130,134],"new":[6],"sparse":[7,20,37,89],"matrix":[8,38,60,79,138],"data":[9],"format":[10],"that":[11],"leads":[12],"to":[13,107,122],"improved":[14],"memory":[15],"coalescing":[16],"and":[17,71,126],"more":[18],"efficient":[19],"matrix-vector":[21],"multiplication":[22],"for":[23,111],"wide":[25,135],"range":[26,136],"of":[27,55,96,137],"problems":[28],"on":[29,47,75],"high-throughput":[30],"architectures":[31],"such":[32],"as":[33,52],"GPU.":[35],"The":[36],"structure":[39],"is":[40],"constructed":[41],"by":[42,63,101],"sorting":[43],"the":[44,48,53,78,94,109,127],"rows":[45,70],"based":[46],"row":[49,90,103],"length":[50],"(defined":[51],"number":[54,95],"non-zero":[56],"elements":[57],"in":[58,105],"row)":[61],"followed":[62],"partition":[65],"into":[66,84],"two":[67],"ranges,":[68],"short":[69],"long":[72],"rows.":[73],"Based":[74],"partition,":[77],"entries":[80],"are":[81,98,120],"then":[82],"transformed":[83],"ELLPACK":[85],"or":[86],"vectorized":[87],"compressed":[88],"format.":[91],"addition,":[93],"threads":[97],"adaptively":[99],"selected":[100],"their":[102],"length,":[104],"order":[106],"balance":[108],"workload":[110],"each":[112],"graphics":[113],"processing":[114],"unit":[115],"thread.":[116],"Several":[117],"computational":[118],"experiments":[119],"presented":[121],"support":[123],"approach":[125],"results":[128],"suggest":[129],"notable":[131],"improvement":[132],"over":[133],"structures.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}