{"id":"https://openalex.org/W4247828381","doi":"https://doi.org/10.1109/sc.2016.57","title":"Merge-Based Parallel Sparse Matrix-Vector Multiplication","display_name":"Merge-Based Parallel Sparse Matrix-Vector Multiplication","alternate_titles":[],"publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W4247828381","doi":"https://doi.org/10.1109/sc.2016.57"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2016.57","doi":"https://doi.org/10.1109/sc.2016.57","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2016.57","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC16: International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4247828381"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5061047316","display_name":"Duane Merrill","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duane Merrill","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602","observed_orcids":["https://orcid.org/0000-0001-6093-7602"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":5.8799,"has_fulltext":false,"cited_by_count":166,"citation_normalized_percentile":{"value":0.97007987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"678","last_page":"689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9750999808311462,"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":0.9750999808311462,"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":0.022099999710917473,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/sparse-matrix-vector-multiplication","display_name":"sparse matrix-vector multiplication","score":0.9990000128746033},{"id":"https://openalex.org/keywords/compressed-sparse-row","display_name":"compressed sparse row format","score":0.7710000276565552},{"id":"https://openalex.org/keywords/load-balancing","display_name":"load balancing","score":0.7020000219345093},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"parallel computing","score":0.47200000286102295},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.7070000171661377},{"id":"https://openalex.org/keywords/performance-predictability","display_name":"performance predictability","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114585876464844},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.71875},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7159641981124878},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6682156324386597},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5500612258911133},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4951919615268707},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4908488392829895},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.43078309297561646},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.42621827125549316},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4240257740020752},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.4154089689254761},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.363042414188385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1883620321750641},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.1763519048690796},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sc.2016.57","doi":"https://doi.org/10.1109/sc.2016.57","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2016.57","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC16: International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W1482680420","https://openalex.org/W1527464046","https://openalex.org/W1588915715","https://openalex.org/W1735172278","https://openalex.org/W1749918898","https://openalex.org/W1987840949","https://openalex.org/W2007441708","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2043105874","https://openalex.org/W2044031350","https://openalex.org/W2085248745","https://openalex.org/W2087507944","https://openalex.org/W2088866486","https://openalex.org/W2124007994","https://openalex.org/W2125528794","https://openalex.org/W2126004407","https://openalex.org/W2128853364","https://openalex.org/W2134237243","https://openalex.org/W2151285624","https://openalex.org/W2162283062","https://openalex.org/W2167868137","https://openalex.org/W2521313883","https://openalex.org/W2570841452","https://openalex.org/W4256207042","https://openalex.org/W6907659760"],"related_works":["https://openalex.org/W2284629249","https://openalex.org/W2741427986","https://openalex.org/W2794469028","https://openalex.org/W2318592257","https://openalex.org/W2041417770","https://openalex.org/W2527991513","https://openalex.org/W2571103886","https://openalex.org/W2525374804","https://openalex.org/W7130420947","https://openalex.org/W2898633576"],"abstract_inverted_index":{"We":[0,78,98],"present":[1],"a":[2,89],"strictly":[3],"balanced":[4],"method":[5,81,119],"for":[6,58],"the":[7,20,46,128],"parallel":[8],"computation":[9],"of":[10,36,93,130,139],"sparse":[11,25,95],"matrix-vector":[12],"products":[13],"(SpMV).":[14],"Our":[15],"algorithm":[16],"operates":[17],"directly":[18],"upon":[19,137],"Compressed":[21],"Sparse":[22],"Row":[23],"(CSR)":[24],"matrix":[26,96],"format":[27],"without":[28],"preprocessing,":[29],"inspection,":[30],"reformatting,":[31],"or":[32],"supplemental":[33],"encoding.":[34],"Regardless":[35],"nonzero":[37],"structure,":[38],"our":[39,54,80,118],"equitable":[40],"2D":[41],"merge-based":[42],"decomposition":[43],"tightly":[44],"bounds":[45],"workload":[47],"assigned":[48],"to":[49,109,127],"each":[50],"processing":[51],"element.":[52],"Furthermore,":[53],"technique":[55],"is":[56,124],"suitable":[57],"recursively":[59],"partitioning":[60],"CSR":[61],"datasets":[62],"themselves":[63],"into":[64],"multi-scale,":[65],"distributed,":[66],"NUMA,":[67],"and":[68,85,134],"GPU":[69,86],"environments":[70],"that":[71,100,123,138],"are":[72,104],"constrained":[73],"by":[74],"fixed-size":[75],"local":[76],"memories.":[77],"evaluate":[79],"on":[82],"both":[83],"CPU":[84],"microarchitectures":[87],"across":[88,113],"very":[90],"large":[91],"corpus":[92],"diverse":[94],"datasets.":[97,115],"show":[99],"traditional":[101],"CsrMV":[102,141],"methods":[103],"inconsistent":[105],"performers,":[106],"often":[107],"subject":[108],"order-of-magnitude":[110],"performance":[111,122],"variation":[112],"similarly-sized":[114],"In":[116],"comparison,":[117],"provides":[120],"predictable":[121],"substantially":[125],"uncorrelated":[126],"distribution":[129],"nonzeros":[131],"among":[132],"rows":[133],"broadly":[135],"improves":[136],"current":[140],"methods.":[142]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4247828381","counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2022-05-12T00:00:00"}
