{"id":"https://openalex.org/W2765161574","doi":"https://doi.org/10.1145/3148226.3148230","title":"Flexible batched sparse matrix-vector product on GPUs","display_name":"Flexible batched sparse matrix-vector product on GPUs","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2765161574","doi":"https://doi.org/10.1145/3148226.3148230","mag":"2765161574"},"language":"en","primary_location":{"id":"doi:10.1145/3148226.3148230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148226.3148230","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3148230&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3148230&type=pdf","any_repository_has_fulltext":null},"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Hartwig Anzt","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany and University of Tennessee"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany and University of Tennessee","institution_ids":["https://openalex.org/I102335020","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038274067","display_name":"Gary Collins","orcid":null},"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":"Gary Collins","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"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"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee and University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"University of Tennessee and University of Manchester, Manchester, UK","institution_ids":["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":["Universidad Jaume I, Castellon, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"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":"Enrique S. Quintana-Ort\u00ed","raw_affiliation_strings":["Universidad Jaume I, Castellon, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"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":0.6805,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70009785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.7705150842666626},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6874755024909973},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6794485449790955},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.676100492477417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6561828851699829},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5084320902824402},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.481693834066391},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4642086625099182},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37465083599090576},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.23194316029548645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09760123491287231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705150842666626},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6874755024909973},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6794485449790955},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.676100492477417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6561828851699829},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5084320902824402},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.481693834066391},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4642086625099182},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37465083599090576},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.23194316029548645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09760123491287231},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3148226.3148230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148226.3148230","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3148230&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3148226.3148230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3148226.3148230","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3148230&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.44999998807907104,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G5372185796","display_name":null,"funder_award_id":"DE-SC-0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6395306892","display_name":null,"funder_award_id":"732631 OPRECOMP","funder_id":"https://openalex.org/F4320338336","funder_display_name":"H2020 Future and Emerging Technologies"},{"id":"https://openalex.org/G7702789587","display_name":null,"funder_award_id":"TIN2014-53495-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320338336","display_name":"H2020 Future and Emerging Technologies","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2765161574.pdf","grobid_xml":"https://content.openalex.org/works/W2765161574.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1575701986","https://openalex.org/W2035080386","https://openalex.org/W2101511474","https://openalex.org/W2124007994","https://openalex.org/W2259574154","https://openalex.org/W2340769696","https://openalex.org/W2499931820","https://openalex.org/W2617808919","https://openalex.org/W3216978890","https://openalex.org/W4230252700","https://openalex.org/W6604925666"],"related_works":["https://openalex.org/W2119534391","https://openalex.org/W2503137108","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2765743988","https://openalex.org/W2062253548","https://openalex.org/W2393490604","https://openalex.org/W2393707426","https://openalex.org/W3203633922","https://openalex.org/W2146871484"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,10,38,69],"variety":[3],"of":[4,13,40,75],"batched":[5,26],"routines":[6],"for":[7],"concurrently":[8],"processing":[9,22],"large":[11],"collection":[12],"small-size,":[14],"independent":[15],"sparse":[16,58],"matrix-vector":[17],"products":[18],"(SpMV)":[19],"on":[20,68],"graphics":[21],"units":[23],"(GPUs).":[24],"These":[25],"SpMV":[27,82],"kernels":[28],"are":[29],"designed":[30],"to":[31,36,77,80],"be":[32],"flexible":[33],"in":[34,44],"order":[35],"handle":[37],"batch":[39],"matrices":[41],"which":[42],"differ":[43],"size,":[45],"nonzero":[46,49],"count,":[47],"and":[48,63],"distribution.":[50],"Furthermore,":[51],"they":[52],"support":[53],"three":[54],"most":[55],"commonly":[56],"used":[57],"storage":[59],"formats:":[60],"CSR,":[61],"COO":[62],"ELL.":[64],"Our":[65],"experimental":[66],"results":[67],"state-of-the-art":[70],"GPU":[71],"reveal":[72],"performance":[73],"improvements":[74],"up":[76],"25X":[78],"compared":[79],"non-batched":[81],"routines.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}