{"id":"https://openalex.org/W2023930909","doi":"https://doi.org/10.1145/2304576.2304624","title":"clSpMV","display_name":"clSpMV","publication_year":2012,"publication_date":"2012-06-25","ids":{"openalex":"https://openalex.org/W2023930909","doi":"https://doi.org/10.1145/2304576.2304624","mag":"2023930909"},"language":"en","primary_location":{"id":"doi:10.1145/2304576.2304624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Supercomputing","raw_type":"proceedings-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/A5028514073","display_name":"Bor-Yiing Su","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bor-Yiing Su","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028514073"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":11.6023,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":{"value":0.98941353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"364"},"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":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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/cuda","display_name":"CUDA","score":0.8334810733795166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8275463581085205},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7261689305305481},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7139197587966919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6619495153427124},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5535281300544739},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.49107861518859863},{"id":"https://openalex.org/keywords/matrix-free-methods","display_name":"Matrix-free methods","score":0.44999468326568604},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.44287461042404175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4334392547607422},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33010101318359375},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3201552629470825},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2165985405445099},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21321457624435425},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14561545848846436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08639618754386902}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8334810733795166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275463581085205},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7261689305305481},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7139197587966919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6619495153427124},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5535281300544739},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49107861518859863},{"id":"https://openalex.org/C54219892","wikidata":"https://www.wikidata.org/wiki/Q4080929","display_name":"Matrix-free methods","level":4,"score":0.44999468326568604},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.44287461042404175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4334392547607422},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33010101318359375},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3201552629470825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2165985405445099},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21321457624435425},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14561545848846436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08639618754386902},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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:10.1145/2304576.2304624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1588915715","https://openalex.org/W1906046253","https://openalex.org/W1990832096","https://openalex.org/W2002555321","https://openalex.org/W2035080386","https://openalex.org/W2038071684","https://openalex.org/W2099625934","https://openalex.org/W2111667319","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2132117096","https://openalex.org/W2144511445","https://openalex.org/W2165964351","https://openalex.org/W2167868137","https://openalex.org/W2518567779","https://openalex.org/W4239881334"],"related_works":["https://openalex.org/W2076165488","https://openalex.org/W2011159963","https://openalex.org/W1981557297","https://openalex.org/W2144511445","https://openalex.org/W2108540054","https://openalex.org/W2023019000","https://openalex.org/W2529540995","https://openalex.org/W2791204867","https://openalex.org/W2023930909","https://openalex.org/W1997614470"],"abstract_inverted_index":{"Sparse":[0],"matrix":[1,77,92],"vector":[2],"multiplication":[3],"(SpMV)":[4],"kernel":[5,33,64],"is":[6,105],"a":[7,43,51,74],"key":[8],"computation":[9],"in":[10,34,191,206],"linear":[11,36],"algebra.":[12,37],"Most":[13],"iterative":[14],"methods":[15],"are":[16,58,132,146],"composed":[17],"of":[18,41,54,85,88,111,121,162,185,202],"SpMV":[19,32,63],"operations":[20],"with":[21],"BLAS1":[22],"updates.":[23],"Therefore,":[24],"researchers":[25],"make":[26],"extensive":[27],"efforts":[28],"to":[29,60,82,107,143,148,179,198],"optimize":[30,61],"the":[31,39,62,79,86,96,101,118,122,159,163,180,186,199],"sparse":[35,76,91,112,124,165,189,204],"With":[38],"appearance":[40],"OpenCL,":[42],"programming":[44,49],"language":[45],"that":[46,104,131,145,155],"standardizes":[47],"parallel":[48],"across":[50,134],"wide":[52],"variety":[53],"heterogeneous":[55],"platforms,":[56,150,172],"we":[57,72,99],"able":[59,106],"on":[65,95,126,167],"many":[66,89],"different":[67,90,127],"platforms.":[68,128],"In":[69],"this":[70],"paper,":[71],"propose":[73],"new":[75],"format,":[78],"Cocktail":[80,97],"Format,":[81,98],"take":[83],"advantage":[84],"strengths":[87],"formats.":[93],"Based":[94],"develop":[100],"clSpMV":[102,156],"framework":[103],"analyze":[108],"all":[109,203],"kinds":[110],"matrices":[113,125,166],"at":[114],"runtime,":[115],"and":[116,170,173,193],"recommend":[117],"best":[119,160],"representations":[120,161],"given":[123],"Although":[129],"solutions":[130,144],"portable":[133],"diverse":[135],"platforms":[136],"generally":[137],"provide":[138],"lower":[139],"performance":[140,177,196],"when":[141],"compared":[142,178,197],"specialized":[147],"particular":[149],"our":[151],"experimental":[152],"results":[153],"show":[154],"can":[157],"find":[158],"input":[164],"both":[168],"Nvidia":[169],"AMD":[171],"deliver":[174],"83%":[175],"higher":[176,195],"vendor":[181],"optimized":[182],"CUDA":[183,200],"implementation":[184],"proposed":[187],"hybrid":[188],"format":[190],"[3],":[192],"63.6%":[194],"implementations":[201],"formats":[205],"[3].":[207]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}