{"id":"https://openalex.org/W2003117296","doi":"https://doi.org/10.1145/2491956.2462181","title":"SMAT","display_name":"SMAT","publication_year":2013,"publication_date":"2013-06-11","ids":{"openalex":"https://openalex.org/W2003117296","doi":"https://doi.org/10.1145/2491956.2462181","mag":"2003117296"},"language":"en","primary_location":{"id":"doi:10.1145/2491956.2462181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491956.2462181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation","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/A5100454305","display_name":"Jiajia Li","orcid":"https://orcid.org/0000-0003-1270-4147"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajia Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104072170","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645579","display_name":"Mingyu Chen","orcid":"https://orcid.org/0000-0003-4469-1037"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Chen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738014","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-4179-2660"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100454305"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":4.8632,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.94970902,"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":"117","last_page":"126"},"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":0.9968000054359436,"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":0.9955000281333923,"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":0.8039765357971191},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.7793381214141846},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7266463041305542},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6658825874328613},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5053289532661438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4903554916381836},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.47892388701438904},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4252268970012665},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10693362355232239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039765357971191},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7793381214141846},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7266463041305542},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6658825874328613},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5053289532661438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4903554916381836},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.47892388701438904},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4252268970012665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10693362355232239},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1145/2491956.2462181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491956.2462181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W26990288","https://openalex.org/W52481882","https://openalex.org/W90568776","https://openalex.org/W1525132831","https://openalex.org/W1617107202","https://openalex.org/W1884140786","https://openalex.org/W1961194538","https://openalex.org/W1980081612","https://openalex.org/W1990832096","https://openalex.org/W2000873501","https://openalex.org/W2022916138","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2065339245","https://openalex.org/W2066636486","https://openalex.org/W2095836023","https://openalex.org/W2099059741","https://openalex.org/W2099625934","https://openalex.org/W2100452915","https://openalex.org/W2100738695","https://openalex.org/W2102182691","https://openalex.org/W2103877122","https://openalex.org/W2111667319","https://openalex.org/W2113921339","https://openalex.org/W2124007994","https://openalex.org/W2128539477","https://openalex.org/W2130289795","https://openalex.org/W2130304700","https://openalex.org/W2132117096","https://openalex.org/W2135653967","https://openalex.org/W2136324023","https://openalex.org/W2136952590","https://openalex.org/W2154590891","https://openalex.org/W2169492033","https://openalex.org/W6659374036"],"related_works":["https://openalex.org/W3215381467","https://openalex.org/W2915956107","https://openalex.org/W4301207796","https://openalex.org/W4846490","https://openalex.org/W2099986681","https://openalex.org/W4240878335","https://openalex.org/W2138537133","https://openalex.org/W4321636545","https://openalex.org/W4247995867","https://openalex.org/W2023476765"],"abstract_inverted_index":{"Sparse":[0,50],"Matrix":[1],"Vector":[2],"multiplication":[3,52],"(SpMV)":[4],"is":[5,104],"an":[6,107,183],"important":[7],"kernel":[8],"in":[9,41,74,106,153,157,182],"both":[10,166],"traditional":[11],"high":[12],"performance":[13,148,193],"computing":[14],"and":[15,63,80,86,155],"emerging":[16],"data-intensive":[17],"applications.":[18,43],"By":[19],"far,":[20],"SpMV":[21],"libraries":[22,33],"are":[23,165],"optimized":[24],"by":[25,110],"either":[26],"application-specific":[27],"or":[28],"architecture-specific":[29],"approaches,":[30],"making":[31],"the":[32,58,83,125,133,137,173],"become":[34],"too":[35],"complicated":[36],"to":[37,56,130,151],"be":[38],"used":[39],"extensively":[40],"real":[42],"In":[44],"this":[45,96],"work":[46],"we":[47],"develop":[48],"a":[49,70,100,111,116],"Matrix-vector":[51],"Auto-Tuning":[53],"system":[54],"(SMAT)":[55],"bridge":[57],"gap":[59],"between":[60],"specific":[61],"optimizations":[62],"general-purpose":[64],"usage.":[65],"SMAT":[66,98,145],"provides":[67],"users":[68],"with":[69,115,190],"unified":[71],"programming":[72],"interface":[73],"compressed":[75],"sparse":[76,91,127],"row":[77],"(CSR)":[78],"format":[79,85],"automatically":[81],"determines":[82],"optimal":[84],"implementation":[87],"for":[88],"any":[89],"input":[90],"matrix":[92,128,138],"at":[93],"runtime.":[94],"For":[95],"purpose,":[97],"leverages":[99],"learning":[101,113],"model,":[102],"which":[103,164],"generated":[105],"off-line":[108],"stage":[109],"machine":[112],"method":[114],"training":[117],"set":[118],"of":[119,136,149],"more":[120,167],"than":[121,168,172],"2000":[122],"matrices":[123],"from":[124,187],"UF":[126],"collection,":[129],"quickly":[131],"predict":[132],"best":[134],"combination":[135],"feature":[139],"parameters.":[140],"Our":[141],"experiments":[142],"show":[143],"that":[144],"achieves":[146],"impressive":[147],"up":[150],"51GFLOPS":[152],"single-precision":[154],"37GFLOPS":[156],"double-precision":[158],"on":[159],"mainstream":[160],"x86":[161],"multi-core":[162],"processors,":[163],"3":[169],"times":[170],"faster":[171],"Intel":[174],"MKL":[175],"library.":[176],"We":[177],"also":[178],"demonstrate":[179],"its":[180],"adaptability":[181],"algebraic":[184],"multigrid":[185],"solver":[186],"Hypre":[188],"library":[189],"above":[191],"20%":[192],"improvement":[194],"reported.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2016-06-24T00:00:00"}
