{"id":"https://openalex.org/W2886632348","doi":"https://doi.org/10.1145/3218823","title":"Design and Implementation of Adaptive SpMV Library for Multicore and Many-Core Architecture","display_name":"Design and Implementation of Adaptive SpMV Library for Multicore and Many-Core Architecture","publication_year":2018,"publication_date":"2018-08-09","ids":{"openalex":"https://openalex.org/W2886632348","doi":"https://doi.org/10.1145/3218823","mag":"2886632348"},"language":"en","primary_location":{"id":"doi:10.1145/3218823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3218823","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","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/A5104072170","display_name":"Guangming Tan","orcid":null},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101402440","display_name":"Junhong Liu","orcid":"https://orcid.org/0000-0001-7596-7011"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Liu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454305","display_name":"Jiajia Li","orcid":"https://orcid.org/0000-0003-1270-4147"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajia Li","raw_affiliation_strings":["Computational Science and Engineering, Georgia Institute of Technology, North Avenue, Atlanta, GA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science and Engineering, Georgia Institute of Technology, North Avenue, Atlanta, GA, US","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1505,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95459499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"44","issue":"4","first_page":"1","last_page":"25"},"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":0.9990000128746033,"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/x86","display_name":"x86","score":0.8751769065856934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582158088684082},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.8467029333114624},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7103328704833984},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6134853363037109},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6132844686508179},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5700737833976746},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5622283816337585},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.4162767827510834},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4162186086177826},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36515265703201294},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2120245099067688},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14403441548347473}],"concepts":[{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.8751769065856934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582158088684082},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8467029333114624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7103328704833984},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6134853363037109},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6132844686508179},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5700737833976746},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5622283816337585},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.4162767827510834},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4162186086177826},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36515265703201294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2120245099067688},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14403441548347473},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3218823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3218823","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5855638324","display_name":null,"funder_award_id":"61521092, 91430218, 31327901, 61472395, and 61432018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W26990288","https://openalex.org/W52481882","https://openalex.org/W90568776","https://openalex.org/W1525132831","https://openalex.org/W1588915715","https://openalex.org/W1884140786","https://openalex.org/W1961194538","https://openalex.org/W1973542104","https://openalex.org/W1980081612","https://openalex.org/W1987840949","https://openalex.org/W2000873501","https://openalex.org/W2003117296","https://openalex.org/W2004642969","https://openalex.org/W2009654791","https://openalex.org/W2022916138","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2065339245","https://openalex.org/W2066636486","https://openalex.org/W2091883426","https://openalex.org/W2095836023","https://openalex.org/W2099059741","https://openalex.org/W2099625934","https://openalex.org/W2100452915","https://openalex.org/W2100738695","https://openalex.org/W2101511474","https://openalex.org/W2102182691","https://openalex.org/W2103877122","https://openalex.org/W2111667319","https://openalex.org/W2113921339","https://openalex.org/W2115052535","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/W2162283062","https://openalex.org/W2168931017","https://openalex.org/W2169492033","https://openalex.org/W2259574154","https://openalex.org/W2276719940","https://openalex.org/W2339718050","https://openalex.org/W2415007423","https://openalex.org/W2418287910","https://openalex.org/W2518567779","https://openalex.org/W2570841452","https://openalex.org/W2620106252","https://openalex.org/W2730999914","https://openalex.org/W2731053425","https://openalex.org/W2741907101","https://openalex.org/W2786159829","https://openalex.org/W2788264912","https://openalex.org/W2789228469","https://openalex.org/W2791012218","https://openalex.org/W2891832717","https://openalex.org/W3125710003","https://openalex.org/W4234290723","https://openalex.org/W4243261006","https://openalex.org/W4243966422","https://openalex.org/W4254473027"],"related_works":["https://openalex.org/W2740999212","https://openalex.org/W2188971969","https://openalex.org/W1994052277","https://openalex.org/W2769399951","https://openalex.org/W2024554511","https://openalex.org/W2588843388","https://openalex.org/W3042238487","https://openalex.org/W2885985254","https://openalex.org/W2599563411","https://openalex.org/W2841806531"],"abstract_inverted_index":{"Sparse":[0],"matrix":[1,70,85,113],"vector":[2],"multiplication":[3],"(SpMV)":[4],"is":[5],"an":[6,42,176],"important":[7],"computational":[8],"kernel":[9],"in":[10,34,110,175],"traditional":[11],"high-performance":[12],"computing":[13],"and":[14,53,78,93,149,184],"emerging":[15],"data-intensive":[16],"applications.":[17,36],"Previous":[18],"SpMV":[19],"libraries":[20],"are":[21,105],"optimized":[22],"by":[23,72,163],"either":[24],"application-specific":[25],"or":[26],"architecture-specific":[27],"approaches":[28],"but":[29],"present":[30],"difficulties":[31],"for":[32,81],"use":[33],"real":[35],"In":[37],"this":[38],"work,":[39],"we":[40],"develop":[41],"auto-tuning":[43],"system":[44],"(SMATER)":[45],"to":[46,97,124],"bridge":[47],"the":[48,64,75,100,111,129,156,181],"gap":[49],"between":[50],"specific":[51],"optimizations":[52],"general-purpose":[54],"use.":[55],"SMATER":[56,88,119,160],"provides":[57],"programmers":[58],"a":[59,90],"unified":[60],"interface":[61],"based":[62],"on":[63,135,142,168],"compressed":[65],"sparse":[66,69,84],"row":[67],"(CSR)":[68],"format":[71,77],"implicitly":[73],"choosing":[74],"best":[76],"fastest":[79],"implementation":[80],"any":[82],"input":[83],"during":[86],"runtime.":[87],"leverages":[89],"machine-learning":[91],"model":[92],"retargetable":[94],"back-end":[95],"library":[96,183],"quickly":[98],"predict":[99],"optimal":[101],"combination.":[102],"Performance":[103],"parameters":[104],"extracted":[106],"from":[107,180],"2,386":[108],"matrices":[109],"SuiteSparse":[112],"collection.":[114],"The":[115],"experiments":[116],"show":[117],"that":[118,127],"achieves":[120],"good":[121],"performance":[122,189],"(up":[123],"10":[125],"times":[126,167],"of":[128],"Intel":[130,136,150,157],"Math":[131],"Kernel":[132],"Library":[133],"(MKL)":[134],"E5-2680":[137],"v3)":[138],"while":[139],"being":[140],"portable":[141],"state-of-the-art":[143],"x86":[144],"multicore":[145],"processors,":[146],"NVIDIA":[147],"GPUs,":[148],"Xeon":[151],"Phi":[152],"accelerators.":[153],"Compared":[154],"with":[155],"MKL":[158],"library,":[159],"runs":[161],"faster":[162],"more":[164],"than":[165,187],"2.5":[166],"average.":[169],"We":[170],"further":[171],"demonstrate":[172],"its":[173],"adaptivity":[174],"algebraic":[177],"multigrid":[178],"solver":[179],"Hypre":[182],"report":[185],"greater":[186],"20%":[188],"improvement.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}