{"id":"https://openalex.org/W3110597019","doi":"https://doi.org/10.1109/tpds.2020.3040150","title":"Adaptive SpMV/SpMSpV on GPUs for Input Vectors of Varied Sparsity","display_name":"Adaptive SpMV/SpMSpV on GPUs for Input Vectors of Varied Sparsity","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3110597019","doi":"https://doi.org/10.1109/tpds.2020.3040150","mag":"3110597019"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3040150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3040150","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5101590950","display_name":"Min Li","orcid":"https://orcid.org/0000-0001-9329-1086"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"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"]},{"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":"Min Li","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Software, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Software, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001005409","display_name":"Yulong Ao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Ao","raw_affiliation_strings":["School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101590950"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.5414,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89924506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9919999837875366,"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":0.8813629150390625},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7897164821624756},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6735486388206482},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6409732103347778},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6166939735412598},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5609912276268005},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5327674746513367},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4666813313961029},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09144353866577148},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.08180579543113708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06441670656204224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813629150390625},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7897164821624756},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6735486388206482},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6409732103347778},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6166939735412598},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5609912276268005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5327674746513367},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4666813313961029},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09144353866577148},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.08180579543113708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06441670656204224},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.3040150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3040150","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2658562473","display_name":null,"funder_award_id":"JQ18001","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W317340121","https://openalex.org/W1506342804","https://openalex.org/W1588915715","https://openalex.org/W1783256592","https://openalex.org/W1893178273","https://openalex.org/W1971367716","https://openalex.org/W1987840949","https://openalex.org/W2003117296","https://openalex.org/W2009654791","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2082238959","https://openalex.org/W2084296319","https://openalex.org/W2087507944","https://openalex.org/W2088866486","https://openalex.org/W2101234009","https://openalex.org/W2111667319","https://openalex.org/W2114977680","https://openalex.org/W2126004407","https://openalex.org/W2128853364","https://openalex.org/W2136324023","https://openalex.org/W2139882553","https://openalex.org/W2141380216","https://openalex.org/W2144085134","https://openalex.org/W2147370410","https://openalex.org/W2153635508","https://openalex.org/W2154111453","https://openalex.org/W2274716813","https://openalex.org/W2284629249","https://openalex.org/W2479693678","https://openalex.org/W2518567779","https://openalex.org/W2521497392","https://openalex.org/W2542072367","https://openalex.org/W2558367073","https://openalex.org/W2560815304","https://openalex.org/W2617403939","https://openalex.org/W2788264912","https://openalex.org/W2791012218","https://openalex.org/W2885436857","https://openalex.org/W2887822915","https://openalex.org/W2887930195","https://openalex.org/W2891325938","https://openalex.org/W2952598959","https://openalex.org/W2953657981","https://openalex.org/W2962812689","https://openalex.org/W2964301839","https://openalex.org/W3013652274","https://openalex.org/W3015089394","https://openalex.org/W3072519247","https://openalex.org/W4235600583","https://openalex.org/W4238995617","https://openalex.org/W6675354045","https://openalex.org/W6748643619","https://openalex.org/W6765240346","https://openalex.org/W6781957646"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W2076165488","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2138537133"],"abstract_inverted_index":{"Despite":[0],"numerous":[1],"efforts":[2],"for":[3,93],"optimizing":[4],"the":[5,50,59,87,100,125,147,152,156,169,175],"performance":[6,130],"of":[7,40,54,62,154],"Sparse":[8,26,29],"Matrix":[9,27],"and":[10,28,56,67,97,115,149,158,163,186],"Vector":[11,30],"Multiplication":[12,31],"(SpMV)":[13],"on":[14,49,91,103,106,138,181],"modern":[15],"hardware":[16,159],"architectures,":[17],"few":[18],"works":[19],"are":[20,122],"done":[21],"to":[22,34,127,145],"its":[23],"sparse":[24,95],"counterpart,":[25],"(SpMSpV),":[32],"not":[33,72],"mention":[35],"dealing":[36],"with":[37,151],"input":[38,157],"vectors":[39],"varied":[41],"sparsity.":[42],"The":[43],"key":[44,107],"challenge":[45],"is":[46,143],"that":[47,168],"depending":[48],"sparsity":[51],"levels,":[52],"distribution":[53,114],"data,":[55],"compute":[57],"platform,":[58],"optimal":[60],"choice":[61,70],"SpMV/SpMSpV":[63,81,89,120],"kernel":[64,90,141,148],"can":[65,84,172],"vary,":[66],"a":[68,132],"static":[69],"does":[71],"suffice.":[73],"In":[74],"this":[75],"article,":[76],"we":[77],"propose":[78],"an":[79],"adaptive":[80,170],"framework,":[82],"which":[83],"automatically":[85],"select":[86],"appropriate":[88],"GPUs":[92],"any":[94],"matrix":[96],"vector":[98],"at":[99],"runtime.":[101],"Based":[102],"systematic":[104],"analysis":[105],"factors":[108],"such":[109],"as":[110],"computing":[111],"pattern,":[112],"workload":[113],"write-back":[116],"strategy,":[117],"eight":[118],"candidate":[119],"kernels":[121],"encapsulated":[123],"into":[124],"framework":[126,171],"achieve":[128],"high":[129],"in":[131,178],"seamless":[133],"manner.":[134],"A":[135],"comprehensive":[136],"study":[137],"machine":[139],"learning-based":[140],"selector":[142],"performed":[144],"choose":[146],"adapt":[150],"varieties":[153],"both":[155,161],"from":[160],"accuracy":[162],"overhead":[164],"perspectives.":[165],"Experiments":[166],"demonstrate":[167],"substantially":[173],"outperform":[174],"previous":[176],"state-of-the-art":[177],"real-world":[179],"applications":[180],"NVIDIA":[182],"Tesla":[183],"K40m,":[184],"P100,":[185],"V100":[187],"GPUs.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}