{"id":"https://openalex.org/W2082238959","doi":"https://doi.org/10.1109/tpds.2014.2308221","title":"Performance Analysis and Optimization for SpMV on GPU Using Probabilistic Modeling","display_name":"Performance Analysis and Optimization for SpMV on GPU Using Probabilistic Modeling","publication_year":2014,"publication_date":"2014-02-25","ids":{"openalex":"https://openalex.org/W2082238959","doi":"https://doi.org/10.1109/tpds.2014.2308221","mag":"2082238959"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2308221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2308221","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/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I157455823","display_name":"SUNY New Paltz","ror":"https://ror.org/03j3dv688","country_code":"US","type":"education","lineage":["https://openalex.org/I157455823"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","Department of Computer Science, State University of New York, New Paltz, NY","National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","College of Information Science and Engineering,Hunan University,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY","institution_ids":["https://openalex.org/I157455823"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","institution_ids":[]},{"raw_affiliation_string":"College of Information Science and Engineering,Hunan University,Changsha,P.R. China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","College of Information Science and Engineering,Hunan University,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","institution_ids":[]},{"raw_affiliation_string":"College of Information Science and Engineering,Hunan University,Changsha,P.R. China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I157455823","display_name":"SUNY New Paltz","ror":"https://ror.org/03j3dv688","country_code":"US","type":"education","lineage":["https://openalex.org/I157455823"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Keqin Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","Department of Computer Science, State University of New York, New Paltz, NY","National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","Department of Computer Science, State University of New York, New Paltz,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY","institution_ids":["https://openalex.org/I157455823"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha Hunan, P.R. China","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz,","institution_ids":["https://openalex.org/I1327163397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.3124,"has_fulltext":false,"cited_by_count":224,"citation_normalized_percentile":{"value":0.99666436,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"26","issue":"1","first_page":"196","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.992900013923645,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8183774352073669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443951368331909},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5372197031974792},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4732763469219208},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4490151107311249},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4470241367816925},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4319138824939728},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4127305746078491},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41103076934814453},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16249513626098633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12114614248275757},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10962262749671936},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08210200071334839}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8183774352073669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443951368331909},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5372197031974792},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4732763469219208},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4490151107311249},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4470241367816925},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4319138824939728},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4127305746078491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41103076934814453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16249513626098633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12114614248275757},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10962262749671936},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08210200071334839},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2014.2308221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2308221","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W70618093","https://openalex.org/W1588915715","https://openalex.org/W1976184248","https://openalex.org/W1981557297","https://openalex.org/W1985938427","https://openalex.org/W1996843728","https://openalex.org/W2003117296","https://openalex.org/W2025003325","https://openalex.org/W2028045344","https://openalex.org/W2034258707","https://openalex.org/W2035080386","https://openalex.org/W2038071684","https://openalex.org/W2089908605","https://openalex.org/W2095836023","https://openalex.org/W2102994616","https://openalex.org/W2105545110","https://openalex.org/W2113282196","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2129343865","https://openalex.org/W2130289795","https://openalex.org/W2130336316","https://openalex.org/W2130561688","https://openalex.org/W2132117096","https://openalex.org/W2148542244","https://openalex.org/W2153492376","https://openalex.org/W2154118576","https://openalex.org/W2157456954","https://openalex.org/W2158592499","https://openalex.org/W2158961033","https://openalex.org/W2167334577","https://openalex.org/W2399991609","https://openalex.org/W2428307425","https://openalex.org/W2518567779","https://openalex.org/W2797111759","https://openalex.org/W2997945685","https://openalex.org/W4300907844","https://openalex.org/W6644363512","https://openalex.org/W6675569598","https://openalex.org/W6683672642"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W4384937382","https://openalex.org/W52131579","https://openalex.org/W2794469028","https://openalex.org/W1996843728"],"abstract_inverted_index":{"This":[0,18],"paper":[1],"presents":[2],"a":[3,74,86,99,243],"unique":[4],"method":[5,19,46],"of":[6,26,82,98,105,124,128,154,201,203,209,215,235,259,269,282],"performance":[7,127,188,192,257,267],"analysis":[8,195],"and":[9,29,109,118,135,164,194,207,228,242],"optimization":[10],"for":[11,23,95,145,189,213,251,273],"sparse":[12,27,41,87,100,219],"matrix-vector":[13],"multiplication":[14],"(SpMV)":[15],"on":[16,131,222],"GPU.":[17],"has":[20],"wide":[21],"adaptability":[22],"different":[24,31],"types":[25],"matrices":[28,220],"is":[30,246,262,275],"from":[32],"existing":[33],"methods":[34],"which":[35,56],"only":[36],"adapt":[37],"to":[38,52,76,151,184],"some":[39],"particular":[40],"matrices.":[42],"In":[43],"addition,":[44],"our":[45,260],"does":[47],"not":[48],"need":[49],"additional":[50],"benchmarks":[51],"get":[53],"optimized":[54],"parameters,":[55],"are":[57,196,230],"calculated":[58],"directly":[59],"through":[60,115,181],"the":[61,68,79,96,116,121,126,141,155,160,165,174,182,186,204,210,216,223,231,270,283],"probability":[62],"mass":[63],"function":[64],"(PMF).":[65],"We":[66,72],"make":[67],"following":[69],"contributions.":[70],"(1)":[71],"present":[73],"PMF":[75,90,183],"analyze":[77],"precisely":[78,114],"distribution":[80],"pattern":[81],"non-zero":[83],"elements":[84],"in":[85],"matrix.":[88,101],"The":[89,199,233,256,265],"can":[91,111,137,147,178],"provide":[92],"theoretical":[93,161],"basis":[94],"compression":[97],"(2)":[102],"Compression":[103],"efficiency":[104],"COO,":[106,132,226],"CSR,":[107,133,227],"ELL,":[108,134],"HYB":[110,136,274],"be":[112,138,148,179],"analyzed":[113],"PMF,":[117],"combined":[119],"with":[120,280],"hardware":[122],"parameters":[123],"GPU,":[125],"SpMV":[129,146],"based":[130,221],"estimated.":[139],"Furthermore,":[140],"most":[142],"appropriate":[143],"format":[144],"selected":[149],"according":[150],"estimated":[152,162,205,240],"value":[153,241,245],"performance.":[156],"Experiments":[157],"prove":[158],"that":[159,208,281],"values":[163,167],"tested":[166,211,218,244],"have":[168],"high":[169],"consistency.":[170],"(3)":[171],"For":[172],"HYB,":[173],"optimal":[175,187,271],"segmentation":[176],"threshold":[177],"found":[180],"achieve":[185],"SpMV.":[190],"Our":[191],"modeling":[193],"very":[197],"accurate.":[198],"order":[200],"magnitude":[202],"speedup":[206,212],"each":[214],"ten":[217],"three":[224],"formats":[225],"ELL":[229],"same.":[232],"percentage":[234],"relative":[236],"difference":[237],"between":[238],"an":[239],"less":[247],"than":[248],"20":[249],"percent":[250,254,278],"over":[252,276],"80":[253],"cases.":[255],"improvement":[258,268],"algorithm":[261],"also":[263],"effective.":[264],"average":[266],"solution":[272,285],"15":[277],"compared":[279],"automatic":[284],"provided":[286],"by":[287],"CUSPARSE":[288],"lib.":[289]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}