{"id":"https://openalex.org/W2025890876","doi":"https://doi.org/10.1109/tc.2014.2366731","title":"Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs","display_name":"Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs","publication_year":2014,"publication_date":"2014-11-24","ids":{"openalex":"https://openalex.org/W2025890876","doi":"https://doi.org/10.1109/tc.2014.2366731","mag":"2025890876"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2014.2366731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2014.2366731","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","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/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, Hunan, China","National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]},{"author_position":"middle","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, China","College of Information Science and Engineering, Hunan University, Hunan, China","Department of Computer Science, State University of New York, New Paltz, NY, USA","National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY, USA","institution_ids":["https://openalex.org/I157455823"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054583215","display_name":"Zeyao Mo","orcid":"https://orcid.org/0000-0003-3280-5682"},"institutions":[{"id":"https://openalex.org/I4210145278","display_name":"Institute of Applied Physics and Computational Mathematics","ror":"https://ror.org/03sxpbt26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyao Mo","raw_affiliation_strings":["Institute of Applied Physics and Computational Mathematics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Physics and Computational Mathematics, Beijing, China","institution_ids":["https://openalex.org/I4210145278"]}]},{"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/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, China","College of Information Science and Engineering, Hunan University, Hunan, China","Department of Computer Science, State University of New York, New Paltz, NY, USA","National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY, USA","institution_ids":["https://openalex.org/I157455823"]},{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8406,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.98714019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"64","issue":"9","first_page":"2623","last_page":"2636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13924","display_name":"Internet of Things and Social Network Interactions","score":0.975600004196167,"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"}},"topics":[{"id":"https://openalex.org/T13924","display_name":"Internet of Things and Social Network Interactions","score":0.975600004196167,"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":0.9742000102996826,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9545000195503235,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/parallel-computing","display_name":"Parallel computing","score":0.8162574172019958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901124954223633},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7691049575805664},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6024531126022339},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.5217838287353516},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5165042281150818},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5147619247436523},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.45081597566604614},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4242018759250641},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1494312286376953}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8162574172019958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901124954223633},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7691049575805664},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6024531126022339},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5217838287353516},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5165042281150818},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5147619247436523},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.45081597566604614},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4242018759250641},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1494312286376953},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2014.2366731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2014.2366731","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G2243909624","display_name":null,"funder_award_id":"61133005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2707076737","display_name":null,"funder_award_id":"61432005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G662528876","display_name":null,"funder_award_id":"61472124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6925281636","display_name":"\u5f02\u6784\u5e76\u884c\u73af\u5883\u4e0b\u7684MapReduce\u8d44\u6e90\u8c03\u5ea6\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61370095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1588915715","https://openalex.org/W1857970128","https://openalex.org/W1974288188","https://openalex.org/W1981557297","https://openalex.org/W1983797753","https://openalex.org/W2001990291","https://openalex.org/W2017533742","https://openalex.org/W2025003325","https://openalex.org/W2027718011","https://openalex.org/W2028045344","https://openalex.org/W2034258707","https://openalex.org/W2035080386","https://openalex.org/W2038071684","https://openalex.org/W2043105874","https://openalex.org/W2056882228","https://openalex.org/W2059710204","https://openalex.org/W2072806558","https://openalex.org/W2081874478","https://openalex.org/W2082238959","https://openalex.org/W2089908605","https://openalex.org/W2095292158","https://openalex.org/W2103600672","https://openalex.org/W2103877122","https://openalex.org/W2111667319","https://openalex.org/W2113300255","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2148570406","https://openalex.org/W2154118576","https://openalex.org/W2158961033","https://openalex.org/W2159481344","https://openalex.org/W2164904521","https://openalex.org/W2169999287","https://openalex.org/W2399991609","https://openalex.org/W2518567779","https://openalex.org/W2797111759","https://openalex.org/W2997945685","https://openalex.org/W3000120212","https://openalex.org/W3099744258","https://openalex.org/W4300907844","https://openalex.org/W6676508306","https://openalex.org/W6683672642"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2030992542","https://openalex.org/W2955328870","https://openalex.org/W2166713816","https://openalex.org/W52131579","https://openalex.org/W2794469028","https://openalex.org/W1996843728"],"abstract_inverted_index":{"This":[0,19],"paper":[1],"presents":[2],"a":[3,62,83,97,132,146,166,205,208,223,244,262],"sparse":[4,28,42,63,87,167],"matrix":[5,168,206],"partitioning":[6,47,84,151,253],"strategy":[7,85,152],"to":[8,39,115,194,249],"improve":[9],"the":[10,55,76,106,123,158,197,202,213,218,225,252,257],"performance":[11,159,179,227],"of":[12,27,58,71,86,93,119,126,160,181,196,204,217,220,229,243,251,261],"SpMV":[13,139,161,185,233],"on":[14,90,140,190,212,238,256],"GPUs":[15,141,239],"and":[16,30,65,142,157,240],"multicore":[17,143,191,241],"CPUs.":[18],"method":[20,48,104],"has":[21,105,153],"wide":[22],"adaptability":[23],"for":[24,138,184,232],"different":[25,32],"types":[26],"matrices,":[29],"is":[31,162,169,186,234],"from":[33,122],"existing":[34],"methods":[35,254],"which":[36],"only":[37],"adapt":[38],"some":[40],"particular":[41],"matrices.":[43],"In":[44],"addition,":[45],"our":[46,103,175,182,230],"can":[49],"obtain":[50],"dense":[51,172],"blocks":[52,173],"by":[53],"analyzing":[54],"probability":[56,214],"distribution":[57,156],"non-zero":[59,94],"elements":[60,95],"in":[61,67,96,145,207,222],"matrix,":[64],"result":[66],"very":[68],"low":[69],"proportion":[70],"zero":[72],"padded.":[73],"We":[74,81,100,130],"make":[75],"following":[77],"significant":[78],"contributions.":[79],"(1)":[80],"present":[82],"matrices":[88],"based":[89,211,255],"probabilistic":[91],"modeling":[92],"row.":[98],"(2)":[99],"prove":[101],"that":[102,195,250],"highest":[107],"mean":[108],"density":[109],"compared":[110,193,248],"with":[111],"other":[112,198],"strategies":[113],"according":[114],"certain":[116],"given":[117],"ratios":[118],"partition":[120],"obtained":[121],"computing":[124,136,148,246],"powers":[125],"heterogeneous":[127,147,245],"processors.":[128],"(3)":[129],"develop":[131],"CPU-GPU":[133],"hybrid":[134],"parallel":[135],"model":[137],"CPUs":[144,242],"platform.":[149],"Our":[150],"balanced":[154],"load":[155],"significantly":[163],"improved":[164],"when":[165],"partitioned":[170],"into":[171],"using":[174],"method.":[176],"The":[177],"average":[178,226],"improvement":[180,228],"solution":[183,231],"about":[187,235],"15.75":[188],"percent":[189,237],"CPUs,":[192],"solutions.":[199],"By":[200],"considering":[201],"rows":[203],"unique":[209],"order":[210,260],"mass":[215],"function":[216],"number":[219],"non-zeros":[221],"row,":[224],"33.52":[236],"platform,":[247],"original":[258],"row":[259],"matrix.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}