{"id":"https://openalex.org/W2034258707","doi":"https://doi.org/10.1177/1094342013501126","title":"Optimization of quasi-diagonal matrix\u2013vector multiplication on GPU","display_name":"Optimization of quasi-diagonal matrix\u2013vector multiplication on GPU","publication_year":2013,"publication_date":"2013-09-02","ids":{"openalex":"https://openalex.org/W2034258707","doi":"https://doi.org/10.1177/1094342013501126","mag":"2034258707"},"language":"en","primary_location":{"id":"doi:10.1177/1094342013501126","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013501126","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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"]},{"id":"https://openalex.org/I39521962","display_name":"Hunan City University","ror":"https://ror.org/01vd7vb53","country_code":"CN","type":"education","lineage":["https://openalex.org/I39521962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China","National Supercomputing Centre in Changsha, China","School of Information Science and Engineering, Hunan City University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Centre in Changsha, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Hunan City University, China","institution_ids":["https://openalex.org/I39521962"]}]},{"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/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I39521962","display_name":"Hunan City University","ror":"https://ror.org/01vd7vb53","country_code":"CN","type":"education","lineage":["https://openalex.org/I39521962"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China","National Supercomputing Centre in Changsha, China","School of Information Science and Engineering, Hunan City University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Centre in Changsha, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Hunan City University, China","institution_ids":["https://openalex.org/I39521962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008561380","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-1849-6991"},"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":"Yan Liu","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758136","display_name":"Lin Shi","orcid":"https://orcid.org/0009-0008-1878-9528"},"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":"Lin Shi","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China","National Supercomputing Centre in Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Centre in Changsha, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032952145","display_name":"Lanjun Wan","orcid":"https://orcid.org/0000-0001-7236-3589"},"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":"Lanjun Wan","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China","National Supercomputing Centre in Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Supercomputing Centre in Changsha, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078793726"],"corresponding_institution_ids":["https://openalex.org/I16609230","https://openalex.org/I39521962"],"apc_list":null,"apc_paid":null,"fwci":4.1425,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9347503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"28","issue":"2","first_page":"183","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9983000159263611,"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/diagonal","display_name":"Diagonal","score":0.761297345161438},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7245645523071289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7066939473152161},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6978506445884705},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6310082674026489},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6071453094482422},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5637509226799011},{"id":"https://openalex.org/keywords/diagonal-matrix","display_name":"Diagonal matrix","score":0.5482542514801025},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5139224529266357},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5066004991531372},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4574614465236664},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44363313913345337},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4412393867969513},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3353976309299469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20398196578025818},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1265624463558197},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08787932991981506},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.07665503025054932}],"concepts":[{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.761297345161438},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7245645523071289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7066939473152161},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6978506445884705},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6310082674026489},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6071453094482422},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5637509226799011},{"id":"https://openalex.org/C113313756","wikidata":"https://www.wikidata.org/wiki/Q332791","display_name":"Diagonal matrix","level":3,"score":0.5482542514801025},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5139224529266357},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5066004991531372},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4574614465236664},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44363313913345337},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4412393867969513},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3353976309299469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20398196578025818},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1265624463558197},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08787932991981506},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.07665503025054932},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342013501126","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013501126","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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":24,"referenced_works":["https://openalex.org/W1523532434","https://openalex.org/W1555620806","https://openalex.org/W1588915715","https://openalex.org/W1816932979","https://openalex.org/W1841716671","https://openalex.org/W1857970128","https://openalex.org/W1980714869","https://openalex.org/W1985938427","https://openalex.org/W2023019000","https://openalex.org/W2027718011","https://openalex.org/W2038071684","https://openalex.org/W2095836023","https://openalex.org/W2104509996","https://openalex.org/W2107625757","https://openalex.org/W2108343462","https://openalex.org/W2109711595","https://openalex.org/W2120768584","https://openalex.org/W2128539477","https://openalex.org/W2143098136","https://openalex.org/W2145018926","https://openalex.org/W2148570406","https://openalex.org/W2183317050","https://openalex.org/W2518567779","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2503137108","https://openalex.org/W2119534391","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2062253548","https://openalex.org/W2393490604","https://openalex.org/W2393707426","https://openalex.org/W3203633922","https://openalex.org/W2765743988","https://openalex.org/W2146871484"],"abstract_inverted_index":{"Sparse":[0],"matrix\u2013vector":[1,51],"multiplication":[2,52],"(SpMV)":[3],"is":[4,13,58,197],"of":[5,46,102,115,135,144,157,166,195,201,222],"singular":[6],"importance":[7],"in":[8,17,73,137,146,188,240],"sparse":[9,49,55,123,167],"linear":[10],"algebra,":[11],"which":[12,131],"an":[14],"important":[15],"issue":[16],"scientific":[18],"computing":[19],"and":[20,31,66,81,120,141,179,181,235],"engineering":[21],"practice.":[22],"Much":[23],"effort":[24],"has":[25,70],"been":[26,37,71],"put":[27],"into":[28],"accelerating":[29],"SpMV,":[30,47],"a":[32,43,113,173,189,226,231,236],"few":[33],"parallel":[34,100],"solutions":[35],"have":[36],"proposed.":[38],"This":[39,76],"paper":[40,77],"focuses":[41],"on":[42,89],"special":[44],"type":[45],"namely":[48],"quasi-diagonal":[50,56],"(SQDMV).":[53],"The":[54],"matrix":[57],"the":[59,90,98,103,116,121,133,142,154,158,183,193,212,219,241],"key":[60],"to":[61,160,162,171,224,229],"solving":[62],"many":[63],"differential":[64],"equations,":[65],"very":[67],"little":[68],"research":[69],"done":[72],"this":[74],"field.":[75],"discusses":[78],"data":[79],"structures":[80],"algorithms":[82],"for":[83,97,205],"SQDMV":[84],"that":[85,192,200],"are":[86],"efficiently":[87],"implemented":[88],"compute":[91],"unified":[92,227],"device":[93],"architecture":[94,101],"(CUDA)":[95],"platform":[96],"fine-grained":[99],"graphics":[104],"processing":[105],"unit":[106],"(GPU).":[107],"A":[108],"new":[109],"diagonal":[110,117,159],"storage":[111,155],"format,":[112],"hybrid":[114],"format":[118,125],"(DLA)":[119],"compressed":[122],"row":[124],"(CSR)":[126],"(HDC)":[127],"will":[128],"be":[129],"presented,":[130],"overcomes":[132],"inefficiency":[134],"DLA":[136,178],"storing":[138,147],"irregular":[139],"matrices":[140,206],"imbalances":[143],"CSR":[145],"non-zero":[148],"elements.":[149],"Furthermore,":[150],"HDC":[151,196,223],"can":[152],"adjust":[153],"bandwidth":[156],"adapt":[161],"different":[163,220],"discrete":[164,209],"degrees":[165],"matrix,":[168],"so":[169],"as":[170],"get":[172,230],"higher":[174,237],"compression":[175,233],"ratio":[176,234,239],"than":[177,199],"CSR,":[180],"reduce":[182],"computational":[184],"complexity.":[185],"Our":[186],"implementation":[187],"GPU":[190],"shows":[191],"performance":[194],"better":[198,232],"other":[202],"formats,":[203],"especially":[204],"with":[207],"some":[208],"points":[210],"outside":[211],"main":[213],"diagonal.":[214],"In":[215],"addition,":[216],"we":[217],"combine":[218],"parts":[221],"make":[225],"kernel":[228],"speedup":[238],"GPU.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}