{"id":"https://openalex.org/W7124765019","doi":"https://doi.org/10.1002/cpe.70552","title":"<scp>GFSAI</scp> : An Adaptive Factorized Sparse Approximate Inverse Preconditioning Algorithm on <scp>GPU</scp>","display_name":"<scp>GFSAI</scp> : An Adaptive Factorized Sparse Approximate Inverse Preconditioning Algorithm on <scp>GPU</scp>","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124765019","doi":"https://doi.org/10.1002/cpe.70552"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.70552","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70552","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/cpe.70552","source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/cpe.70552","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yizhou Wang","orcid":"https://orcid.org/0009-0008-6168-5118"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Wang","raw_affiliation_strings":["Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China"],"raw_orcid":"https://orcid.org/0009-0008-6168-5118","affiliations":[{"raw_affiliation_string":"Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101449909","display_name":"Yige Zhang","orcid":"https://orcid.org/0000-0002-7719-6035"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yige Zhang","raw_affiliation_strings":["Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047780118","display_name":"Jiaquan Gao","orcid":"https://orcid.org/0000-0002-2983-9921"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaquan Gao","raw_affiliation_strings":["Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Lab for NSLSCS, School of Computer and Electronic Information Nanjing Normal University  Nanjing China","institution_ids":["https://openalex.org/I152031979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047780118"],"corresponding_institution_ids":["https://openalex.org/I152031979"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":{"value":4740,"currency":"USD","value_usd":4740},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1085326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.6873999834060669,"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":0.6873999834060669,"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/T12303","display_name":"Tensor decomposition and applications","score":0.10379999876022339,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.019300000742077827,"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/thread","display_name":"Thread (computing)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.45730000734329224},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4350000023841858},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4189999997615814},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.3716000020503998},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.3598000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226000070571899},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.45730000734329224},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4350000023841858},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C156891508","wikidata":"https://www.wikidata.org/wiki/Q1004114","display_name":"Bulk synchronous parallel","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2776003309","wikidata":"https://www.wikidata.org/wiki/Q1988072","display_name":"Adaptive algorithm","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/cpe.70552","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70552","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/cpe.70552","source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/cpe.70552","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70552","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/cpe.70552","source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2706846334","display_name":"\u9762\u5411\u5f02\u6784\u7cfb\u7edf\u7684\u53ef\u6269\u5c55\u7684\u8fed\u4ee3\u65b9\u6cd5\u5e76\u884c\u4f18\u5316\u6a21\u578b\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"61872422","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124765019.pdf","grobid_xml":"https://content.openalex.org/works/W7124765019.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1966756606","https://openalex.org/W1969255113","https://openalex.org/W1986652366","https://openalex.org/W1994805693","https://openalex.org/W1998388190","https://openalex.org/W2018215034","https://openalex.org/W2026502086","https://openalex.org/W2035080386","https://openalex.org/W2045633650","https://openalex.org/W2083640533","https://openalex.org/W2089099677","https://openalex.org/W2095258827","https://openalex.org/W2129343865","https://openalex.org/W2140153041","https://openalex.org/W2155216327","https://openalex.org/W2271597431","https://openalex.org/W2444544770","https://openalex.org/W2520865709","https://openalex.org/W2544527082","https://openalex.org/W2617808919","https://openalex.org/W2801644589","https://openalex.org/W2921480401","https://openalex.org/W2944108582","https://openalex.org/W2993109347","https://openalex.org/W2995489632","https://openalex.org/W3100838950","https://openalex.org/W3161385399","https://openalex.org/W4321222463"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"The":[1],"factorized":[2],"sparse":[3],"approximate":[4],"inverse":[5],"(FSAI)":[6],"preconditioner":[7],"has":[8,38],"been":[9],"proven":[10],"to":[11,22,73,76,99,121,163,178],"be":[12,128],"effective":[13,79,193],"in":[14,200],"accelerating":[15,31],"the":[16,23,28,44,101,124,134,165,201],"convergence":[17],"of":[18,26,46,118],"iterative":[19],"methods.":[20],"Due":[21],"high":[24],"cost":[25],"constructing":[27],"FSAI":[29,49,80,92,141,210],"preconditioner,":[30],"it":[32],"on":[33,52,83,95,133,183,213],"graphics":[34],"processing":[35],"unit":[36],"(GPU)":[37],"attracted":[39],"considerable":[40],"attention.":[41],"However,":[42],"despite":[43],"development":[45],"some":[47],"existing":[48],"preconditioning":[50,81,93,198,211],"algorithms":[51],"GPU,":[53,96],"their":[54],"performance":[55],"will":[56],"significantly":[57],"decrease":[58],"when":[59],"they":[60],"encounter":[61],"matrix":[62],"types":[63,117,181],"that":[64,123,174,188],"are":[65,112,147],"not":[66,176],"suitable":[67],"for":[68,114,172],"them.":[69],"This":[70],"motivates":[71],"us":[72],"investigate":[74],"how":[75],"design":[77],"an":[78,90],"algorithm":[82,94,199,212],"GPU.":[84,214],"In":[85,104],"this":[86],"paper,":[87],"we":[88,150],"propose":[89,159],"adaptive":[91,108],"called":[97,143],"GFSAI\u2010Adaptive,":[98,105],"address":[100],"above":[102],"problem.":[103],"first,":[106],"two":[107,115,136,140,179],"thread":[109,137],"allocation":[110,138],"strategies":[111],"proposed":[113,135,190],"special":[116,180],"SPD":[119],"matrices":[120,173],"ensure":[122],"allocated":[125],"threads":[126],"can":[127],"fully":[129],"utilized.":[130],"Second,":[131],"based":[132,182],"strategies,":[139],"kernels,":[142],"GFSAII":[144,169],"and":[145,157,170,194,205],"GFSAIII,":[146],"presented.":[148],"Third,":[149],"construct":[151],"a":[152,160,196,206],"new":[153],"graph":[154],"convolutional":[155],"network,":[156],"thus":[158],"search":[161],"engine":[162],"select":[164],"optimal":[166],"kernel":[167],"from":[168],"GFSAIII":[171],"do":[175],"belong":[177],"it.":[184],"Experimental":[185],"results":[186],"show":[187],"our":[189],"GFSAI\u2010Adaptive":[191],"is":[192],"outperforms":[195],"popular":[197],"public":[202],"CUSPARSE":[203],"library":[204],"recent":[207],"parallel":[208],"static":[209]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-20T00:00:00"}