{"id":"https://openalex.org/W2963744345","doi":"https://doi.org/10.1137/15m1039523","title":"Analysis of a Splitting Approach for the Parallel Solution of Linear Systems on GPU Cards","display_name":"Analysis of a Splitting Approach for the Parallel Solution of Linear Systems on GPU Cards","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963744345","doi":"https://doi.org/10.1137/15m1039523","mag":"2963744345"},"language":"en","primary_location":{"id":"doi:10.1137/15m1039523","is_oa":false,"landing_page_url":"https://doi.org/10.1137/15m1039523","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","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/A5100413601","display_name":"Ang Li","orcid":"https://orcid.org/0000-0002-2309-9811"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ang Li","raw_affiliation_strings":["Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065615643","display_name":"Radu Serban","orcid":"https://orcid.org/0000-0002-4219-905X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Serban","raw_affiliation_strings":["Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027224030","display_name":"Dan Negru\u0163","orcid":"https://orcid.org/0000-0003-1565-2784"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Negrut","raw_affiliation_strings":["Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706","Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100413601"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.9483,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79301736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"39","issue":"3","first_page":"C215","last_page":"C237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":1.0,"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":1.0,"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.7777550220489502},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.6446927189826965},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.637152910232544},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6363680958747864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6277114152908325},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.6178765296936035},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5852060317993164},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5592204332351685},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.5043874979019165},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.46290597319602966},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4560234248638153},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4343017339706421},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42533040046691895},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.34229153394699097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33955705165863037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3374365568161011},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33393388986587524},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.25196772813796997},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.2326933741569519},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2080073356628418},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.1095111072063446},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08813753724098206}],"concepts":[{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.7777550220489502},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.6446927189826965},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.637152910232544},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6363680958747864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277114152908325},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.6178765296936035},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5852060317993164},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5592204332351685},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.5043874979019165},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.46290597319602966},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4560234248638153},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4343017339706421},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42533040046691895},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.34229153394699097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33955705165863037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3374365568161011},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33393388986587524},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.25196772813796997},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.2326933741569519},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2080073356628418},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.1095111072063446},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08813753724098206},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/15m1039523","is_oa":false,"landing_page_url":"https://doi.org/10.1137/15m1039523","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.6347","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.6347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sbel.wisc.edu/documents/TR-2015-12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2624145723","display_name":null,"funder_award_id":"SI2-SSE 1147337","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G315277985","display_name":"SI2-SSE Collaborative Research: SPIKE-An Implementation of a Recursive Divide-and-Conquer Parallel Strategy for Solving Large Systems of Linear Equations","funder_award_id":"1147337","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1897320022","https://openalex.org/W2003105834","https://openalex.org/W2017431061","https://openalex.org/W2052280672","https://openalex.org/W2069849438","https://openalex.org/W2070571481","https://openalex.org/W2072576437","https://openalex.org/W2089309544","https://openalex.org/W2099753835","https://openalex.org/W2149454052","https://openalex.org/W2600100536"],"related_works":["https://openalex.org/W4299721548","https://openalex.org/W2996013851","https://openalex.org/W2756224289","https://openalex.org/W2950173424","https://openalex.org/W4299356399","https://openalex.org/W2503137108","https://openalex.org/W2119534391","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2020279179"],"abstract_inverted_index":{"We":[0],"discuss":[1],"an":[2],"approach":[3,46],"for":[4,125],"solving":[5],"sparse":[6,110],"or":[7,70],"dense":[8,163],"banded":[9,164],"linear":[10],"systems":[11,165],"$Ax":[12],"=":[13],"b$":[14],"on":[15,121],"a":[16,95,150,183],"graphics":[17],"processing":[18],"unit":[19],"(GPU)":[20],"card.":[21],"The":[22,41,64],"matrix":[23,51],"${A}":[24],"\\in":[25],"{\\mathbb{R}}^{N":[26],"\\times":[27],"N}$":[28],"is":[29,100,135,174],"possibly":[30],"nonsymmetric":[31],"and":[32,43,115,132,137,177],"moderately":[33],"large,":[34],"i.e.,":[35],"${10,000}{}":[36],"\\leq":[37,39],"N":[38],"{500,000}{}$.":[40],"split":[42],"parallelize":[44],"(SaP)":[45],"seeks":[47],"to":[48,68,71,161,169],"partition":[49],"the":[50,73,77,85,122,145],"$A$":[52],"into":[53],"diagonal":[54,78],"subblocks":[55,79],"$A_i$,":[56],"$i=1,\\ldots,P$,":[57],"which":[58,99,118],"are":[59,92,167],"independently":[60],"factored":[61],"in":[62,94,102,129,140],"parallel.":[63],"solution":[65],"may":[66],"choose":[67],"consider":[69],"ignore":[72],"matrices":[74],"that":[75,89,166],"couple":[76],"$A_i$.":[80],"This":[81],"approach,":[82],"along":[83],"with":[84,106,144],"Krylov-subspace-based":[86],"iterative":[87],"method":[88],"it":[90],"preconditions,":[91],"implemented":[93],"solver":[96],"called":[97],"SaP::GPU,":[98,117],"compared":[101],"terms":[103,141],"of":[104,142],"efficiency":[105,143],"three":[107],"commonly":[108],"used":[109,160],"direct":[111,147],"solvers:":[112],"PARDISO,":[113],"SuperLU,":[114],"MUMPS.":[116],"runs":[119],"entirely":[120],"GPU":[123],"except":[124],"several":[126],"stages":[127],"involved":[128],"preliminary":[130],"row":[131],"column":[133],"permutations,":[134],"robust":[136],"compares":[138],"well":[139,158],"aforementioned":[146],"solvers.":[148],"In":[149],"comparison":[151],"against":[152],"Intel's":[153],"MKL,":[154],"SaP::GPU":[155,173],"also":[156],"fared":[157],"when":[159],"solve":[162],"close":[168],"being":[170],"diagonally":[171],"dominant.":[172],"publicly":[175],"available":[176],"distributed":[178],"as":[179],"open":[180],"source":[181],"under":[182],"permissive":[184],"BSD-3":[185],"license.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}