{"id":"https://openalex.org/W3117932782","doi":"https://doi.org/10.1177/1094342020981153","title":"Point-block incomplete LU preconditioning with asynchronous iterations on GPU for multiphysics problems","display_name":"Point-block incomplete LU preconditioning with asynchronous iterations on GPU for multiphysics problems","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3117932782","doi":"https://doi.org/10.1177/1094342020981153","mag":"3117932782"},"language":"en","primary_location":{"id":"doi:10.1177/1094342020981153","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020981153","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["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/A5110665483","display_name":"Wenpeng Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I130750295","display_name":"Xinyang Normal University","ror":"https://ror.org/0190x2a66","country_code":"CN","type":"education","lineage":["https://openalex.org/I130750295"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenpeng Ma","raw_affiliation_strings":["School of Computer and Information Technology, Xinyang Normal University, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Xinyang Normal University, Henan, China","institution_ids":["https://openalex.org/I130750295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006367748","display_name":"Xiao\u2010Chuan Cai","orcid":"https://orcid.org/0000-0003-0296-8640"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Xiao-Chuan Cai","raw_affiliation_strings":["Department of Mathematics, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-0296-8640","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006367748"],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":0.1458,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.57108096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"35","issue":"2","first_page":"121","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.878578782081604},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6806491613388062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6567543745040894},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6420391201972961},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.591228723526001},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5886397361755371},{"id":"https://openalex.org/keywords/block-matrix","display_name":"Block matrix","score":0.5543863773345947},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4977398216724396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43016183376312256},{"id":"https://openalex.org/keywords/multiphysics","display_name":"Multiphysics","score":0.4238024353981018},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42269501090049744},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.3548111319541931},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3328781723976135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3052164316177368},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.22164389491081238},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09530377388000488},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.07494911551475525}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.878578782081604},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6806491613388062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6567543745040894},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6420391201972961},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.591228723526001},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5886397361755371},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.5543863773345947},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4977398216724396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43016183376312256},{"id":"https://openalex.org/C46435376","wikidata":"https://www.wikidata.org/wiki/Q1829750","display_name":"Multiphysics","level":3,"score":0.4238024353981018},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42269501090049744},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3548111319541931},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3328781723976135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3052164316177368},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.22164389491081238},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09530377388000488},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.07494911551475525},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342020981153","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020981153","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["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":25,"referenced_works":["https://openalex.org/W102985962","https://openalex.org/W1506342804","https://openalex.org/W1778498721","https://openalex.org/W1965034778","https://openalex.org/W1966263104","https://openalex.org/W2027485220","https://openalex.org/W2053999255","https://openalex.org/W2059418655","https://openalex.org/W2060803192","https://openalex.org/W2063610976","https://openalex.org/W2069366634","https://openalex.org/W2080090223","https://openalex.org/W2095258827","https://openalex.org/W2140254393","https://openalex.org/W2184502091","https://openalex.org/W2320527962","https://openalex.org/W2444544770","https://openalex.org/W2476506026","https://openalex.org/W2498468807","https://openalex.org/W2544527082","https://openalex.org/W2561373036","https://openalex.org/W2563513434","https://openalex.org/W2617808919","https://openalex.org/W2743824295","https://openalex.org/W3005203535"],"related_works":["https://openalex.org/W2084426624","https://openalex.org/W3026055904","https://openalex.org/W1967668711","https://openalex.org/W2946870551","https://openalex.org/W2047866757","https://openalex.org/W2001342884","https://openalex.org/W2125326641","https://openalex.org/W2595503355","https://openalex.org/W1928489786","https://openalex.org/W2163027735"],"abstract_inverted_index":{"Point-block":[0],"matrices":[1,25,68],"arise":[2],"naturally":[3],"in":[4,125,152,163],"multiphysics":[5],"problems":[6,108],"when":[7],"all":[8],"variables":[9],"associated":[10],"with":[11,145],"a":[12,172],"mesh":[13],"point":[14],"are":[15,19,32,109],"ordered":[16],"together,":[17],"and":[18,52,54,91,95,133,167],"different":[20],"from":[21,184],"the":[22,27,30,41,47,76,83,89,103,113,116,121,128,135,142,146,159,168,179,185],"general":[23],"block":[24],"since":[26],"sizes":[28],"of":[29,40,50,75,86,99,102,115,127,130],"blocks":[31,43],"so":[33],"small":[34],"one":[35],"can":[36,175],"often":[37],"invert":[38],"some":[39],"diagonal":[42],"explicitly.":[44],"Motivated":[45],"by":[46],"recent":[48],"works":[49],"Chow":[51,55],"Patel":[53],"et":[56],"al.,":[57],"we":[58,140],"propose":[59],"an":[60],"efficient":[61],"incomplete":[62],"LU":[63],"(ILU)":[64],"preconditioner":[65,77],"for":[66,88],"point-block":[67,118],"targeting":[69],"applications":[70],"on":[71],"GPU.":[72],"The":[73],"construction":[74],"involves":[78],"two":[79],"critical":[80],"steps:":[81],"(1)":[82],"initial":[84],"guessing":[85],"values":[87],"lower":[90],"upper":[92],"triangular":[93,104],"matrices;":[94],"(2)":[96],"several":[97],"sweeps":[98],"asynchronous":[100],"updating":[101],"matrices.":[105],"Three":[106],"representative":[107],"studied":[110],"to":[111],"show":[112,170],"advantage":[114],"proposed":[117,143],"approach":[119,124],"over":[120,178],"standard":[122],"point-wise":[123],"terms":[126],"number":[129],"GMRES":[131],"iterations":[132],"also":[134],"total":[136],"compute":[137],"time.":[138],"Moreover,":[139],"compare":[141],"algorithm":[144,150],"level-scheduling":[147],"based":[148],"parallel":[149],"employed":[151],"NVIDIA\u2019s":[153],"cuSPARSE":[154,186],"library":[155],"as":[156,158],"well":[157],"serial":[160],"method":[161],"implemented":[162],"Intel":[164],"MKL":[165],"library,":[166],"experiments":[169],"that":[171],"2\u00d7\u20135\u00d7":[173],"speedup":[174],"be":[176],"achieved":[177],"block-based":[180],"ILU(":[181],"p)":[182],"factorizations":[183],"library.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}