{"id":"https://openalex.org/W1972321715","doi":"https://doi.org/10.1137/120894452","title":"A Parallel Auxiliary Grid Algebraic Multigrid Method for Graphic Processing Units","display_name":"A Parallel Auxiliary Grid Algebraic Multigrid Method for Graphic Processing Units","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W1972321715","doi":"https://doi.org/10.1137/120894452","mag":"1972321715"},"language":"en","primary_location":{"id":"doi:10.1137/120894452","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120894452","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/A5100364430","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0002-2248-3328"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lu Wang","raw_affiliation_strings":["Pennsylvania State Univ#TAB#"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State Univ#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029270343","display_name":"Xiaozhe Hu","orcid":"https://orcid.org/0000-0001-7533-0416"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhe Hu","raw_affiliation_strings":["Pennsylvania State Univ#TAB#"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State Univ#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079416691","display_name":"Jonathan Cohen","orcid":"https://orcid.org/0000-0003-1004-5598"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Cohen","raw_affiliation_strings":["Nvidia"],"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101494424","display_name":"Jinchao Xu","orcid":"https://orcid.org/0009-0004-4132-0227"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchao Xu","raw_affiliation_strings":["Mathematics"],"affiliations":[{"raw_affiliation_string":"Mathematics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100364430"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":8.1017,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96532847,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"3","first_page":"C263","last_page":"C283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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/multigrid-method","display_name":"Multigrid method","score":0.7926489114761353},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7432560920715332},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7213958501815796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694725513458252},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6216790676116943},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5963073372840881},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.581541895866394},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5549980998039246},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4674540162086487},{"id":"https://openalex.org/keywords/quadtree","display_name":"Quadtree","score":0.4255439341068268},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3681856095790863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25058242678642273},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.12521621584892273}],"concepts":[{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.7926489114761353},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7432560920715332},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7213958501815796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694725513458252},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6216790676116943},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5963073372840881},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.581541895866394},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5549980998039246},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4674540162086487},{"id":"https://openalex.org/C151416825","wikidata":"https://www.wikidata.org/wiki/Q934791","display_name":"Quadtree","level":2,"score":0.4255439341068268},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3681856095790863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25058242678642273},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.12521621584892273},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/120894452","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120894452","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.46000000834465027,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1810154588","https://openalex.org/W1964284734","https://openalex.org/W1967983557","https://openalex.org/W1985263109","https://openalex.org/W1997596109","https://openalex.org/W2006382715","https://openalex.org/W2008196645","https://openalex.org/W2009250131","https://openalex.org/W2012231377","https://openalex.org/W2017217780","https://openalex.org/W2037979149","https://openalex.org/W2039789965","https://openalex.org/W2047614366","https://openalex.org/W2061512082","https://openalex.org/W2080139289","https://openalex.org/W2099957444","https://openalex.org/W2108371414","https://openalex.org/W2131738355","https://openalex.org/W2142304406","https://openalex.org/W2142762932"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2983282793","https://openalex.org/W2115641454","https://openalex.org/W2031630671","https://openalex.org/W2032508741","https://openalex.org/W2607998022","https://openalex.org/W2059382600","https://openalex.org/W2363538625","https://openalex.org/W4297775710","https://openalex.org/W1937514268"],"abstract_inverted_index":{"In":[0,23],"this":[1,117,147],"paper,":[2],"we":[3,31,131],"develop":[4],"a":[5,33,41,95],"new":[6,83,134,154],"parallel":[7,87,96,114,135],"auxiliary":[8,47,136],"grid":[9,137],"algebraic":[10],"multigrid":[11],"(AMG)":[12],"method":[13,139,155],"to":[14,52,106,180],"leverage":[15],"the":[16,24,27,55,62,100,104,108,113,121,143,150,181],"power":[17],"of":[18,26,61,103,116,146,152,166],"graphic":[19],"processing":[20],"units":[21],"(GPUs).":[22],"construction":[25],"hierarchical":[28],"coarse":[29],"grid,":[30],"use":[32],"simple":[34],"and":[35,58,72,111,142,172,188,198],"fixed":[36],"coarsening":[37],"procedure":[38],"based":[39,98],"on":[40,76,90,99,120,140,169,174],"region":[42],"quadtree":[43,105],"generated":[44],"from":[45],"an":[46,163],"grid.":[48],"This":[49,65],"allows":[50],"us":[51],"explicitly":[53],"control":[54],"sparsity":[56],"patterns":[57,75],"operator":[59],"complexities":[60],"AMG":[63,138,182],"solver.":[64,118],"feature":[66],"provides":[67],"(nearly)":[68,157],"optimal":[69],"load":[70],"balancing":[71],"predictable":[73],"communication":[74],"shape":[77,175],"regular":[78,176],"grids,":[79],"which":[80],"makes":[81],"our":[82,133,153],"algorithm":[84],"suitable":[85],"for":[86,156,195],"computing,":[88],"especially":[89],"GPUs.":[91],"We":[92],"also":[93],"design":[94],"smoother":[97],"special":[101],"coloring":[102],"accelerate":[107],"convergence":[109],"rate":[110],"improve":[112],"performance":[115],"Based":[119],"CUDA":[122,125],"toolkit":[123],"[NVIDIA":[124],"Programming":[126],"Guide,":[127],"NVIDIA":[128],"Corp.,":[129],"2010],":[130],"implemented":[132],"GPUs":[141],"numerical":[144],"results":[145,161],"implementation":[148,183],"demonstrate":[149],"efficiency":[151],"isotropic":[158],"problems.":[159],"The":[160],"achieve":[162],"average":[164],"speedup":[165],"over":[167],"4":[168],"quasi-uniform":[170],"grids":[171,177],"2":[173],"when":[178],"compared":[179],"in":[184],"CUSP":[185],"[M.":[186],"Garland":[187],"N.":[189],"Bell,":[190],"CUSP:":[191],"Generic":[192],"Parallel":[193],"Algorithms":[194],"Sparse":[196],"Matrix":[197],"Graph":[199],"Computations,":[200],"http://cusplibrary.github.com/":[201],"(2010)].":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}