{"id":"https://openalex.org/W2635312788","doi":"https://doi.org/10.1145/3093172.3093230","title":"Asynchronous Task-Based Parallelization of Algebraic Multigrid","display_name":"Asynchronous Task-Based Parallelization of Algebraic Multigrid","publication_year":2017,"publication_date":"2017-06-23","ids":{"openalex":"https://openalex.org/W2635312788","doi":"https://doi.org/10.1145/3093172.3093230","mag":"2635312788"},"language":"en","primary_location":{"id":"doi:10.1145/3093172.3093230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-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/A5089453574","display_name":"Amani AlOnazi","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Amani AlOnazi","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026974411","display_name":"George Markomanolis","orcid":"https://orcid.org/0000-0002-5571-4823"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"George S. Markomanolis","raw_affiliation_strings":["KAUST Supercomputing Laboratory, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST Supercomputing Laboratory, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089453574"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.9013,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73734968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8283154964447021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8266105651855469},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7380893230438232},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.6947548389434814},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6141580939292908},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.5925616025924683},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.534204363822937},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.511260986328125},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4984626770019531},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.49669820070266724},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.47523048520088196},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4531151056289673},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3254527449607849},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.2745676636695862},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.14138835668563843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08600649237632751},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.07981964945793152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283154964447021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8266105651855469},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7380893230438232},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.6947548389434814},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6141580939292908},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.5925616025924683},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.534204363822937},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.511260986328125},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4984626770019531},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49669820070266724},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.47523048520088196},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4531151056289673},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3254527449607849},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2745676636695862},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.14138835668563843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08600649237632751},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.07981964945793152},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3093172.3093230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/625632","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/625632","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W103987825","https://openalex.org/W823952558","https://openalex.org/W1483559473","https://openalex.org/W1522102036","https://openalex.org/W1524106338","https://openalex.org/W1575767586","https://openalex.org/W1579891937","https://openalex.org/W1839773802","https://openalex.org/W1976677460","https://openalex.org/W1992935956","https://openalex.org/W2012492661","https://openalex.org/W2016279572","https://openalex.org/W2017217780","https://openalex.org/W2022090406","https://openalex.org/W2036551003","https://openalex.org/W2039789965","https://openalex.org/W2057361098","https://openalex.org/W2067484330","https://openalex.org/W2079472602","https://openalex.org/W2100437155","https://openalex.org/W2102635728","https://openalex.org/W2121893797","https://openalex.org/W2142677441","https://openalex.org/W2151317657","https://openalex.org/W2166834428","https://openalex.org/W2486796129","https://openalex.org/W2915344229","https://openalex.org/W2945154147","https://openalex.org/W4230055019","https://openalex.org/W4300509647","https://openalex.org/W6759348079"],"related_works":["https://openalex.org/W1970451660","https://openalex.org/W2085974832","https://openalex.org/W2185482126","https://openalex.org/W191463404","https://openalex.org/W1981872744","https://openalex.org/W4248099758","https://openalex.org/W2126866131","https://openalex.org/W2039771558","https://openalex.org/W4241547419","https://openalex.org/W2104702637"],"abstract_inverted_index":{"As":[0],"processor":[1],"clock":[2],"rates":[3],"become":[4,9],"more":[5,10],"dynamic":[6],"and":[7,63,82,102,106,129,177,192,230],"workloads":[8],"adaptive,":[11],"the":[12,33,45,127,142,162,174,178,184,188,193,227],"vulnerability":[13],"to":[14,72,90,96,115,133,160,199,240],"global":[15],"synchronization":[16,81],"that":[17],"already":[18],"complicates":[19],"programming":[20],"for":[21,152,187,201],"performance":[22,65],"in":[23,37,44,183,213],"today's":[24],"petascale":[25],"environment":[26],"will":[27],"be":[28],"exacerbated.":[29],"Algebraic":[30],"multigrid":[31],"(AMG),":[32],"solver":[34],"of":[35,88,117,226,242],"choice":[36],"many":[38,73],"large-scale":[39],"PDE-based":[40],"simulations,":[41],"scales":[42],"well":[43,61],"weak":[46,238],"sense,":[47],"with":[48,150,244],"fixed":[49],"problem":[50],"size":[51],"per":[52,222,233],"node,":[53,148],"on":[54],"tightly":[55],"coupled":[56],"systems":[57],"when":[58],"loads":[59],"are":[60,85],"balanced":[62],"core":[64,218],"is":[66,78],"reliable.":[67],"However,":[68],"its":[69],"strong":[70,214],"scaling":[71,215],"cores":[74],"within":[75,146,168],"a":[76,138,147,157,202],"node":[77,225,234],"challenging.":[79],"Reducing":[80],"increasing":[83],"concurrency":[84,105],"vital":[86],"adaptations":[87],"AMG":[89,99,132],"hybrid":[91,139,207],"architectures.":[92],"Recent":[93],"communication-reducing":[94],"improvements":[95],"classical":[97],"additive":[98,131],"by":[100],"Vassilevski":[101,128],"Yang":[103,130],"improve":[104],"increase":[107],"communication-computation":[108],"overlap,":[109],"while":[110],"retaining":[111],"convergence":[112],"properties":[113],"close":[114],"those":[116],"standard":[118],"multiplicative":[119],"AMG,":[120],"but":[121],"remain":[122],"bulk":[123],"synchronous.":[124],"We":[125,155,171],"extend":[126],"asynchronous":[134],"task-based":[135],"parallelism":[136],"using":[137],"MPI+OmpSs":[140],"(from":[141],"Barcelona":[143],"Supercomputer":[144],"Center)":[145],"along":[149],"MPI":[151,245],"internode":[153],"communications.":[154],"implement":[156],"tiling":[158],"approach":[159,212],"decompose":[161],"grid":[163],"hierarchy":[164],"into":[165],"parallel":[166],"units":[167],"task":[169],"containers.":[170],"compare":[172],"against":[173],"MPI-only":[175],"BoomerAMG":[176],"Auxiliary-space":[179],"Maxwell":[180],"Solver":[181],"(AMS)":[182],"hypre":[185],"library":[186],"3D":[189],"Laplacian":[190],"operator":[191],"electromagnetic":[194],"diffusion,":[195],"respectively.":[196],"In":[197],"time":[198],"solution":[200],"full":[203,217],"solve":[204],"an":[205,210],"MPI-OmpSs":[206],"improves":[208],"over":[209],"all-MPI":[211],"at":[216],"count":[219],"(32":[220],"threads":[221],"single":[223],"Haswell":[224],"Cray":[228],"XC40)":[229],"maintains":[231],"this":[232],"advantage":[235],"as":[236],"both":[237],"scale":[239],"thousands":[241],"cores,":[243],"between":[246],"nodes.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
