{"id":"https://openalex.org/W2758813627","doi":"https://doi.org/10.1109/tpds.2017.2755655","title":"Asynchronous Task-Based Polar Decomposition on Single Node Manycore Architectures","display_name":"Asynchronous Task-Based Polar Decomposition on Single Node Manycore Architectures","publication_year":2017,"publication_date":"2017-09-29","ids":{"openalex":"https://openalex.org/W2758813627","doi":"https://doi.org/10.1109/tpds.2017.2755655","mag":"2758813627"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2755655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2755655","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01585079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064027099","display_name":"Dalal Sukkari","orcid":"https://orcid.org/0000-0002-4228-4211"},"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":"Dalal Sukkari","raw_affiliation_strings":["Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)"],"raw_orcid":"https://orcid.org/0000-0002-4228-4211","affiliations":[{"raw_affiliation_string":"Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"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":"Hatem Ltaief","raw_affiliation_strings":["Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)"],"raw_orcid":"https://orcid.org/0000-0002-6897-1095","affiliations":[{"raw_affiliation_string":"Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034603717","display_name":"Mathieu Faverge","orcid":"https://orcid.org/0000-0002-2128-1230"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"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":["FR","SA"],"is_corresponding":false,"raw_author_name":"Mathieu Faverge","raw_affiliation_strings":["Bordeaux INP, CNRS, INRIA et Universit\u00e9 de Bordeaux, Talence, France","KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)","Bordeaux INP - Institut Polytechnique de Bordeaux (Avenue des facult\u00e9s\r\n33405 Talence - France)","HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)"],"raw_orcid":"https://orcid.org/0000-0002-2128-1230","affiliations":[{"raw_affiliation_string":"Bordeaux INP, CNRS, INRIA et Universit\u00e9 de Bordeaux, Talence, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Bordeaux INP - Institut Polytechnique de Bordeaux (Avenue des facult\u00e9s\r\n33405 Talence - France)","institution_ids":["https://openalex.org/I4210160189"]},{"raw_affiliation_string":"HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]}]},{"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":["Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computer, Electrical, and Mathematical Sciences and Engineering, Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"KAUST - King Abdullah University of Science and Technology [Saudi Arabia] (King Abdullah University of Science and Technology P.O.Box 55455 Jeddah 21534, Saudi Arabia - Saudi Arabia)","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1845,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93102631,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":"2","first_page":"312","last_page":"323"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9962000250816345,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9941999912261963,"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":0.8037680387496948},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6838864088058472},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6582776308059692},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5600179433822632},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5008552074432373},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.4788767695426941},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4278278648853302},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0906991958618164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037680387496948},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6838864088058472},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6582776308059692},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5600179433822632},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5008552074432373},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.4788767695426941},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4278278648853302},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0906991958618164},{"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpds.2017.2755655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2755655","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01585079v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01585079","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems, 2017, XX, ⟨10.1109/TPDS.2017.2755655⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/625885","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/625885","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":"Article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01585079v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01585079","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems, 2017, XX, ⟨10.1109/TPDS.2017.2755655⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G5713630684","display_name":"SOLvers for Heterogeneous Architectures over Runtime systems","funder_award_id":"ANR-13-MONU-0007","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W574202735","https://openalex.org/W995198334","https://openalex.org/W1494445573","https://openalex.org/W1594234351","https://openalex.org/W1624763321","https://openalex.org/W1981745143","https://openalex.org/W1983292127","https://openalex.org/W1986834688","https://openalex.org/W1987255606","https://openalex.org/W1999664467","https://openalex.org/W2004089677","https://openalex.org/W2006882211","https://openalex.org/W2016279572","https://openalex.org/W2016358047","https://openalex.org/W2020054862","https://openalex.org/W2022846189","https://openalex.org/W2040557342","https://openalex.org/W2052799831","https://openalex.org/W2059076129","https://openalex.org/W2079562210","https://openalex.org/W2088307891","https://openalex.org/W2093529653","https://openalex.org/W2104008467","https://openalex.org/W2105524676","https://openalex.org/W2112033694","https://openalex.org/W2121893797","https://openalex.org/W2122747952","https://openalex.org/W2124480634","https://openalex.org/W2140064412","https://openalex.org/W2145960411","https://openalex.org/W2149294210","https://openalex.org/W2275630370","https://openalex.org/W2326297968","https://openalex.org/W2405076432","https://openalex.org/W2462018851","https://openalex.org/W2504210177","https://openalex.org/W2546742253","https://openalex.org/W2547058949","https://openalex.org/W2562243536","https://openalex.org/W2617628430","https://openalex.org/W2753239506","https://openalex.org/W2946724226","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4239096436","https://openalex.org/W4320800818","https://openalex.org/W6712983310","https://openalex.org/W6729471629"],"related_works":["https://openalex.org/W2016659453","https://openalex.org/W2078349096","https://openalex.org/W2002598339","https://openalex.org/W2150953077","https://openalex.org/W1599936522","https://openalex.org/W2142486491","https://openalex.org/W2006707200","https://openalex.org/W2391999311","https://openalex.org/W2919544312","https://openalex.org/W4388311419"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,9,25,33,36,39,43,50,55,71,82,86,90,95,100,141,154,158,166,170,197],"first":[4],"asynchronous,":[5],"task-based":[6,73],"formulation":[7,23],"of":[8,24,35,78,81,85],"polar":[10,37,121,198],"decomposition":[11,122,199],"and":[12,45,138,162,194,212],"its":[13],"corresponding":[14],"implementation":[15,41,74],"on":[16,20,68,169,200],"manycore":[17],"architectures.":[18,66],"Based":[19],"a":[21,128],"new":[22],"iterative":[26],"QR":[27,58],"dynamically-weighted":[28],"Halley":[29],"algorithm":[30],"(QDWH)":[31],"for":[32,49,114,196],"calculation":[34],"decomposition,":[38],"proposed":[40],"replaces":[42],"original":[44],"hostile":[46],"LU":[47],"factorization":[48,59],"condition":[51],"number":[52],"estimator":[53],"by":[54],"more":[56],"adequate":[57],"to":[60,108,152,156,163],"enable":[61],"software":[62],"portability":[63],"across":[64],"various":[65,159],"Relying":[67],"fine-grained":[69],"computations,":[70],"novel":[72],"is":[75,150],"also":[76],"capable":[77],"taking":[79],"advantage":[80],"identity":[83],"structure":[84],"matrix":[87],"involved":[88],"during":[89],"QDWH":[91],"iterations,":[92],"which":[93],"decreases":[94],"overall":[96,119],"algorithmic":[97],"complexity.":[98],"Furthermore,":[99],"artifactual":[101],"synchronization":[102],"points":[103],"have":[104],"been":[105],"weakened":[106],"compared":[107],"previous":[109],"implementations,":[110],"unveiling":[111],"look-ahead":[112],"opportunities":[113],"better":[115],"hardware":[116,172],"occupancy.":[117],"The":[118,145],"QDWH-based":[120],"can":[123],"then":[124],"be":[125],"represented":[126],"as":[127],"directed":[129],"acyclic":[130],"graph":[131],"(DAG),":[132],"where":[133],"nodes":[134],"represent":[135],"computational":[136,167],"tasks":[137,168],"edges":[139],"define":[140],"inter-task":[142],"data":[143,160],"dependencies.":[144],"StarPU":[146],"dynamic":[147],"runtime":[148],"system":[149],"employed":[151],"traverse":[153],"DAG,":[155],"track":[157],"dependencies":[161],"asynchronously":[164],"schedule":[165],"underlying":[171],"resources,":[173],"resulting":[174],"in":[175],"an":[176],"out-of-order":[177],"task":[178],"scheduling.":[179],"Benchmarking":[180],"experiments":[181],"show":[182],"significant":[183],"improvements":[184],"against":[185],"existing":[186],"state-of-the-art":[187],"high":[188,217],"performance":[189],"implementations":[190],"(i.e.,":[191,205],"Intel":[192,206],"MKL":[193],"Elemental)":[195],"latest":[201],"shared-memory":[202],"vendors'":[203],"systems":[204],"Haswell/Broadwell/Knights":[207],"Landing,":[208],"NVIDIA":[209],"K80/P100":[210],"GPUs":[211],"IBM":[213],"Power8),":[214],"while":[215],"maintaining":[216],"numerical":[218],"accuracy.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}