{"id":"https://openalex.org/W2774512715","doi":"https://doi.org/10.1145/3328723","title":"Massively Parallel Polar Decomposition on Distributed-memory Systems","display_name":"Massively Parallel Polar Decomposition on Distributed-memory Systems","publication_year":2019,"publication_date":"2019-03-31","ids":{"openalex":"https://openalex.org/W2774512715","doi":"https://doi.org/10.1145/3328723","mag":"2774512715"},"language":"en","primary_location":{"id":"doi:10.1145/3328723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3328723","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel 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/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":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Jeddah, KSA"],"raw_orcid":"https://orcid.org/0000-0002-6897-1095","affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Jeddah, KSA","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","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":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Jeddah, KSA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Jeddah, KSA","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006847865","display_name":"Aniello Esposito","orcid":"https://orcid.org/0000-0003-1597-0811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aniello Esposito","raw_affiliation_strings":["Cray EMEA Research Lab, Bristol, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cray EMEA Research Lab, Bristol, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008129578","display_name":"Yuji Nakatsukasa","orcid":"https://orcid.org/0000-0001-7911-1501"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuji Nakatsukasa","raw_affiliation_strings":["Mathematical Institute, University of Oxford, Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematical Institute, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"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, Jeddah, KSA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Jeddah, KSA","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9641,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76495963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"15"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9957000017166138,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6704603433609009},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.630188524723053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6006617546081543},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5442578792572021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5326145887374878},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5291512608528137},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.5242441296577454},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5148955583572388},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4658205509185791},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.4463827610015869},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43475258350372314},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4296911060810089},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4289172291755676},{"id":"https://openalex.org/keywords/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.42175811529159546},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4150984287261963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.365484356880188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3163350224494934},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.2223944067955017}],"concepts":[{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6704603433609009},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.630188524723053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6006617546081543},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5442578792572021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5326145887374878},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5291512608528137},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5242441296577454},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5148955583572388},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4658205509185791},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4463827610015869},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43475258350372314},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4296911060810089},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4289172291755676},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.42175811529159546},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4150984287261963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.365484356880188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3163350224494934},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2223944067955017},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3328723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3328723","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:9323f520-186a-4965-9adb-46c26e46432c","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:9323f520-186a-4965-9adb-46c26e46432c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/626359","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/626359","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":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"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":19,"referenced_works":["https://openalex.org/W995198334","https://openalex.org/W1624763321","https://openalex.org/W1987255606","https://openalex.org/W2020054862","https://openalex.org/W2022846189","https://openalex.org/W2040557342","https://openalex.org/W2059076129","https://openalex.org/W2078841894","https://openalex.org/W2093529653","https://openalex.org/W2105524676","https://openalex.org/W2112033694","https://openalex.org/W2121893797","https://openalex.org/W2128362857","https://openalex.org/W2275630370","https://openalex.org/W2326297968","https://openalex.org/W2613618711","https://openalex.org/W2758813627","https://openalex.org/W2943231329","https://openalex.org/W3164573826"],"related_works":["https://openalex.org/W4289729660","https://openalex.org/W2887023857","https://openalex.org/W2950000202","https://openalex.org/W2004134826","https://openalex.org/W4321472478","https://openalex.org/W1668534708","https://openalex.org/W2048125828","https://openalex.org/W2063338407","https://openalex.org/W1970113381","https://openalex.org/W2123489408"],"abstract_inverted_index":{"We":[0,150,161],"present":[1],"a":[2,110,168],"high-performance":[3],"implementation":[4],"of":[5,78,90,130,167,171,192,201],"the":[6,16,23,29,34,42,51,56,79,88,119,128,165,197],"Polar":[7],"Decomposition":[8],"(PD)":[9],"on":[10,15,55,158],"distributed-memory":[11],"systems.":[12],"Building":[13],"upon":[14],"QR-based":[17],"Dynamically":[18],"Weighted":[19],"Halley":[20],"(QDWH)":[21],"algorithm,":[22],"key":[24],"idea":[25],"lies":[26],"in":[27,63,102,116,145,164,186,196],"finding":[28],"best":[30],"rational":[31,58],"approximation":[32],"for":[33,45,74,84,123,194],"scalar":[35],"sign":[36],"function,":[37],"which":[38],"also":[39],"corresponds":[40],"to":[41,48,114,118,155,177,182],"polar":[43],"factor":[44],"symmetric":[46],"matrices,":[47,76],"further":[49],"accelerate":[50],"QDWH":[52,179,189],"convergence.":[53],"Based":[54],"Zolotarev":[57,61,91],"functions\u2014introduced":[59],"by":[60,180],"(ZOLO)":[62],"1877\u2014this":[64],"new":[65],"PD":[66],"algorithm":[67],"ZOLO-PD":[68,86,108,174],"converges":[69],"within":[70],"two":[71,98,159],"iterations":[72,82],"even":[73],"ill-conditioned":[75],"instead":[77],"original":[80],"six":[81],"needed":[83],"QDWH.":[85,124],"uses":[87],"property":[89],"functions":[92,99],"that":[93],"optimality":[94],"is":[95,175],"maintained":[96],"when":[97],"are":[100],"composed":[101],"an":[103,146],"appropriate":[104],"manner.":[105],"The":[106],"resulting":[107],"has":[109],"convergence":[111,121],"rate":[112,122],"up":[113,154,181],"17,":[115],"contrast":[117],"cubic":[120],"This":[125],"comes":[126],"at":[127],"price":[129],"higher":[131],"arithmetic":[132],"costs":[133],"and":[134],"memory":[135],"footprint.":[136],"These":[137],"extra":[138],"floating-point":[139],"operations":[140],"can,":[141],"however,":[142],"be":[143],"processed":[144],"embarrassingly":[147],"parallel":[148],"fashion.":[149],"demonstrate":[151,162],"performance":[152],"using":[153],"102,400":[156],"cores":[157],"supercomputers.":[160],"that,":[163],"presence":[166],"large":[169],"number":[170],"processing":[172],"units,":[173],"able":[176],"outperform":[178],"2.3\u00d7":[183],"speedup,":[184],"especially":[185],"situations":[187],"where":[188],"runs":[190],"out":[191],"work,":[193],"instance,":[195],"strong":[198],"scaling":[199],"mode":[200],"operation.":[202]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
