{"id":"https://openalex.org/W2943231329","doi":"https://doi.org/10.1145/3309548","title":"A QDWH-based SVD Software Framework on Distributed-memory Manycore Systems","display_name":"A QDWH-based SVD Software Framework on Distributed-memory Manycore Systems","publication_year":2019,"publication_date":"2019-04-26","ids":{"openalex":"https://openalex.org/W2943231329","doi":"https://doi.org/10.1145/3309548","mag":"2943231329"},"language":"en","primary_location":{"id":"doi:10.1145/3309548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309548","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"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 Mathematical Software","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/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":true,"raw_author_name":"Dalal Sukkari","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, 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":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","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":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Aniello Esposito","raw_affiliation_strings":["Cray EMEA Research Lab (CERL), Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Cray EMEA Research Lab (CERL), Basel, Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"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":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064027099"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.9631,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72280198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"45","issue":"2","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9952999949455261,"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":0.8234515190124512},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.763663649559021},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5888597965240479},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.46009865403175354},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.43187618255615234},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4311182200908661},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4258950650691986},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37501060962677},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3678120970726013},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08399707078933716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234515190124512},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.763663649559021},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5888597965240479},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.46009865403175354},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.43187618255615234},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4311182200908661},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4258950650691986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37501060962677},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3678120970726013},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08399707078933716},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3309548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309548","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"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 Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/626212","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/626212","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":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W995198334","https://openalex.org/W1987255606","https://openalex.org/W2006882211","https://openalex.org/W2052799831","https://openalex.org/W2059076129","https://openalex.org/W2093529653","https://openalex.org/W2121213195","https://openalex.org/W2148678374","https://openalex.org/W2168612748","https://openalex.org/W2546742253","https://openalex.org/W2613618711","https://openalex.org/W2758813627","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4242589337"],"related_works":["https://openalex.org/W2782904003","https://openalex.org/W2118633810","https://openalex.org/W2150953077","https://openalex.org/W4226434912","https://openalex.org/W2002598339","https://openalex.org/W1995410415","https://openalex.org/W2133814741","https://openalex.org/W4301603585","https://openalex.org/W3108343813","https://openalex.org/W4312481107"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,9,50,96,148,226,240],"high-performance":[4],"software":[5,180],"framework":[6,207],"for":[7,82,229],"computing":[8],"dense":[10],"SVD":[11,29,47,61,186,254],"on":[12,32,128,160,188,194,213,244],"distributed-memory":[13,190],"manycore":[14,191],"systems.":[15],"Originally":[16],"introduced":[17],"by":[18,163],"Nakatsukasa":[19,24],"et":[20],"al.":[21],"(2010)":[22],"and":[23,25,139,152,168,184,200,221,231,252,261,264],"Higham":[26],"(2013),":[27],"the":[28,33,37,45,59,63,67,83,88,100,108,113,118,121,129,136,140,144,154,157,161,166,214,269],"solver":[30],"relies":[31],"polar":[34,250],"decomposition":[35,251],"using":[36],"QR":[38],"Dynamically":[39],"Weighted":[40],"Halley":[41],"algorithm":[42,48],"(QDWH).":[43],"Although":[44],"QDWH-based":[46,249],"performs":[49],"significant":[51],"amount":[52],"of":[53,71,115,120,143,156],"extra":[54],"floating-point":[55],"operations":[56],"compared":[57],"to":[58,126,210,224],"traditional":[60],"with":[62,74,95,239],"one-stage":[64],"bidiagonal":[65],"reduction,":[66],"inherent":[68],"high":[69],"level":[70],"concurrency":[72],"associated":[73],"Level":[75],"3":[76],"BLAS":[77],"compute-bound":[78],"kernels":[79],"ultimately":[80],"compensates":[81],"arithmetic":[84],"complexity":[85,138],"overhead.":[86],"Using":[87],"ScaLAPACK":[89,219],"two-dimensional":[90],"block":[91],"cyclic":[92],"data":[93],"distribution":[94],"rectangular":[97],"processor":[98,132],"topology,":[99],"resulting":[101],"QDWH-SVD":[102,206],"further":[103],"reduces":[104],"excessive":[105],"communications":[106],"during":[107,117],"panel":[109],"factorization,":[110],"while":[111],"increasing":[112],"degree":[114],"parallelism":[116],"update":[119],"trailing":[122],"submatrix,":[123],"as":[124],"opposed":[125],"relying":[127],"default":[130],"square":[131],"grid.":[133],"After":[134],"detailing":[135],"algorithmic":[137],"memory":[141],"footprint":[142],"algorithm,":[145],"we":[146],"conduct":[147],"thorough":[149],"performance":[150,162,174,241],"analysis":[151],"study":[153],"impact":[155],"grid":[158],"topology":[159],"looking":[164],"at":[165,259],"communication":[167],"computation":[169],"profiling":[170],"trade-offs.":[171],"We":[172,234],"report":[173],"results":[175],"against":[176,218],"state-of-the-art":[177],"existing":[178],"QDWH":[179],"implementations":[181],"(e.g.,":[182],"Elemental)":[183],"their":[185],"extensions":[187],"large-scale":[189],"systems":[192],"based":[193,243],"commodity":[195],"Intel":[196],"x86":[197],"Haswell":[198],"processors":[199],"Knights":[201],"Landing":[202],"(KNL)":[203],"architecture.":[204],"The":[205],"achieves":[208],"up":[209,237],"3/8-fold":[211],"speedups":[212],"Haswell/KNL-based":[215],"platforms,":[216],"respectively,":[217,263],"PDGESVD":[220],"turns":[222],"out":[223],"be":[225],"competitive":[227],"alternative":[228],"well-":[230],"ill-conditioned":[232],"matrices.":[233],"finally":[235],"come":[236],"herein":[238],"model":[242],"these":[245],"empirical":[246],"results.":[247],"Our":[248],"its":[253],"extension":[255],"are":[256],"freely":[257],"available":[258],"https://github.com/ecrc/qdwh.git":[260],"https://github.com/ecrc/ksvd.git,":[262],"have":[265],"been":[266],"integrated":[267],"into":[268],"Cray":[270],"Scientific":[271],"numerical":[272],"library":[273],"LibSci":[274],"v17.11.1.":[275]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
