{"id":"https://openalex.org/W2057204994","doi":"https://doi.org/10.1145/2450153.2450154","title":"High-performance bidiagonal reduction using tile algorithms on homogeneous multicore architectures","display_name":"High-performance bidiagonal reduction using tile algorithms on homogeneous multicore architectures","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2057204994","doi":"https://doi.org/10.1145/2450153.2450154","mag":"2057204994"},"language":"en","primary_location":{"id":"doi:10.1145/2450153.2450154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2450153.2450154","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/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":["KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, Knoxville, TN","University of Tennessee, Knoxville, TN;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, TN;","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Oak Ridge National Laboratory, and University of Manchester, Knoxville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Oak Ridge National Laboratory, and University of Manchester, Knoxville, TN","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2139,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96237359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"39","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7559184432029724},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6576672792434692},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6152477264404297},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5727227926254272},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1719900667667389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559184432029724},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6576672792434692},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6152477264404297},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5727227926254272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1719900667667389},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2450153.2450154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2450153.2450154","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:CiteSeerX.psu:10.1.1.228.8934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.8934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/lawn247.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.5604","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.5604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.utk.edu/~luszczek/pubs/gebrdtoms.pdf","raw_type":"text"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/575572","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/575572","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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W94439627","https://openalex.org/W1481082265","https://openalex.org/W1492601037","https://openalex.org/W1494445573","https://openalex.org/W1555915743","https://openalex.org/W1576347883","https://openalex.org/W1584723861","https://openalex.org/W1842923156","https://openalex.org/W1991973947","https://openalex.org/W1996369530","https://openalex.org/W1998492046","https://openalex.org/W1999600349","https://openalex.org/W2008942408","https://openalex.org/W2013417994","https://openalex.org/W2021178437","https://openalex.org/W2030167104","https://openalex.org/W2039937805","https://openalex.org/W2041797552","https://openalex.org/W2064733273","https://openalex.org/W2071128523","https://openalex.org/W2077166865","https://openalex.org/W2078841894","https://openalex.org/W2080710904","https://openalex.org/W2087716616","https://openalex.org/W2092590148","https://openalex.org/W2095597068","https://openalex.org/W2099083833","https://openalex.org/W2107410315","https://openalex.org/W2107864772","https://openalex.org/W2113277707","https://openalex.org/W2119522963","https://openalex.org/W2124480634","https://openalex.org/W2145960411","https://openalex.org/W2168457205","https://openalex.org/W2168612748","https://openalex.org/W2169378749","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4237384699","https://openalex.org/W4320800818"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2352590024"],"abstract_inverted_index":{"This":[0,13],"article":[1,14,81],"presents":[2],"a":[3,50,107,157,178,240,254,258,264],"new":[4,248],"high-performance":[5,20,150,249],"bidiagonal":[6,146],"reduction":[7,22,109,231],"(BRD)":[8],"for":[9,153],"homogeneous":[10],"multicore":[11],"architectures.":[12],"is":[15,39,53,205],"an":[16,99],"extension":[17],"of":[18,49,55,75,86,116,212,232],"the":[19,25,34,40,45,56,76,84,117,120,135,139,164,172,185,190,196,209,213,217,225,230,233,270],"tridiagonal":[21],"implemented":[23,187],"by":[24,148],"same":[26],"authors":[27],"[Luszczek":[28],"et":[29],"al.,":[30],"IPDPS":[31],"2011]":[32],"to":[33,65,113,124,129,145,207,224,253],"BRD":[35,38,77,250],"case.":[36],"The":[37,72,236,247],"first":[41,121,234],"step":[42],"toward":[43],"computing":[44],"singular":[46],"value":[47],"decomposition":[48],"matrix,":[51],"which":[52,97,221],"one":[54],"most":[57,115],"important":[58,88],"algorithms":[59,92],"in":[60,69,79,103],"numerical":[61,276],"linear":[62],"algebra":[63],"due":[64],"its":[66],"broad":[67],"impact":[68,211],"computational":[70],"science.":[71],"high":[73],"performance":[74,237],"described":[78],"this":[80],"comes":[82],"from":[83,143,287],"combination":[85],"four":[87],"features:":[89],"(1)":[90],"tile":[91,94,173,214],"with":[93,167,263,282],"data":[95,101,158,169,174,197],"layout,":[96],"provide":[98],"efficient":[100],"representation":[102],"main":[104],"memory;":[105],"(2)":[106],"two-stage":[108],"approach":[110],"that":[111,162,182,195],"allows":[112],"cast":[114],"computation":[118],"during":[119,138],"stage":[122,141],"(reduction":[123,142],"band":[125,144],"form)":[126,147],"into":[127,171],"calls":[128],"Level":[130],"3":[131],"BLAS":[132,286],"and":[133,176,193,274,284],"reduces":[134],"memory":[136],"traffic":[137],"second":[140],"using":[149],"kernels":[151,188],"optimized":[152,283],"cache":[154],"reuse;":[155],"(3)":[156],"dependence":[159],"translation":[160],"layer":[161],"maps":[163],"general":[165],"algorithm":[166],"column-major":[168],"layout":[170],"layout;":[175],"(4)":[177],"dynamic":[179],"runtime":[180],"system":[181],"efficiently":[183],"schedules":[184],"newly":[186],"across":[189],"processing":[191],"units":[192],"ensures":[194],"dependencies":[198],"are":[199],"not":[200],"violated.":[201],"A":[202],"detailed":[203],"analysis":[204],"provided":[206],"understand":[208],"critical":[210],"size":[215,228,268],"on":[216,257],"total":[218],"execution":[219],"time,":[220],"also":[222],"corresponds":[223],"matrix":[226,267],"bandwidth":[227],"after":[229],"stage.":[235],"results":[238],"show":[239],"significant":[241],"improvement":[242],"over":[243],"currently":[244],"established":[245],"alternatives.":[246],"achieves":[251],"up":[252],"30-fold":[255],"speedup":[256],"16-core":[259],"Intel":[260,292],"Xeon":[261],"machine":[262],"12000\u00d7":[265],"12000":[266],"against":[269],"state-of-the-art":[271],"open":[272],"source":[273],"commercial":[275],"software":[277],"packages,":[278],"namely":[279],"LAPACK,":[280],"compiled":[281],"multithreaded":[285],"MKL":[288,293],"as":[289,291],"well":[290],"version":[294],"10.2.":[295]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"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":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}