{"id":"https://openalex.org/W2122427868","doi":"https://doi.org/10.1109/clustr.2008.4663801","title":"A dynamic programming approach to optimizing the blocking strategy for the Householder QR decomposition","display_name":"A dynamic programming approach to optimizing the blocking strategy for the Householder QR decomposition","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2122427868","doi":"https://doi.org/10.1109/clustr.2008.4663801","mag":"2122427868"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2008.4663801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2008.4663801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055706373","display_name":"Takeshi Fukaya","orcid":"https://orcid.org/0000-0003-1217-6444"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Fukaya","raw_affiliation_strings":["Graduate School of Engineering, Nagoya University","Grad. Sch. of Eng., Nagoya Univ., Nagoya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Nagoya University","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Nagoya Univ., Nagoya","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103155193","display_name":"Yusaku Yamamoto","orcid":"https://orcid.org/0000-0001-5682-3434"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusaku Yamamoto","raw_affiliation_strings":["Graduate School of Engineering, Nagoya University","Grad. Sch. of Eng., Nagoya Univ., Nagoya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Nagoya University","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Nagoya Univ., Nagoya","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103141271","display_name":"Shao\u2010Liang Zhang","orcid":"https://orcid.org/0000-0002-6547-3525"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shao-Liang Zhang","raw_affiliation_strings":["Graduate School of Engineering, Nagoya University","Grad. Sch. of Eng., Nagoya Univ., Nagoya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Nagoya University","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Nagoya Univ., Nagoya","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4671","issue":null,"first_page":"402","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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/blocking","display_name":"Blocking (statistics)","score":0.8963816165924072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7889627814292908},{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.699895977973938},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6891757249832153},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.665870726108551},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.624890148639679},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.493203341960907},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4772196412086487},{"id":"https://openalex.org/keywords/block-size","display_name":"Block size","score":0.47526925802230835},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4596085548400879},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4339067339897156},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41616740822792053},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3034116327762604},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.14488324522972107},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13405227661132812},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09396839141845703},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0797387957572937}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.8963816165924072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889627814292908},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.699895977973938},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6891757249832153},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.665870726108551},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.624890148639679},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.493203341960907},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4772196412086487},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.47526925802230835},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4596085548400879},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4339067339897156},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41616740822792053},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3034116327762604},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.14488324522972107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13405227661132812},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09396839141845703},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0797387957572937},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clustr.2008.4663801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2008.4663801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1505753777","https://openalex.org/W1551177513","https://openalex.org/W1552910341","https://openalex.org/W1593783515","https://openalex.org/W1973305402","https://openalex.org/W1981745143","https://openalex.org/W2002257715","https://openalex.org/W2032052535","https://openalex.org/W2039778940","https://openalex.org/W2128344236","https://openalex.org/W2136952590","https://openalex.org/W2138003372","https://openalex.org/W2341171179","https://openalex.org/W4244968939"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W135623081"],"abstract_inverted_index":{"In":[0,18],"this":[1,85,117,153,162],"paper,":[2],"we":[3,119,143,164],"present":[4],"a":[5,32,92,122,129,149,159,201],"new":[6,123],"approach":[7],"to":[8,30,73,147],"optimizing":[9],"the":[10,14,23,36,40,51,63,67,74,78,101,178,197],"blocking":[11,33,48,53,98,134,168,194],"strategy":[12,151,169,186],"for":[13,35],"householder":[15,24],"QR":[16,25,198],"decomposition.":[17],"high":[19],"performance":[20,103],"implementations":[21],"of":[22,39,87,95,105,133,161,200],"algorithm,":[26],"it":[27],"is":[28],"common":[29],"use":[31,38],"technique":[34],"efficient":[37],"cache":[41],"memory.":[42],"There":[43],"are":[44,70],"several":[45],"well":[46],"known":[47],"strategies":[49,82,109,135],"like":[50],"fixed-size":[52],"and":[54,57,66,77,180],"recursive":[55,193],"blocking,":[56],"usually":[58],"their":[59],"parameters":[60],"such":[61],"as":[62],"block":[64],"size":[65],"recursion":[68],"level":[69],"tuned":[71],"according":[72],"target":[75],"machine":[76],"problem":[79],"size.":[80],"However,":[81],"generated":[83],"with":[84],"kind":[86],"parameter":[88],"optimization":[89],"constitute":[90],"only":[91],"small":[93],"fraction":[94],"all":[96],"possible":[97],"strategies.":[99],"Given":[100],"complex":[102],"characteristics":[104],"modern":[106],"microprocessors,":[107],"non-standard":[108],"may":[110],"prove":[111],"effective":[112,167],"on":[113,177],"some":[114],"machines.":[115],"Considering":[116],"situation,":[118],"first":[120],"propose":[121],"universal":[124],"model":[125],"that":[126,170,184],"can":[127],"express":[128],"far":[130],"larger":[131],"class":[132,154],"than":[136],"has":[137,171],"been":[138,173],"considered":[139],"so":[140],"far.":[141],"Next,":[142],"give":[144],"an":[145,166],"algorithm":[146],"find":[148],"near-optimal":[150],"from":[152],"using":[155],"dynamic":[156],"programming.":[157],"As":[158],"result":[160],"approach,":[163],"found":[165],"never":[172],"reported.":[174],"Performance":[175],"evaluation":[176],"Opteron":[179],"Core2":[181],"processors":[182],"show":[183],"our":[185],"achieves":[187],"about":[188],"1.2":[189],"times":[190,203],"speedup":[191],"over":[192],"when":[195],"computing":[196],"decomposition":[199],"6000":[202,204],"matrix.":[205]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}