{"id":"https://openalex.org/W2014260564","doi":"https://doi.org/10.1142/s0129626414420043","title":"Design and Implementation of a Large Scale Tree-Based QR Decomposition Using a 3D Virtual Systolic Array and a Lightweight Runtime","display_name":"Design and Implementation of a Large Scale Tree-Based QR Decomposition Using a 3D Virtual Systolic Array and a Lightweight Runtime","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2014260564","doi":"https://doi.org/10.1142/s0129626414420043","mag":"2014260564"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626414420043","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414420043","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","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/A5052397462","display_name":"Ichitaro Yamazaki","orcid":"https://orcid.org/0000-0002-6196-2508"},"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":"Ichitaro Yamazaki","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee 37996-3450, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee 37996-3450, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"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":"Jakub Kurzak","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee 37996-3450, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee 37996-3450, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"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, Tennessee 37996-3450, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee 37996-3450, USA","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/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, USA","University of Manchester, Manchester, M13 9PL, UK","University of Tennessee, Knoxville, Tennessee 37996-3450, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"University of Manchester, Manchester, M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee 37996-3450, USA","institution_ids":["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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08926216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"04","first_page":"1442004","last_page":"1442004"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/systolic-array","display_name":"Systolic array","score":0.8359635472297668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266162037849426},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6364389657974243},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6080007553100586},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.5797159671783447},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44277626276016235},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41231662034988403},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.20268335938453674},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.12687325477600098},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10417038202285767}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.8359635472297668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266162037849426},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6364389657974243},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6080007553100586},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.5797159671783447},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44277626276016235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41231662034988403},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.20268335938453674},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.12687325477600098},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10417038202285767},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1142/s0129626414420043","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414420043","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.637.8091","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.637.8091","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/prt_qr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1494445573","https://openalex.org/W1978319530","https://openalex.org/W1988888548","https://openalex.org/W2028267160","https://openalex.org/W2033614580","https://openalex.org/W2158140132","https://openalex.org/W2165904264","https://openalex.org/W2253535924","https://openalex.org/W2528483095","https://openalex.org/W3210998770","https://openalex.org/W4205190765"],"related_works":["https://openalex.org/W2126436096","https://openalex.org/W1986431723","https://openalex.org/W2365845987","https://openalex.org/W3029568918","https://openalex.org/W2188022358","https://openalex.org/W2020196933","https://openalex.org/W3215706942","https://openalex.org/W2023656250","https://openalex.org/W2032632402","https://openalex.org/W2405661381"],"abstract_inverted_index":{"A":[0],"systolic":[1,35,64,106,138],"array":[2,36,65,107,139],"provides":[3],"an":[4,45,154,173],"alternative":[5],"computing":[6],"paradigm":[7,21],"to":[8,22,44,66,143,166],"the":[9,27,34,95,120],"von":[10],"Neumann":[11],"architecture.":[12],"Though":[13],"its":[14],"hardware":[15],"implementation":[16,78],"has":[17],"failed":[18],"as":[19,37,116],"a":[20,38,61,68,73,82,87,91,98,103,113,117,132,144,159,168],"design":[23,58],"integrated":[24],"circuits":[25],"in":[26,54,178],"past,":[28],"we":[29,57,101,129],"are":[30],"now":[31],"discovering":[32],"that":[33,85],"software":[39],"virtualization":[40],"layer":[41],"can":[42,140],"lead":[43],"extremely":[46],"scalable":[47],"execution":[48],"paradigm.":[49],"To":[50],"demonstrate":[51,130],"this":[52,55,110],"scalability,":[53],"paper,":[56],"and":[59,147,181],"implement":[60],"3D":[62],"virtual":[63,105,137],"compute":[67,167],"tile":[69],"QR":[70,160],"decomposition":[71,161],"of":[72,97,119,172],"tall-and-skinny":[74],"dense":[75],"matrix.":[76],"Our":[77],"is":[79,153,162],"based":[80,89],"on":[81,90,131],"state-of-the-art":[83],"algorithm":[84],"factorizes":[86],"panel":[88],"tree-reduction.":[92],"Freed":[93],"from":[94],"constraint":[96],"planar":[99],"layout,":[100],"present":[102],"three-dimensional":[104],"architecture":[108],"for":[109,164],"algorithm.":[111],"Using":[112],"runtime":[114],"developed":[115],"part":[118],"Parallel":[121],"Ultra":[122],"Light":[123],"Systolic":[124],"Array":[125],"Runtime":[126],"(PULSAR)":[127],"project,":[128],"Cray-XT5":[133],"machine":[134,146],"how":[135],"our":[136],"be":[141],"mapped":[142],"large-scale":[145],"obtain":[148],"excellent":[149],"parallel":[150],"performance.":[151],"This":[152],"important":[155],"contribution":[156],"since":[157],"such":[158],"used,":[163],"example,":[165],"least":[169],"squares":[170],"solution":[171],"overdetermined":[174],"system,":[175],"which":[176],"arises":[177],"many":[179],"scientific":[180],"engineering":[182],"problems.":[183]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
