{"id":"https://openalex.org/W2082171474","doi":"https://doi.org/10.1109/fpl.2012.6339142","title":"Enhancing performance of Tall-Skinny QR factorization using FPGAs","display_name":"Enhancing performance of Tall-Skinny QR factorization using FPGAs","publication_year":2012,"publication_date":"2012-08-01","ids":{"openalex":"https://openalex.org/W2082171474","doi":"https://doi.org/10.1109/fpl.2012.6339142","mag":"2082171474"},"language":"en","primary_location":{"id":"doi:10.1109/fpl.2012.6339142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2012.6339142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Conference on Field Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/81242/1/Enhancing%20performance%20of%20Tall-Skinny%20QR%20factorization%20using%20FPGAs.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029208880","display_name":"Abid Rafique","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Abid Rafique","raw_affiliation_strings":["Electrical and Electronic Engineering Department, Imperial College London, London, UK","Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering Department, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015534628","display_name":"Nachiket Kapre","orcid":"https://orcid.org/0000-0002-2187-0406"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nachiket Kapre","raw_affiliation_strings":["Electrical and Electronic Engineering Department, Imperial College London, London, UK","Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering Department, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029829952","display_name":"George A. Constantinides","orcid":"https://orcid.org/0000-0002-0201-310X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"George A. Constantinides","raw_affiliation_strings":["Electrical and Electronic Engineering Department, Imperial College London, London, UK","Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering Department, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Electrical & Electronic Engineering Department, Imperial College, London, UK#TAB#","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029208880"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":2.6349,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89905933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996999979019165,"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":0.996999979019165,"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":0.994700014591217,"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/T10232","display_name":"Optical Network Technologies","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.7786277532577515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7637622952461243},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6818194389343262},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5597262978553772},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5570618510246277},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5169931650161743},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5019702911376953},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.49274399876594543},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4647957682609558},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4299084544181824},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.413756787776947},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2200239896774292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19589224457740784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1642799973487854}],"concepts":[{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7786277532577515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637622952461243},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6818194389343262},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5597262978553772},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5570618510246277},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5169931650161743},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5019702911376953},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.49274399876594543},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4647957682609558},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4299084544181824},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.413756787776947},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2200239896774292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19589224457740784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1642799973487854},{"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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fpl.2012.6339142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2012.6339142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Conference on Field Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/81242","is_oa":true,"landing_page_url":"http://hdl.handle.net/10220/39153","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/81242/1/Enhancing%20performance%20of%20Tall-Skinny%20QR%20factorization%20using%20FPGAs.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.385.7567","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cas.ee.ic.ac.uk/people/gac1/pubs/AbidFPL12.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/81242","is_oa":true,"landing_page_url":"http://hdl.handle.net/10220/39153","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/81242/1/Enhancing%20performance%20of%20Tall-Skinny%20QR%20factorization%20using%20FPGAs.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5524266619","display_name":null,"funder_award_id":"EP/I020357/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6787767956","display_name":null,"funder_award_id":"EP/G031576/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2082171474.pdf","grobid_xml":"https://content.openalex.org/works/W2082171474.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W594283781","https://openalex.org/W1907157228","https://openalex.org/W2039778940","https://openalex.org/W2047614366","https://openalex.org/W2111221242","https://openalex.org/W2126051700","https://openalex.org/W2133545594","https://openalex.org/W2906444339","https://openalex.org/W2951443864","https://openalex.org/W2951500637","https://openalex.org/W4302564868","https://openalex.org/W6662378236","https://openalex.org/W6757384154"],"related_works":["https://openalex.org/W160834089","https://openalex.org/W2112488134","https://openalex.org/W2142486491","https://openalex.org/W2887888236","https://openalex.org/W2391999311","https://openalex.org/W2919544312","https://openalex.org/W2030640282","https://openalex.org/W2152666498","https://openalex.org/W2023965391","https://openalex.org/W2021525945"],"abstract_inverted_index":{"Communication-avoiding":[0],"linear":[1,56,174],"algebra":[2,57,175],"algorithms":[3],"with":[4,149],"low":[5],"communication":[6,85,127],"latency":[7,86],"and":[8,45,83,98,117,155,161,185],"high":[9],"memory":[10,77],"bandwidth":[11,78],"requirements":[12],"like":[13,177],"Tall-Skinny":[14],"QR":[15,27,43,81,115,151],"factorization":[16,28,152],"(TSQR)":[17],"are":[18],"highly":[19],"appropriate":[20],"for":[21,113,180,183,187],"acceleration":[22],"using":[23,109],"FPGAs.":[24],"TSQR":[25,52],"parallelizes":[26],"of":[29,71,95,136,145],"tall-skinny":[30],"matrices":[31],"in":[32,79,87],"a":[33,54,131],"divide-and-conquer":[34],"fashion":[35],"by":[36,75,108,118],"decomposing":[37],"them":[38],"into":[39],"sub-matrices,":[40],"performing":[41,119],"local":[42,80,114],"factorizations":[44,82,116],"then":[46],"merging":[47],"the":[48,69,76,88,93,96,120],"intermediate":[49],"results.":[50],"As":[51],"is":[53,73],"dense":[55],"problem,":[58],"one":[59],"would":[60],"therefore":[61],"imagine":[62],"GPU":[63,72,156],"to":[64,125,159],"show":[65,168],"better":[66],"performance.":[67],"However,":[68],"performance":[70,135,171],"limited":[74],"global":[84],"merge":[89,121],"stage.":[90],"We":[91,129],"exploit":[92],"shape":[94],"matrix":[97],"propose":[99],"an":[100],"FPGA-based":[101],"custom":[102],"architecture":[103],"which":[104],"avoids":[105],"these":[106],"bottlenecks":[107],"high-bandwidth":[110],"on-chip":[111,124],"memories":[112],"stage":[122],"entirely":[123],"reduce":[126],"latency.":[128],"achieve":[130],"peak":[132],"double-precision":[133],"floating-point":[134],"129":[137],"GFLOPs":[138],"on":[139,153],"Virtex-6":[140],"SX475T.":[141],"A":[142],"quantitative":[143],"comparison":[144],"our":[146],"proposed":[147],"design":[148],"recent":[150],"FPGAs":[154],"shows":[157],"up":[158,164],"7.7\u00d7":[160],"12.7\u00d7":[162],"speed":[163],"respectively.":[165],"Additionally,":[166],"we":[167],"even":[169],"higher":[170],"over":[172],"optimized":[173],"libraries":[176],"Intel":[178],"MKL":[179],"multi-cores,":[181],"CULA":[182],"GPUs":[184],"MAGMA":[186],"hybrid":[188],"systems.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}