{"id":"https://openalex.org/W2789139117","doi":"https://doi.org/10.1145/3174243.3174273","title":"High-Performance QR Decomposition for FPGAs","display_name":"High-Performance QR Decomposition for FPGAs","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2789139117","doi":"https://doi.org/10.1145/3174243.3174273","mag":"2789139117"},"language":"en","primary_location":{"id":"doi:10.1145/3174243.3174273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-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/A5082265695","display_name":"Martin Langhammer","orcid":"https://orcid.org/0000-0001-8206-2077"},"institutions":[{"id":"https://openalex.org/I2801054121","display_name":"Coeliac UK","ror":"https://ror.org/042404z19","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2801054121"]},{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Langhammer","raw_affiliation_strings":["Intel, High Wycombe, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Intel, High Wycombe, United Kingdom","institution_ids":["https://openalex.org/I2801054121","https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010739346","display_name":"Bogdan Pasca","orcid":"https://orcid.org/0000-0002-5454-4375"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogdan Pasca","raw_affiliation_strings":["Intel, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Intel, Toulouse, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082265695"],"corresponding_institution_ids":["https://openalex.org/I2801054121","https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":2.2213,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89090909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.9980999827384949,"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":0.7786769270896912},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7245405316352844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724252462387085},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4862474203109741},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4775153696537018},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4705241918563843},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4561540186405182},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4212948679924011},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21551692485809326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17764389514923096},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.14876273274421692}],"concepts":[{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7786769270896912},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7245405316352844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724252462387085},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4862474203109741},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4775153696537018},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4705241918563843},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4561540186405182},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4212948679924011},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21551692485809326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17764389514923096},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.14876273274421692},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3174243.3174273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W26412246","https://openalex.org/W1587654378","https://openalex.org/W1986431723","https://openalex.org/W2097095666","https://openalex.org/W2107971525","https://openalex.org/W2111390700","https://openalex.org/W2133427951","https://openalex.org/W2159642127","https://openalex.org/W2336406473","https://openalex.org/W2559893684","https://openalex.org/W2575651515","https://openalex.org/W2587930272","https://openalex.org/W2751025608","https://openalex.org/W4230460269"],"related_works":["https://openalex.org/W2012366931","https://openalex.org/W2078349096","https://openalex.org/W2002598339","https://openalex.org/W3028347934","https://openalex.org/W2150953077","https://openalex.org/W1599936522","https://openalex.org/W2185692674","https://openalex.org/W2006707200","https://openalex.org/W3200716635","https://openalex.org/W4285580088"],"abstract_inverted_index":{"QR":[0],"decomposition":[1],"(QRD)":[2],"is":[3,133],"of":[4,32,63,84,140,180],"increasing":[5],"importance":[6],"for":[7,129,156,163,177,184],"many":[8,31],"current":[9],"applications,":[10],"such":[11],"as":[12,58,60],"wireless":[13],"and":[14,21,52,114],"radar.":[15],"Data":[16],"dependencies":[17],"in":[18,30,39,53],"known":[19,144],"algorithms":[20],"approaches,":[22],"combined":[23],"with":[24,55,81],"the":[25,36,61,76,105,137,141,178,181],"data":[26],"access":[27],"patterns":[28],"used":[29,183],"these":[33],"methods,":[34],"restrict":[35],"achievable":[37],"performance":[38,125],"software":[40],"programmable":[41],"targets.":[42],"Some":[43],"FPGA":[44],"architectures":[45],"now":[46],"incorporate":[47],"hard":[48],"floating-point":[49],"(HFP)":[50],"resources,":[51],"combination":[54],"distributed":[56],"memories,":[57],"well":[59],"flexibility":[62],"internal":[64],"connectivity,":[65],"can":[66],"support":[67],"high-performance":[68],"matrix":[69],"arithmetic.":[70],"In":[71],"this":[72,96,185],"work,":[73],"we":[74,153],"present":[75],"mapping":[77],"to":[78,127,147,170,174],"parallel":[79],"structures":[80],"inter-vector":[82],"connectivity":[83],"a":[85,91,100,122,157,164,171],"new":[86,97],"QRD":[87],"algorithm.":[88],"Based":[89],"on":[90],"Modified":[92],"Gram-Schmidt":[93],"(MGS)":[94],"algorithm,":[95],"algorithm":[98],"has":[99,121],"different":[101],"loop":[102],"organization,":[103],"but":[104],"dependent":[106],"functional":[107,138],"sequences":[108],"are":[109,117],"unchanged,":[110],"so":[111],"error":[112],"analysis":[113],"numerical":[115],"stability":[116],"unaffected.":[118],"This":[119,168],"work":[120],"theoretical":[123],"sustained-to-peak":[124],"close":[126],"100%":[128],"large":[130],"matrices,":[131],"which":[132],"roughly":[134],"three":[135],"times":[136],"density":[139],"previously":[142],"best":[143],"implementations.":[145],"Mapped":[146],"an":[148],"Intel":[149],"Arria":[150],"10":[151],"device,":[152],"achieve":[154],"80us":[155],"256x256":[158],"single":[159],"precision":[160],"real":[161],"matrix,":[162],"417":[165],"GFLOP":[166],"equivalent.":[167],"corresponds":[169],"95%":[172],"sustained":[173],"peak":[175],"ratio,":[176],"portion":[179],"device":[182],"work.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-12-13T23:11:00.310470","created_date":"2025-10-10T00:00:00"}