{"id":"https://openalex.org/W3161672423","doi":"https://doi.org/10.1145/3447775","title":"Acceleration of Parallel-Blocked QR Decomposition of Tall-and-Skinny Matrices on FPGAs","display_name":"Acceleration of Parallel-Blocked QR Decomposition of Tall-and-Skinny Matrices on FPGAs","publication_year":2021,"publication_date":"2021-05-10","ids":{"openalex":"https://openalex.org/W3161672423","doi":"https://doi.org/10.1145/3447775","mag":"3161672423"},"language":"en","primary_location":{"id":"doi:10.1145/3447775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447775","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447775","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011946728","display_name":"Jos\u00e9 M. Rodr\u0131\u0301guez-Borb\u00f3n","orcid":"https://orcid.org/0000-0002-1041-0017"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jose M. Rodriguez Borbon","raw_affiliation_strings":["University of California, Riverside"],"raw_orcid":"https://orcid.org/0000-0002-1041-0017","affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101920007","display_name":"Junjie Huang","orcid":"https://orcid.org/0000-0002-6761-7967"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["University of California, Riverside"],"raw_orcid":"https://orcid.org/0000-0002-6761-7967","affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022569738","display_name":"Bryan M. Wong","orcid":"https://orcid.org/0000-0002-3477-8043"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan M. Wong","raw_affiliation_strings":["University of California, Riverside"],"raw_orcid":"https://orcid.org/0000-0002-3477-8043","affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033921328","display_name":"Walid Najjar","orcid":"https://orcid.org/0000-0001-6761-6801"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walid Najjar","raw_affiliation_strings":["University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011946728"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.4542,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66925433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"18","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9994999766349792,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9994999766349792,"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":0.9994000196456909,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9929999709129333,"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/flops","display_name":"FLOPS","score":0.8127445578575134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737417221069336},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.7601978778839111},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7049073576927185},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5919542908668518},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5151556730270386},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4806974530220032},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4726378321647644},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4642563462257385},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.462856650352478},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.43786412477493286},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4316532015800476},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29239892959594727},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2290845513343811},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.2190980613231659},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.17241883277893066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10945850610733032}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8127445578575134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737417221069336},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7601978778839111},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7049073576927185},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5919542908668518},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5151556730270386},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4806974530220032},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4726378321647644},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4642563462257385},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.462856650352478},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.43786412477493286},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4316532015800476},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29239892959594727},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2290845513343811},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.2190980613231659},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.17241883277893066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10945850610733032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447775","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3447775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447775","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8899999856948853}],"awards":[{"id":"https://openalex.org/G3311519749","display_name":null,"funder_award_id":"N00014-18-1-2740","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161672423.pdf","grobid_xml":"https://content.openalex.org/works/W3161672423.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W82325001","https://openalex.org/W182691100","https://openalex.org/W1587654378","https://openalex.org/W1597755753","https://openalex.org/W1961751213","https://openalex.org/W1973855976","https://openalex.org/W1986431723","https://openalex.org/W1999085092","https://openalex.org/W2006808488","https://openalex.org/W2012366931","https://openalex.org/W2013417994","https://openalex.org/W2049009664","https://openalex.org/W2064872546","https://openalex.org/W2073260424","https://openalex.org/W2076804384","https://openalex.org/W2078095679","https://openalex.org/W2092590148","https://openalex.org/W2097095666","https://openalex.org/W2105572413","https://openalex.org/W2111221242","https://openalex.org/W2113755305","https://openalex.org/W2117060831","https://openalex.org/W2124408528","https://openalex.org/W2133545594","https://openalex.org/W2135120170","https://openalex.org/W2139116943","https://openalex.org/W2154641788","https://openalex.org/W2157237396","https://openalex.org/W2161761794","https://openalex.org/W2162322364","https://openalex.org/W2188922879","https://openalex.org/W2561675875","https://openalex.org/W2587930272","https://openalex.org/W2789139117","https://openalex.org/W3013247086","https://openalex.org/W3103104567","https://openalex.org/W4210921710","https://openalex.org/W6675996895"],"related_works":["https://openalex.org/W3150370983","https://openalex.org/W2239119680","https://openalex.org/W2023965391","https://openalex.org/W2156524298","https://openalex.org/W3177218348","https://openalex.org/W2065321717","https://openalex.org/W3097256929","https://openalex.org/W17610788","https://openalex.org/W2013660188","https://openalex.org/W2172042531"],"abstract_inverted_index":{"QR":[0,110,117,144],"decomposition":[1,19],"is":[2,207],"one":[3],"of":[4,20,73,102,122,129,174,198],"the":[5,18,71,161,186],"most":[6],"useful":[7],"factorization":[8],"kernels":[9],"in":[10,27],"modern":[11],"numerical":[12,39],"linear":[13],"algebra":[14],"algorithms.":[15],"In":[16,85,200],"particular,":[17],"tall-and-skinny":[21],"matrices":[22],"(TSMs)":[23],"has":[24,95],"major":[25],"applications":[26,51],"areas":[28],"including":[29],"scientific":[30],"computing,":[31],"machine":[32],"learning,":[33],"image":[34],"processing,":[35],"wireless":[36],"networks,":[37],"and":[38,43,57,149],"methods.":[40],"Traditionally,":[41],"CPUs":[42,148],"GPUs":[44],"have":[45],"achieved":[46,103],"better":[47],"throughput":[48],"on":[49,113,147,166,191],"these":[50],"by":[52,171,195],"using":[53],"large":[54],"cache":[55],"hierarchies":[56],"compute":[58],"cores":[59],"running":[60,112,146,165,190],"at":[61],"a":[62,81,90,96,172,192,196],"high":[63,67,98],"frequency,":[64],"leading":[65],"to":[66,104,108,202,213],"power":[68],"consumption.":[69],"With":[70],"advent":[72],"heterogeneous":[74],"platforms,":[75],"however,":[76],"FPGAs":[77],"are":[78],"emerging":[79],"as":[80],"promising":[82],"viable":[83],"alternative.":[84],"this":[86],"work,":[87],"we":[88],"propose":[89],"high-throughput":[91],"FPGA-based":[92],"engine":[93],"that":[94,137],"very":[97],"computational":[99],"efficiency":[100,121,128],"(ratio":[101],"peak":[105],"throughput)":[106],"compared":[107],"similar":[109],"solvers":[111,118,145],"FPGAs.":[114],"Although":[115],"comparable":[116],"achieve":[119],"an":[120,127,167],"36%,":[123],"our":[124,133,138,158,183,205,217],"design":[125,139,159,184,206,218],"exhibits":[126],"54%.":[130],"For":[131,151,176],"TSMs,":[132],"experimental":[134],"results":[135],"show":[136],"can":[140],"outperform":[141],"highly":[142],"optimized":[143],"GPUs.":[150],"TSMs":[152,177],"with":[153],"more":[154,220],"than":[155,221],"50K":[156],"rows,":[157],"outperforms":[160,185],"Intel":[162,168],"MKL":[163],"solver":[164,189],"quad-core":[169],"processor":[170],"factor":[173,197],"1.5\u00d7.":[175],"containing":[178],"256":[179],"columns":[180],"or":[181],"less,":[182],"NVIDIA":[187],"CUBLAS":[188],"K40":[193],"GPU":[194],"3.0\u00d7.":[199],"addition":[201],"being":[203],"fast,":[204],"energy":[208],"efficient\u2014competing":[209],"platforms":[210],"execute":[211],"up":[212],"0.6":[214],"GFLOPS/Joule,":[215],"whereas":[216],"executes":[219],"1.0":[222],"GFLOPS/Joule.":[223]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}