{"id":"https://openalex.org/W3037775421","doi":"https://doi.org/10.1145/3369583.3392685","title":"High Accuracy Matrix Computations on Neural Engines: A Study of QR Factorization and its Applications","display_name":"High Accuracy Matrix Computations on Neural Engines: A Study of QR Factorization and its Applications","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3037775421","doi":"https://doi.org/10.1145/3369583.3392685","mag":"3037775421"},"language":"en","primary_location":{"id":"doi:10.1145/3369583.3392685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3392685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing","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/A5091290657","display_name":"Shaoshuai Zhang","orcid":"https://orcid.org/0000-0002-9525-1659"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaoshuai Zhang","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058138886","display_name":"Elaheh Baharlouei","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaheh Baharlouei","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020822198","display_name":"Panruo Wu","orcid":"https://orcid.org/0000-0003-1859-3580"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panruo Wu","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091290657"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":1.3862,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80023229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9965999722480774,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/artificial-neural-network","display_name":"Artificial neural network","score":0.7278285026550293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249020338058472},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5479075312614441},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5383684635162354},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5121264457702637},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.46205204725265503},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4610893130302429},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4320065379142761},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41714048385620117},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.41194069385528564},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3953104019165039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36767616868019104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24672240018844604}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7278285026550293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249020338058472},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5479075312614441},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5383684635162354},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5121264457702637},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.46205204725265503},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4610893130302429},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4320065379142761},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41714048385620117},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.41194069385528564},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3953104019165039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36767616868019104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24672240018844604},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3369583.3392685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3392685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W36826159","https://openalex.org/W1558296484","https://openalex.org/W1576347883","https://openalex.org/W1750594686","https://openalex.org/W2005498993","https://openalex.org/W2014724759","https://openalex.org/W2018192914","https://openalex.org/W2020804487","https://openalex.org/W2021039675","https://openalex.org/W2024015221","https://openalex.org/W2032052535","https://openalex.org/W2039778940","https://openalex.org/W2052087587","https://openalex.org/W2073260424","https://openalex.org/W2092590148","https://openalex.org/W2093529653","https://openalex.org/W2097897435","https://openalex.org/W2111221242","https://openalex.org/W2157237396","https://openalex.org/W2316564661","https://openalex.org/W2599973081","https://openalex.org/W2752879223","https://openalex.org/W2763827516","https://openalex.org/W2765439756","https://openalex.org/W2796649226","https://openalex.org/W2798909945","https://openalex.org/W2808102735","https://openalex.org/W2895305554","https://openalex.org/W2901549770","https://openalex.org/W2903589674","https://openalex.org/W2949136722","https://openalex.org/W3101543398","https://openalex.org/W3104528661","https://openalex.org/W3130391092","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4233049725","https://openalex.org/W4240959780","https://openalex.org/W4320800818"],"related_works":["https://openalex.org/W2078349096","https://openalex.org/W2002598339","https://openalex.org/W2150953077","https://openalex.org/W1599936522","https://openalex.org/W2006707200","https://openalex.org/W3200716635","https://openalex.org/W4388311419","https://openalex.org/W3093858099","https://openalex.org/W3215209251","https://openalex.org/W2016659453"],"abstract_inverted_index":{"Fueled":[0],"by":[1,136],"the":[2,14,53,122],"surge":[3],"of":[4,9,57,84],"ever":[5],"expanding":[6],"successful":[7],"applications":[8,72],"deep":[10,58],"neural":[11,59,65,75,93,131],"networks":[12],"and":[13,22,34,45,55,86,107,117,128,139],"great":[15],"computational":[16],"power":[17],"demanded,":[18],"modern":[19],"computer":[20],"processors":[21],"accelerators":[23],"are":[24,134],"beginning":[25],"to":[26,51,100,104],"offer":[27],"half":[28],"precision":[29],"floating":[30],"point":[31],"arithmetic":[32],"support,":[33],"special":[35],"units":[36],"(neural":[37],"engines)":[38],"such":[39],"as":[40],"NVIDIA":[41],"TensorCore":[42],"on":[43,92,130],"GPU":[44],"Google":[46],"Tensor":[47],"Processing":[48],"Unit":[49],"(TPU)":[50],"accelerate":[52],"training":[54],"prediction":[56],"networks.":[60,76],"It":[61],"remains":[62],"unclear":[63],"how":[64],"engines":[66,132],"can":[67],"be":[68],"profitably":[69],"used":[70],"in":[71],"other":[73],"than":[74],"In":[77],"this":[78],"paper":[79],"we":[80],"present":[81],"an":[82],"endeavor":[83],"accelerating":[85],"stabilizing":[87],"a":[88],"fundamental":[89],"matrix":[90],"factorization":[91],"engines---the":[94],"QR":[95,115],"factorization---which":[96],"may":[97],"open":[98],"doors":[99],"much":[101],"wider":[102],"relevance":[103],"scientific,":[105],"engineering,":[106],"data":[108,124],"science.":[109],"We":[110],"show":[111],"that":[112],"traditional":[113],"Householder":[114],"algorithms":[116],"implementations":[118],"do":[119],"not":[120],"have":[121],"necessary":[123],"locality,":[125],"parallelism,":[126],"accuracy,":[127],"robustness":[129],"which":[133],"characterized":[135],"extreme":[137],"speed":[138],"low":[140],"precision/range.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}