{"id":"https://openalex.org/W2081787310","doi":"https://doi.org/10.1109/hpec.2015.7322479","title":"Bisection and twisted SVD on GPU","display_name":"Bisection and twisted SVD on GPU","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2081787310","doi":"https://doi.org/10.1109/hpec.2015.7322479","mag":"2081787310"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2015.7322479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2015.7322479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5101948906","display_name":"L\u00fc He","orcid":"https://orcid.org/0000-0002-5329-2153"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lu He","raw_affiliation_strings":["University of Massachusetts Lowell","University of Massachusetts Lowell, 01854, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts Lowell, 01854, United States","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003621523","display_name":"Yan Luo","orcid":"https://orcid.org/0000-0002-5301-5092"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Luo","raw_affiliation_strings":["University of Massachusetts Lowell","University of Massachusetts Lowell, 01854, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts Lowell, 01854, United States","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448557","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-8578-0733"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]},{"id":"https://openalex.org/I5429594","display_name":"Fitchburg State University","ror":"https://ror.org/031tt0491","country_code":"US","type":"education","lineage":["https://openalex.org/I5429594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Fitchburg State University","Wake Forest University, Winston-Salem, NC 27106, United States"],"affiliations":[{"raw_affiliation_string":"Fitchburg State University","institution_ids":["https://openalex.org/I5429594"]},{"raw_affiliation_string":"Wake Forest University, Winston-Salem, NC 27106, United States","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052662150","display_name":"Hengyong Yu","orcid":"https://orcid.org/0000-0002-5852-0813"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hengyong Yu","raw_affiliation_strings":["University of Massachusetts Lowell","University of Massachusetts Lowell, 01854, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts Lowell, 01854, United States","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692224","display_name":"Yu Cao","orcid":"https://orcid.org/0009-0006-4567-713X"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":["University of Massachusetts Lowell","University of Massachusetts Lowell, 01854, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts Lowell, 01854, United States","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080788490","display_name":"Xuzhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I5429594","display_name":"Fitchburg State University","ror":"https://ror.org/031tt0491","country_code":"US","type":"education","lineage":["https://openalex.org/I5429594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuzhou Chen","raw_affiliation_strings":["Fitchburg State University","Fitchburg State University, MA 01420, United States"],"affiliations":[{"raw_affiliation_string":"Fitchburg State University","institution_ids":["https://openalex.org/I5429594"]},{"raw_affiliation_string":"Fitchburg State University, MA 01420, United States","institution_ids":["https://openalex.org/I5429594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102805559","display_name":"Seung Woo Son","orcid":"https://orcid.org/0000-0001-8922-418X"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung Woo Son","raw_affiliation_strings":["University of Massachusetts Lowell","University of Massachusetts Lowell, 01854, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts Lowell, 01854, United States","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101948906"],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04730314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9922999739646912,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.6737977266311646},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5856108665466309},{"id":"https://openalex.org/keywords/bisection","display_name":"Bisection","score":0.4427386224269867},{"id":"https://openalex.org/keywords/bisection-method","display_name":"Bisection method","score":0.42006608843803406},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.39169585704803467},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3794653117656708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2722542881965637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21771541237831116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11597973108291626},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10115963220596313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737977266311646},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5856108665466309},{"id":"https://openalex.org/C31599958","wikidata":"https://www.wikidata.org/wiki/Q3128632","display_name":"Bisection","level":2,"score":0.4427386224269867},{"id":"https://openalex.org/C157544257","wikidata":"https://www.wikidata.org/wiki/Q866300","display_name":"Bisection method","level":2,"score":0.42006608843803406},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.39169585704803467},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3794653117656708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2722542881965637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21771541237831116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11597973108291626},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10115963220596313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2015.7322479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2015.7322479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W148852858","https://openalex.org/W1749424093","https://openalex.org/W1760551737","https://openalex.org/W1964635340","https://openalex.org/W1970967332","https://openalex.org/W1983085277","https://openalex.org/W2005423095","https://openalex.org/W2016279572","https://openalex.org/W2047614366","https://openalex.org/W2065060195","https://openalex.org/W2105812312","https://openalex.org/W2111712077","https://openalex.org/W2253627208","https://openalex.org/W2262891426","https://openalex.org/W2326471176","https://openalex.org/W3158780744","https://openalex.org/W4301491118","https://openalex.org/W6642897435","https://openalex.org/W6651805951"],"related_works":["https://openalex.org/W2329494729","https://openalex.org/W3112697985","https://openalex.org/W41290553","https://openalex.org/W2585516632","https://openalex.org/W1986919722","https://openalex.org/W2093663313","https://openalex.org/W40332083","https://openalex.org/W4296983618","https://openalex.org/W2158390333","https://openalex.org/W2577097539"],"abstract_inverted_index":{"Singular":[0],"value":[1],"decomposition":[2],"(SVD)":[3],"is":[4,17,81,113],"one":[5],"of":[6,24,28,120,134],"the":[7,22,64,78,106,110,132],"most":[8],"important":[9],"factorizations":[10],"in":[11,59],"matrix":[12],"computation.":[13],"However,":[14],"computing":[15],"SVD":[16,117],"still":[18],"time-consuming,":[19],"especially":[20],"when":[21],"dimension":[23],"matrices":[25,119],"exceeds":[26],"tens":[27],"thousands.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,62],"present":[34],"a":[35,142],"high":[36],"performance":[37],"approach":[38],"called":[39],"\u201cBisection":[40],"and":[41,69,96],"Twisted\u201d":[42],"(BT)":[43],"for":[44,118],"solving":[45],"bidiagonal":[46],"SVD.":[47],"As":[48],"modern":[49],"general":[50],"purpose":[51],"GPUs":[52],"have":[53],"shown":[54],"their":[55],"extreme":[56],"computational":[57],"advantages":[58],"parallel":[60],"computing,":[61],"implement":[63],"BT":[65,79,111],"algorithm":[66,80,112],"on":[67,91,105],"single":[68],"multiple":[70],"GPUs.":[71,108,130],"With":[72],"our":[73,135],"carefully":[74],"designed":[75],"GPU":[76],"kernels,":[77],"about":[82],"10":[83],"times":[84,98],"faster":[85,99],"than":[86,100],"MKL":[87],"divide-and-conquer":[88],"routine":[89,103],"DBDSDC":[90],"an":[92],"8-core":[93],"2.53GHz":[94],"CPU,":[95],"36":[97],"CULA":[101],"QR":[102],"DBDSQR":[104],"same":[107],"Additionally,":[109],"able":[114],"to":[115],"compute":[116],"size":[121],"1":[122,125],"million":[123,126],"by":[124],"with":[127],"only":[128],"two":[129],"To":[131],"best":[133],"knowledge,":[136],"no":[137],"implementation":[138],"has":[139],"achieved":[140],"such":[141],"scale.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}