{"id":"https://openalex.org/W3168654039","doi":"https://doi.org/10.1145/3447818.3460692","title":"An optimized tensor completion library for multiple GPUs","display_name":"An optimized tensor completion library for multiple GPUs","publication_year":2021,"publication_date":"2021-06-03","ids":{"openalex":"https://openalex.org/W3168654039","doi":"https://doi.org/10.1145/3447818.3460692","mag":"3168654039"},"language":"en","primary_location":{"id":"doi:10.1145/3447818.3460692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3460692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058494044","display_name":"Ming Dun","orcid":"https://orcid.org/0000-0002-0664-9543"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Dun","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398861","display_name":"Yunchun Li","orcid":"https://orcid.org/0000-0002-1950-4511"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchun Li","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060999547","display_name":"Qingxiao Sun","orcid":"https://orcid.org/0000-0003-2927-362X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiao Sun","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996399998664856,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.7765103578567505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754094004631042},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7319469451904297},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6775529980659485},{"id":"https://openalex.org/keywords/coordinate-descent","display_name":"Coordinate descent","score":0.6686480641365051},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5113091468811035},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47104525566101074},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4709027111530304},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4643362760543823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42541825771331787},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39434558153152466},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34914493560791016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30348441004753113},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1605696678161621},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1545974612236023},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10941138863563538},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10490098595619202}],"concepts":[{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.7765103578567505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754094004631042},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7319469451904297},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6775529980659485},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.6686480641365051},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5113091468811035},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47104525566101074},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4709027111530304},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4643362760543823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42541825771331787},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39434558153152466},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34914493560791016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30348441004753113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1605696678161621},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1545974612236023},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10941138863563538},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10490098595619202},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447818.3460692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3460692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G125913346","display_name":null,"funder_award_id":"62072018,61732002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1378380340","display_name":null,"funder_award_id":"2020YFB1506703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W1511885491","https://openalex.org/W1512387364","https://openalex.org/W1541288193","https://openalex.org/W1574504252","https://openalex.org/W1964704819","https://openalex.org/W1968080575","https://openalex.org/W1969116741","https://openalex.org/W1976801265","https://openalex.org/W1980147176","https://openalex.org/W1999956270","https://openalex.org/W2002555321","https://openalex.org/W2006973305","https://openalex.org/W2020098476","https://openalex.org/W2061873838","https://openalex.org/W2078794610","https://openalex.org/W2079487069","https://openalex.org/W2095729436","https://openalex.org/W2103392911","https://openalex.org/W2106005123","https://openalex.org/W2133353476","https://openalex.org/W2146682077","https://openalex.org/W2173213060","https://openalex.org/W2245094585","https://openalex.org/W2271304962","https://openalex.org/W2613168994","https://openalex.org/W2616032753","https://openalex.org/W2616934551","https://openalex.org/W2762964972","https://openalex.org/W2767121257","https://openalex.org/W2885801207","https://openalex.org/W2893530532","https://openalex.org/W2902783593","https://openalex.org/W2922483423","https://openalex.org/W2950423973","https://openalex.org/W2951781666","https://openalex.org/W2952647294","https://openalex.org/W2963472624","https://openalex.org/W2963482281","https://openalex.org/W2971508019","https://openalex.org/W2986686333","https://openalex.org/W3008803005","https://openalex.org/W3016735325","https://openalex.org/W3099762987","https://openalex.org/W4293320122"],"related_works":["https://openalex.org/W2966297898","https://openalex.org/W2955229517","https://openalex.org/W4286693783","https://openalex.org/W3175914740","https://openalex.org/W4294982320","https://openalex.org/W3034587794","https://openalex.org/W3210805454","https://openalex.org/W2020098476","https://openalex.org/W2356529274","https://openalex.org/W4387817170"],"abstract_inverted_index":{"Tensor":[0],"computations":[1],"are":[2],"gaining":[3],"wide":[4],"adoption":[5],"in":[6,26],"big":[7],"data":[8],"analysis":[9],"and":[10,43,101,115,139,152],"artificial":[11],"intelligence.":[12],"Among":[13],"them,":[14],"tensor":[15,30,50,59,64,75,146],"completion":[16,31,51,60,76,147],"is":[17],"used":[18,88],"to":[19,120,131],"predict":[20],"the":[21,54,68,73,128,133,153],"missing":[22],"or":[23,162],"unobserved":[24],"value":[25],"tensors.":[27],"The":[28],"decomposition-based":[29],"algorithms":[32,90],"have":[33],"attracted":[34],"significant":[35,158],"research":[36],"attention":[37],"since":[38],"they":[39],"exhibit":[40],"better":[41,137,164],"parallelization":[42],"scalability.":[44],"However,":[45],"existing":[46],"optimization":[47,89],"techniques":[48],"for":[49,57,136],"cannot":[52],"sustain":[53],"increasing":[55],"demand":[56],"applying":[58],"on":[61,79,118,149],"ever":[62],"larger":[63],"data.":[65],"To":[66],"address":[67],"above":[69],"limitations,":[70],"we":[71,126],"develop":[72],"first":[74],"library":[77],"cuTC":[78,143,156],"multiple":[80],"Graphics":[81],"Processing":[82],"Units":[83],"(GPUs)":[84],"with":[85,144,160],"three":[86],"widely":[87],"such":[91],"as":[92],"alternating":[93],"least":[94],"squares":[95],"(ALS),":[96],"stochastic":[97],"gradient":[98],"descent":[99,103],"(SGD)":[100],"coordinate":[102],"(CCD+).":[104],"We":[105,141],"propose":[106],"a":[107],"novel":[108],"TB-COO":[109],"format":[110],"that":[111],"leverages":[112],"warp":[113],"shuffle":[114],"shared":[116],"memory":[117],"GPU":[119],"enable":[121],"efficient":[122],"reduction.":[123],"In":[124],"addition,":[125],"adopt":[127],"auto-tuning":[129],"method":[130],"determine":[132],"optimal":[134],"parameters":[135],"convergence":[138],"performance.":[140],"compare":[142],"state-of-the-art":[145],"libraries":[148],"real-world":[150],"datasets,":[151],"results":[154],"show":[155],"achieves":[157],"speedup":[159],"similar":[161],"even":[163],"accuracy.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}