{"id":"https://openalex.org/W7167088565","doi":"https://doi.org/10.1145/3797905.3807865","title":"Optimizing Streaming Tensor Decomposition on GPU","display_name":"Optimizing Streaming Tensor Decomposition on GPU","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167088565","doi":"https://doi.org/10.1145/3797905.3807865"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3807865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807865","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3807865","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073960312","display_name":"Wenqing Lin","orcid":"https://orcid.org/0000-0003-4741-801X"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Lin","raw_affiliation_strings":["College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5519-2819","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139865132","display_name":"Jianuo Sheng","orcid":"https://orcid.org/0009-0003-9135-7338"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianuo Sheng","raw_affiliation_strings":["College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9135-7338","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139889421","display_name":"Shuqin Feng","orcid":"https://orcid.org/0009-0006-5160-7349"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Feng","raw_affiliation_strings":["College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5160-7349","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058494044","display_name":"Ming Dun","orcid":"https://orcid.org/0000-0002-0664-9543"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Dun","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0664-9543","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012125082","display_name":"Huawei Cao","orcid":"https://orcid.org/0000-0003-1176-2521"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Cao","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1176-2521","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060999547","display_name":"Qingxiao Sun","orcid":"https://orcid.org/0000-0003-2927-362X"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]},{"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":["China University of Petroleum-Beijing, Beijing, China and Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2927-362X","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China and Beihang University, Beijing, China","institution_ids":["https://openalex.org/I204553293","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91208791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"662","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.951200008392334,"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":0.951200008392334,"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/T11471","display_name":"Block Copolymer Self-Assembly","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7293999791145325},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5874000191688538},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5157999992370605},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.5127000212669373},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.42559999227523804},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.3725000023841858},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.32440000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605000138282776},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C3019022308","wikidata":"https://www.wikidata.org/wiki/Q1418353","display_name":"Multidimensional data","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3807865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807865","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3807865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807865","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8484223723","display_name":null,"funder_award_id":"62402525","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1511885491","https://openalex.org/W1974133504","https://openalex.org/W1981535808","https://openalex.org/W2000215628","https://openalex.org/W2024165284","https://openalex.org/W2102937240","https://openalex.org/W2108837778","https://openalex.org/W2125833438","https://openalex.org/W2384663018","https://openalex.org/W2469230926","https://openalex.org/W2765083400","https://openalex.org/W2800391958","https://openalex.org/W2902783593","https://openalex.org/W2981758446","https://openalex.org/W2986686333","https://openalex.org/W3129727110","https://openalex.org/W3131137184","https://openalex.org/W3174786754","https://openalex.org/W3174859112","https://openalex.org/W4223979846","https://openalex.org/W4282967953","https://openalex.org/W4321466355","https://openalex.org/W4321636675","https://openalex.org/W4382048176","https://openalex.org/W4384705463","https://openalex.org/W4387007190","https://openalex.org/W4392266035","https://openalex.org/W4401408950","https://openalex.org/W4404133484","https://openalex.org/W4405440056","https://openalex.org/W4406014476","https://openalex.org/W4414486772"],"related_works":[],"abstract_inverted_index":{"Tensors":[0],"represent":[1],"multidimensional":[2],"data":[3,102],"and":[4,104],"cover":[5],"various":[6],"areas":[7],"of":[8,68,88,118],"scientific":[9],"computing.":[10],"The":[11],"Canonical":[12],"Polyadic":[13],"Decomposition":[14],"(CPD)":[15],"emerges":[16],"to":[17,64,71,82,100],"extract":[18],"latent":[19],"patterns":[20,117],"from":[21],"large":[22],"but":[23],"highly":[24],"sparse":[25],"tensors.":[26],"In":[27],"real-world":[28],"scenarios,":[29],"tensor":[30,49,57],"slices":[31,58],"often":[32],"arrive":[33],"dynamically":[34],"over":[35],"time":[36,52],"in":[37,45],"streaming":[38,93],"form,":[39],"making":[40],"traditional":[41],"CPD":[42,55,94],"algorithms":[43],"inefficient":[44],"processing":[46,86],"the":[47,66,84,108,114],"entire":[48],"at":[50],"each":[51],"step.":[53],"Streaming":[54],"processes":[56],"incrementally,":[59],"exploiting":[60],"a":[61],"forgetting":[62],"factor":[63],"adjust":[65],"weight":[67],"historical":[69],"information":[70],"capture":[72],"dynamics.":[73],"Current":[74],"optimizations":[75],"mainly":[76],"focus":[77],"on":[78,95],"CPU":[79],"platforms,":[80],"failing":[81],"meet":[83],"real-time":[85],"requirements":[87],"modern":[89],"applications.":[90],"Efficiently":[91],"deploying":[92],"GPU":[96],"remains":[97],"challenging":[98],"due":[99],"frequent":[101],"transfers":[103],"memory":[105],"operations":[106],"throughout":[107],"complex":[109],"workflow,":[110],"as":[111,113],"well":[112],"intricate":[115],"computational":[116],"bottleneck":[119],"operators.":[120]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-03T00:00:00"}