{"id":"https://openalex.org/W3013208916","doi":"https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","title":"Fast Schedule Tensor Computation on GPU with High Data Reuse and Device Utilization","display_name":"Fast Schedule Tensor Computation on GPU with High Data Reuse and Device Utilization","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3013208916","doi":"https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","mag":"3013208916"},"language":"en","primary_location":{"id":"doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)","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/A5101769560","display_name":"Yuxiang Zhang","orcid":"https://orcid.org/0000-0001-5228-3215"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxiang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036488225","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-6638-6442"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101769560"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22319332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"553","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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"}},"topics":[{"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/T12303","display_name":"Tensor decomposition and applications","score":0.9983000159263611,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8373221755027771},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.7850039005279541},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7388859987258911},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7305007576942444},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7076054215431213},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.511139452457428},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.49471375346183777},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3732699155807495},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30965718626976013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10082170367240906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373221755027771},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.7850039005279541},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7388859987258911},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7305007576942444},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7076054215431213},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.511139452457428},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.49471375346183777},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3732699155807495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30965718626976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10082170367240906},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1989988531","https://openalex.org/W2055312318","https://openalex.org/W2077143534","https://openalex.org/W2735974062","https://openalex.org/W2786320458","https://openalex.org/W2804032941","https://openalex.org/W2804500013","https://openalex.org/W2953384591","https://openalex.org/W2963729050","https://openalex.org/W2963782415","https://openalex.org/W2963960923","https://openalex.org/W4251637954","https://openalex.org/W6713134421","https://openalex.org/W6748324931","https://openalex.org/W6751349269","https://openalex.org/W6752057402"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W2045183646","https://openalex.org/W4234091740","https://openalex.org/W2162409446","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2022275305","https://openalex.org/W2119931478"],"abstract_inverted_index":{"Tensor":[0,104],"computation,":[1],"or":[2],"computation":[3,46,63,97],"on":[4,47,64],"high-dimensional":[5],"arrays,":[6],"is":[7,68],"widely":[8],"used":[9],"in":[10,94],"deep":[11],"learning,":[12],"image":[13],"processing,":[14],"and":[15,43,59,115],"scientific":[16],"computation.":[17],"And":[18,78],"GPU":[19,66],"has":[20],"become":[21],"the":[22,41,72,86,101,116],"mainstream":[23],"platform":[24],"to":[25,39,70,83,91],"accelerate":[26],"computing.":[27],"We":[28],"propose":[29],"an":[30,51],"algorithm":[31,107],"which":[32],"can":[33,108],"efficiently":[34],"find":[35,109],"a":[36,75,110],"promising":[37,111],"schedule":[38,90,112],"exploit":[40],"parallelism":[42,60],"locality":[44],"of":[45,62,74,89,96],"GPU.":[48],"In":[49],"particular,":[50],"empirical":[52,79],"model":[53,67],"comprehensively":[54],"considering":[55],"locality,":[56],"load":[57],"balance":[58],"sufficiency":[61],"given":[65],"designed":[69],"measure":[71],"quality":[73],"candidate":[76],"schedule.":[77],"constraints":[80],"are":[81],"introduced":[82],"significantly":[84],"reduce":[85],"searching":[87],"space":[88],"polynomial":[92],"complexity":[93],"terms":[95],"dimensions.":[98],"Compared":[99],"with":[100],"state-of-the-art":[102],"tool,":[103],"Comprehensions,":[105],"our":[106],"5-45\u00d7":[113],"faster,":[114],"corresponding":[117],"scheduled":[118],"code":[119],"runs":[120],"1.5-10\u00d7":[121],"faster.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}