{"id":"https://openalex.org/W3173462777","doi":"https://doi.org/10.1145/3460945.3464955","title":"Predictive data locality optimization for higher-order tensor computations","display_name":"Predictive data locality optimization for higher-order tensor computations","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3173462777","doi":"https://doi.org/10.1145/3460945.3464955","mag":"3173462777"},"language":"en","primary_location":{"id":"doi:10.1145/3460945.3464955","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460945.3464955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGPLAN International Symposium on Machine Programming","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/A5014581263","display_name":"Tharindu R. Patabandi","orcid":"https://orcid.org/0000-0002-5052-8183"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tharindu R. Patabandi","raw_affiliation_strings":["University of Utah, USA"],"raw_orcid":"https://orcid.org/0000-0002-5052-8183","affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078599914","display_name":"Anand Venkat","orcid":"https://orcid.org/0000-0002-4167-4525"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Venkat","raw_affiliation_strings":["Intel Labs, USA"],"raw_orcid":"https://orcid.org/0000-0002-4167-4525","affiliations":[{"raw_affiliation_string":"Intel Labs, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056024226","display_name":"Abhishek Kulkarni","orcid":"https://orcid.org/0000-0003-3789-002X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Kulkarni","raw_affiliation_strings":["Intel Corporation, USA"],"raw_orcid":"https://orcid.org/0000-0003-3789-002X","affiliations":[{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033393074","display_name":"Pushkar Ratnalikar","orcid":"https://orcid.org/0000-0002-5900-6744"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pushkar Ratnalikar","raw_affiliation_strings":["Intel Corporation, USA"],"raw_orcid":"https://orcid.org/0000-0002-5900-6744","affiliations":[{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, USA"],"raw_orcid":"https://orcid.org/0000-0002-3058-7573","affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005286439","display_name":"Justin Gottschlich","orcid":"https://orcid.org/0000-0003-2742-9205"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Gottschlich","raw_affiliation_strings":["Intel Labs, USA"],"raw_orcid":"https://orcid.org/0000-0003-2742-9205","affiliations":[{"raw_affiliation_string":"Intel Labs, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9904999732971191,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8786835670471191},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8171960711479187},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.7503628730773926},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5822592973709106},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5511514544487},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5194194316864014},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5193337202072144},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.480537474155426},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45985087752342224},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.4410780966281891},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41885754466056824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35666152834892273},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3553125262260437},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27650049328804016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8786835670471191},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8171960711479187},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.7503628730773926},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5822592973709106},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5511514544487},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5194194316864014},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5193337202072144},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.480537474155426},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45985087752342224},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.4410780966281891},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41885754466056824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35666152834892273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3553125262260437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27650049328804016},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460945.3464955","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460945.3464955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM SIGPLAN International Symposium on Machine Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2657488790","display_name":null,"funder_award_id":"4000159989","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3530486268","display_name":null,"funder_award_id":"SHF-1564074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1502777940","https://openalex.org/W1979457157","https://openalex.org/W1994101511","https://openalex.org/W2043275593","https://openalex.org/W2052934867","https://openalex.org/W2055312318","https://openalex.org/W2071455611","https://openalex.org/W2099059741","https://openalex.org/W2102182691","https://openalex.org/W2156560068","https://openalex.org/W2164617852","https://openalex.org/W2168519934","https://openalex.org/W2618564128","https://openalex.org/W2783614532","https://openalex.org/W2801200039","https://openalex.org/W2951841630","https://openalex.org/W2961619211","https://openalex.org/W2964150020","https://openalex.org/W3007772124","https://openalex.org/W3008788679","https://openalex.org/W3012249773","https://openalex.org/W3122749996","https://openalex.org/W3123054690","https://openalex.org/W3147409832","https://openalex.org/W3156745629","https://openalex.org/W4251637954"],"related_works":["https://openalex.org/W3169195854","https://openalex.org/W1498734356","https://openalex.org/W2010414531","https://openalex.org/W2133860611","https://openalex.org/W2889110163","https://openalex.org/W2901114907","https://openalex.org/W2553479971","https://openalex.org/W2083056254","https://openalex.org/W1542326246","https://openalex.org/W4289329099"],"abstract_inverted_index":{"Automating":[0],"locality":[1],"optimization":[2],"is":[3],"still":[4],"an":[5,59,122,172],"open":[6,48],"problem":[7,119],"for":[8,114,153,181],"compiler":[9,132,151,168],"writers.":[10],"Compiler-based":[11],"approaches,":[12],"guided":[13],"by":[14],"analytical":[15],"cost":[16],"models":[17],"have":[18],"achieved":[19],"some":[20,47],"success":[21],"in":[22,53,101],"matching":[23],"high":[24],"performance":[25,139,198],"libraries":[26],"on":[27,162],"a":[28,129,135],"restricted":[29],"set":[30],"of":[31,61,67,72,105,120,175,199],"computations":[32],"such":[33,155],"as":[34,156],"general":[35],"matrix":[36],"multiply":[37],"(GEMM).":[38],"On":[39],"the":[40,118,141,163,197],"other":[41,149],"hand,":[42],"library-based":[43],"approaches":[44],"may":[45],"present":[46],"scalability":[49],"concerns.":[50],"Recent":[51],"developments":[52],"convolutional":[54,97],"neural":[55],"networks":[56],"has":[57],"seen":[58],"explosion":[60],"models,":[62],"each":[63,71],"with":[64,109,140,148],"differing":[65],"combinations":[66],"parameters.":[68],"Manually":[69],"tuning":[70],"these":[73,81],"configurations":[74],"can":[75],"take":[76],"many":[77],"development":[78],"months.":[79],"Further,":[80],"operations":[82],"are":[83,99,191],"called":[84],"multiple":[85],"times":[86],"during":[87],"machine":[88,130],"learning":[89],"training,":[90],"which":[91,133,204],"necessitates":[92],"highly":[93],"optimized":[94],"implementations.":[95],"2D":[96,182],"operators":[98],"unique":[100],"that":[102],"they":[103],"consist":[104],"7-deep":[106],"loop":[107,124,142,157],"nests":[108],"different":[110,115],"loops":[111],"carrying":[112],"reuse":[113],"tensors,":[116],"making":[117],"identifying":[121],"optimal":[123],"ordering":[125],"hard.":[126],"We":[127,144,170,190],"devise":[128],"learning-based":[131],"learns":[134],"regression":[136],"model,":[137],"correlating":[138],"order.":[143],"integrate":[145],"this":[146],"model":[147],"traditional":[150],"analysis":[152],"transformations":[154],"unrolling":[158],"and":[159,177,185,195],"vectorization,":[160],"relying":[161],"MultiLevel":[164],"Intermediate":[165],"Representation":[166],"(MLIR)":[167],"framework.":[169],"achieve":[171],"average":[173],"speedup":[174],"1.67x":[176],"1.41x":[178],"against":[179],"oneDNN":[180],"convolution":[183],"forward":[184],"weight":[186],"update":[187],"kernels":[188],"respectively.":[189],"also":[192],"at":[193],"0.88x":[194],"0.96x":[196],"oneDNN's":[200],"best":[201],"performing":[202],"implementation":[203],"applies":[205],"additional":[206],"data":[207],"layout":[208],"transformations.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}