{"id":"https://openalex.org/W2891477368","doi":"https://doi.org/10.1145/3235029","title":"High-Performance Generalized Tensor Operations","display_name":"High-Performance Generalized Tensor Operations","publication_year":2018,"publication_date":"2018-09-04","ids":{"openalex":"https://openalex.org/W2891477368","doi":"https://doi.org/10.1145/3235029","mag":"2891477368"},"language":"en","primary_location":{"id":"doi:10.1145/3235029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3235029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3235029","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3235029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015476719","display_name":"Roman A. Gareev","orcid":null},"institutions":[{"id":"https://openalex.org/I130823665","display_name":"Ural Federal University","ror":"https://ror.org/00hs7dr46","country_code":"RU","type":"education","lineage":["https://openalex.org/I130823665"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Roman Gareev","raw_affiliation_strings":["Ural Federal University, Ekaterinburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ural Federal University, Ekaterinburg, Russia","institution_ids":["https://openalex.org/I130823665"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055618037","display_name":"Tobias Grosser","orcid":"https://orcid.org/0000-0003-3874-6003"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tobias Grosser","raw_affiliation_strings":["ETH Zurich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077795200","display_name":"Michael Kruse","orcid":"https://orcid.org/0000-0001-7756-7126"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michael Kruse","raw_affiliation_strings":["INRIA, \u00c9cole Normale Sup\u00e9rieur, and Polly Labs, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, \u00c9cole Normale Sup\u00e9rieur, and Polly Labs, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5132,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95846793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9666000008583069,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9625999927520752,"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":0.8558754920959473},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8318634033203125},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7360177636146545},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5493462085723877},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5241979956626892},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.5027041435241699},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4652268588542938},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.45835036039352417},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43819957971572876},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4250306487083435},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.42225590348243713},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3533369302749634},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27207255363464355},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13404759764671326},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07807767391204834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558754920959473},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8318634033203125},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7360177636146545},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5493462085723877},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5241979956626892},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.5027041435241699},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4652268588542938},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.45835036039352417},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43819957971572876},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4250306487083435},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42225590348243713},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3533369302749634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27207255363464355},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13404759764671326},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07807767391204834},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3235029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3235029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3235029","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:elar.urfu.ru:10995/90109","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85053559484","pdf_url":null,"source":{"id":"https://openalex.org/S4306401522","display_name":"Electronic scientific archive of UrFU (Ural Federal University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130823665","host_organization_name":"Ural Federal University","host_organization_lineage":["https://openalex.org/I130823665"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:jah.su:record/340287","is_oa":true,"landing_page_url":"http://hdl.handle.net/10995/90109","pdf_url":null,"source":{"id":"https://openalex.org/S4306401523","display_name":"Electronic scientific archive of UrFU (Ural Federal University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130823665","host_organization_name":"Ural Federal University","host_organization_lineage":["https://openalex.org/I130823665"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3235029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3235029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3235029","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331518","display_name":"Centro Svizzero di Calcolo Scientifico","ror":null},{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891477368.pdf","grobid_xml":"https://content.openalex.org/works/W2891477368.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1440609229","https://openalex.org/W1512982031","https://openalex.org/W1554018429","https://openalex.org/W1559264847","https://openalex.org/W1567153395","https://openalex.org/W1789336918","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1979796968","https://openalex.org/W1983157164","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2007831980","https://openalex.org/W2034761517","https://openalex.org/W2039227678","https://openalex.org/W2043275593","https://openalex.org/W2044701388","https://openalex.org/W2047739511","https://openalex.org/W2051078434","https://openalex.org/W2059696856","https://openalex.org/W2060221201","https://openalex.org/W2064441385","https://openalex.org/W2064872546","https://openalex.org/W2067575922","https://openalex.org/W2071110673","https://openalex.org/W2072800519","https://openalex.org/W2073061372","https://openalex.org/W2083895736","https://openalex.org/W2093135480","https://openalex.org/W2098614082","https://openalex.org/W2102976251","https://openalex.org/W2104736438","https://openalex.org/W2128344236","https://openalex.org/W2137717224","https://openalex.org/W2158154707","https://openalex.org/W2159846564","https://openalex.org/W2169492033","https://openalex.org/W2214596652","https://openalex.org/W2250569434","https://openalex.org/W2252007067","https://openalex.org/W2271840356","https://openalex.org/W2474317821","https://openalex.org/W2516525699","https://openalex.org/W2565236682","https://openalex.org/W2592969254","https://openalex.org/W2963137752","https://openalex.org/W3103952756","https://openalex.org/W3105468881","https://openalex.org/W3143835353","https://openalex.org/W3151489216","https://openalex.org/W4233358870","https://openalex.org/W4250470790","https://openalex.org/W6607381235"],"related_works":["https://openalex.org/W2065608670","https://openalex.org/W4246264663","https://openalex.org/W2950655732","https://openalex.org/W2152397470","https://openalex.org/W2170966469","https://openalex.org/W2049369293","https://openalex.org/W2172096703","https://openalex.org/W2132832499","https://openalex.org/W1989702012","https://openalex.org/W4242404469"],"abstract_inverted_index":{"The":[0],"efficiency":[1],"of":[2,6,21,44],"tensor":[3],"contraction":[4],"is":[5],"great":[7],"importance.":[8],"Compilers":[9],"cannot":[10],"optimize":[11],"it":[12],"well":[13],"enough":[14],"to":[15,18,70,86],"come":[16],"close":[17],"the":[19,42,49,72],"performance":[20,30,43,62],"expert-tuned":[22],"implementations.":[23],"All":[24],"existing":[25],"approaches":[26],"that":[27,40],"provide":[28],"competitive":[29,61],"require":[31],"optimized":[32,45,93],"external":[33,53],"code.":[34],"We":[35],"introduce":[36],"a":[37],"compiler":[38],"optimization":[39],"reaches":[41],"BLAS":[46],"libraries":[47,94],"without":[48],"need":[50],"for":[51,75],"an":[52],"implementation":[54],"or":[55],"automatic":[56],"tuning.":[57],"Our":[58],"approach":[59],"provides":[60],"across":[63],"hardware":[64],"architectures":[65],"and":[66],"can":[67],"be":[68],"generalized":[69],"deliver":[71],"same":[73],"benefits":[74],"algebraic":[76],"path":[77],"problems.":[78],"By":[79],"making":[80],"fast":[81],"linear":[82],"algebra":[83],"kernels":[84],"available":[85],"everyone,":[87],"we":[88],"expect":[89],"productivity":[90],"increases":[91],"when":[92],"are":[95],"not":[96],"available.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-09-27T00:00:00"}
