{"id":"https://openalex.org/W4308596141","doi":"https://doi.org/10.1145/3570641","title":"Autotuning Convolutions Is Easier Than You Think","display_name":"Autotuning Convolutions Is Easier Than You Think","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308596141","doi":"https://doi.org/10.1145/3570641"},"language":"en","primary_location":{"id":"doi:10.1145/3570641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570641","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":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3570641","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015721738","display_name":"Nicolas Tollenaere","orcid":"https://orcid.org/0000-0002-5072-4109"},"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nicolas Tollenaere","raw_affiliation_strings":["INRIA, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-5072-4109","affiliations":[{"raw_affiliation_string":"INRIA, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054129043","display_name":"Guillaume Iooss","orcid":"https://orcid.org/0000-0003-0326-1807"},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Iooss","raw_affiliation_strings":["INRIA, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0003-0326-1807","affiliations":[{"raw_affiliation_string":"INRIA, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011198538","display_name":"St\u00e9phane Pouget","orcid":"https://orcid.org/0000-0003-3950-5818"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Pouget","raw_affiliation_strings":["University of California Los-Angeles, Los Angeles, California, USA","UCLA - University of California [Los Angeles] ( Los Angeles, Californie 90095 - United States)"],"raw_orcid":"https://orcid.org/0000-0003-3950-5818","affiliations":[{"raw_affiliation_string":"University of California Los-Angeles, Los Angeles, California, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"UCLA - University of California [Los Angeles] ( Los Angeles, Californie 90095 - United States)","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081852342","display_name":"Hugo Brunie","orcid":null},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hugo Brunie","raw_affiliation_strings":["INRIA, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-5875-4660","affiliations":[{"raw_affiliation_string":"INRIA, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008882200","display_name":"Christophe Guillon","orcid":"https://orcid.org/0000-0001-8308-8682"},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Guillon","raw_affiliation_strings":["INRIA, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0001-8308-8682","affiliations":[{"raw_affiliation_string":"INRIA, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063162788","display_name":"Albert Cohen","orcid":"https://orcid.org/0000-0002-8866-5343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albert Cohen","raw_affiliation_strings":["Google, Paris, France","Google France ( 8 Rue de Londres, 75009 Paris - France)"],"raw_orcid":"https://orcid.org/0000-0002-8866-5343","affiliations":[{"raw_affiliation_string":"Google, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Google France ( 8 Rue de Londres, 75009 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"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":"P. Sadayappan","raw_affiliation_strings":["University of Utah, Utah, USA","University of Utah (201 Presidents Cir, Salt Lake City, UT 84112 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-4737-2034","affiliations":[{"raw_affiliation_string":"University of Utah, Utah, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah (201 Presidents Cir, Salt Lake City, UT 84112 - United States)","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089282120","display_name":"Fabrice Rastello","orcid":"https://orcid.org/0000-0002-6589-9956"},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Rastello","raw_affiliation_strings":["INRIA, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-6589-9956","affiliations":[{"raw_affiliation_string":"INRIA, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5015721738"],"corresponding_institution_ids":["https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":3.9688,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94491297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"20","issue":"2","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9955999851226807,"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":0.9951000213623047,"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":0.8366363048553467},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.8092993497848511},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5469047427177429},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5168340802192688},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5044847726821899},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5013670921325684},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4874863624572754},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4464588761329651},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42813605070114136},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42721328139305115},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4265485405921936},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41120094060897827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36032044887542725},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2222207486629486},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1677650809288025},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15051639080047607},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11030960083007812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366363048553467},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.8092993497848511},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5469047427177429},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5168340802192688},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5044847726821899},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5013670921325684},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4874863624572754},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4464588761329651},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42813605070114136},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42721328139305115},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4265485405921936},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41120094060897827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36032044887542725},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2222207486629486},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1677650809288025},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15051639080047607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11030960083007812},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3570641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570641","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":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:HAL:hal-03844272v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03844272","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization, 2022, pp.1-23. ⟨10.1145/3570641⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1145/3570641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570641","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":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"display_name":"Industry, innovation and infrastructure","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316512","display_name":"Bpifrance","ror":"https://ror.org/008zkt807"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308596141.pdf","grobid_xml":"https://content.openalex.org/works/W4308596141.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1191262899","https://openalex.org/W1562841074","https://openalex.org/W1970141743","https://openalex.org/W2034761517","https://openalex.org/W2055312318","https://openalex.org/W2077143534","https://openalex.org/W2084379367","https://openalex.org/W2102976251","https://openalex.org/W2129740858","https://openalex.org/W2194775991","https://openalex.org/W2252007067","https://openalex.org/W2570343428","https://openalex.org/W2585460399","https://openalex.org/W2588061952","https://openalex.org/W2804500013","https://openalex.org/W2806891462","https://openalex.org/W2983923412","https://openalex.org/W2985039650","https://openalex.org/W3005909967","https://openalex.org/W3012249773","https://openalex.org/W3123054690","https://openalex.org/W3156745629","https://openalex.org/W4242149169","https://openalex.org/W4244254628","https://openalex.org/W4245312332","https://openalex.org/W4318256790","https://openalex.org/W6600662749","https://openalex.org/W6601630192","https://openalex.org/W6752057402"],"related_works":["https://openalex.org/W2057234250","https://openalex.org/W88028992","https://openalex.org/W3157543420","https://openalex.org/W4232006640","https://openalex.org/W2119347856","https://openalex.org/W2149675621","https://openalex.org/W2164655372","https://openalex.org/W899535088","https://openalex.org/W4293104654","https://openalex.org/W2113167168"],"abstract_inverted_index":{"A":[0],"wide":[1],"range":[2],"of":[3,14,21,34,82,115,163,192,210],"scientific":[4],"and":[5,173,181,197],"machine":[6],"learning":[7,145],"applications":[8],"depend":[9],"on":[10,119,122,170,176],"highly":[11],"optimized":[12],"implementations":[13],"tensor":[15,137],"computations.":[16],"Exploiting":[17],"the":[18,32,35,47,156,161,168,190,193,202],"full":[19],"capacity":[20],"a":[22,27,79,89,98],"given":[23],"processor":[24],"architecture":[25],"remains":[26],"challenging":[28],"task,":[29],"due":[30],"to":[31,63,74,84,107,125,148],"complexity":[33],"microarchitectural":[36],"features":[37],"that":[38,102],"come":[39],"into":[40],"play":[41],"when":[42],"seeking":[43],"near-peak":[44],"performance.":[45],"Among":[46],"state-of-the-art":[48,126,194],"techniques":[49],"for":[50,53,135],"loop":[51],"transformations":[52],"performance":[54,71,134,174,191],"optimization,":[55],"AutoScheduler":[56],"[Zheng":[57],"et":[58],"al.":[59],"2020a":[60],"]":[61],"tends":[62],"outperform":[64,189],"other":[65],"systems.":[66],"It":[67],"often":[68],"yields":[69],"higher":[70,133],"as":[72],"compared":[73],"vendor":[75],"libraries,":[76,127],"but":[77],"takes":[78],"large":[80],"number":[81],"runs":[83],"converge,":[85],"while":[86,159,200],"also":[87],"involving":[88],"complex":[90],"training":[91],"environment.":[92],"In":[93],"this":[94],"article,":[95],"we":[96],"define":[97],"structured":[99,129],"configuration":[100],"space":[101,131,158],"enables":[103,132],"much":[104],"faster":[105],"convergence":[106,171],"high-performance":[108],"code":[109,150],"versions,":[110],"using":[111],"only":[112],"random":[113],"sampling":[114],"candidates.":[116],"We":[117,166,186],"focus":[118],"two-dimensional":[120],"convolutions":[121],"CPUs.":[123],"Compared":[124,147],"our":[128],"search":[130,157],"typical":[136],"shapes":[138],"encountered":[139],"in":[140,143],"convolution":[141],"stages":[142],"deep":[144],"pipelines.":[146],"auto-tuning":[149],"generators":[151],"like":[152],"AutoScheduler,":[153,199],"it":[154],"prunes":[155],"increasing":[160],"density":[162],"efficient":[164],"implementations.":[165],"analyze":[167],"impact":[169],"speed":[172],"distribution,":[175],"two":[177],"Intel":[178],"x86":[179],"processors":[180],"one":[182],"ARM":[183],"AArch64":[184],"processor.":[185],"match":[187],"or":[188],"oneDNN":[195],"library":[196],"TVM\u2019s":[198],"reducing":[201],"autotuning":[203],"effort":[204],"by":[205],"at":[206],"least":[207],"an":[208],"order":[209],"magnitude.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}