{"id":"https://openalex.org/W4386709679","doi":"https://doi.org/10.1145/3605573.3605596","title":"Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs","display_name":"Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709679","doi":"https://doi.org/10.1145/3605573.3605596"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605596","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3605573.3605596&file=Appendix_template.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3605573.3605596&file=Appendix_template.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046708261","display_name":"Mingzhen Li","orcid":"https://orcid.org/0000-0002-4115-9072"},"institutions":[{"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":"Mingzhen Li","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-4115-9072","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"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":"Hailong Yang","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0003-1101-7927","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972392","display_name":"Shanjun Zhang","orcid":"https://orcid.org/0009-0006-6816-058X"},"institutions":[{"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":"Shanjun Zhang","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0009-0006-6816-058X","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102785611","display_name":"Fengwei Yu","orcid":"https://orcid.org/0000-0003-0352-8700"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengwei Yu","raw_affiliation_strings":["SenseTime Research, China"],"raw_orcid":"https://orcid.org/0000-0003-0352-8700","affiliations":[{"raw_affiliation_string":"SenseTime Research, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruihao Gong","orcid":"https://orcid.org/0000-0002-0081-5395"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihao Gong","raw_affiliation_strings":["SenseTime Research, China"],"raw_orcid":"https://orcid.org/0000-0002-0081-5395","affiliations":[{"raw_affiliation_string":"SenseTime Research, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330624","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1829-2817"},"institutions":[{"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":"Yi Liu","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0003-1829-2817","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"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":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-7186-0556","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"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":"Depei Qian","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-5382-1473","affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8791,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90402219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"796"},"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":0.9839000105857849,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9749000072479248,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8468800783157349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754454016685486},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7015926837921143},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.540327250957489},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.49834537506103516},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45634233951568604},{"id":"https://openalex.org/keywords/subgraph-isomorphism-problem","display_name":"Subgraph isomorphism problem","score":0.41772815585136414},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3720245063304901},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3613438606262207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3583265244960785},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35264408588409424},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3403492271900177},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1438525915145874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10443076491355896}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8468800783157349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754454016685486},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7015926837921143},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.540327250957489},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.49834537506103516},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45634233951568604},{"id":"https://openalex.org/C131992880","wikidata":"https://www.wikidata.org/wiki/Q2528185","display_name":"Subgraph isomorphism problem","level":3,"score":0.41772815585136414},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3720245063304901},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3613438606262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3583265244960785},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35264408588409424},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3403492271900177},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1438525915145874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10443076491355896},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605596","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3605573.3605596&file=Appendix_template.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3605573.3605596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605596","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3605573.3605596&file=Appendix_template.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386709679.pdf","grobid_xml":"https://content.openalex.org/works/W4386709679.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W1982063824","https://openalex.org/W2055312318","https://openalex.org/W2804032941","https://openalex.org/W2981758446","https://openalex.org/W3004659153","https://openalex.org/W3012249773","https://openalex.org/W3035582633","https://openalex.org/W3157020554","https://openalex.org/W3211053593","https://openalex.org/W4212986322","https://openalex.org/W4221062244","https://openalex.org/W4318256790","https://openalex.org/W4318541553"],"related_works":["https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W3146558274","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035","https://openalex.org/W1597127505"],"abstract_inverted_index":{"The":[0,156],"requirement":[1],"for":[2,122,148],"deploying":[3],"deep":[4],"learning":[5],"(DL)":[6],"models":[7,113,162],"efficiently":[8],"has":[9,24],"boosted":[10],"the":[11,17,31,41,64,82,99,111,131,135,143,179],"research":[12],"of":[13,19,43,47,145],"DL":[14,26,161],"compilers.":[15],"Especially,":[16],"difficulty":[18],"generating":[20],"optimized":[21],"tensor":[22,74,95],"programs":[23,75,96],"driven":[25],"compilers":[27],"to":[28,39,71,141,178],"commonly":[29,58],"adopt":[30],"auto-tuning":[32,44,56,89,181],"approaches.":[33],"Consequently,":[34],"there":[35],"are":[36,114],"increasing":[37],"demands":[38],"improve":[40],"effectiveness":[42],"in":[45],"terms":[46],"both":[48,172],"search":[49,52,154,169],"efficiency":[50],"and":[51,62,68,174],"quality.":[53,155],"However,":[54],"existing":[55],"approaches":[57],"treat":[59],"subgraphs":[60,106],"individually":[61],"overlook":[63],"similarities":[65],"among":[66],"them,":[67],"thus":[69],"fail":[70],"generate":[72,93],"better":[73,94,168],"under":[76],"limited":[77],"time":[78],"budget.":[79],"To":[80,128],"address":[81],"above":[83],"drawbacks,":[84],"we":[85],"propose":[86],"FamilySeer,":[87],"an":[88],"framework":[90],"that":[91,164],"can":[92,166],"by":[97],"exploiting":[98],"subgraph":[100,108],"similarities.":[101],"Specifically,":[102],"FamilySeer":[103,133,165],"organizes":[104],"similar":[105],"into":[107],"families,":[109],"where":[110],"cost":[112,137],"built":[115],"at":[116],"family":[117,140],"basis":[118],"with":[119],"improved":[120],"accuracy":[121],"estimating":[123],"high":[124],"potential":[125],"program":[126,146],"candidates.":[127],"further":[129],"leverage":[130],"similarity,":[132],"uses":[134],"accurate":[136],"model":[138],"per":[139],"reduce":[142],"number":[144],"candidates":[147],"costly":[149],"hardware":[150],"measurements":[151],"without":[152],"degrading":[153],"experiment":[157],"results":[158],"on":[159,171],"various":[160],"demonstrate":[163],"achieve":[167],"efficiency/quality":[170],"CPU":[173],"GPU":[175],"platforms":[176],"compared":[177],"state-of-the-art":[180],"framework.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}