{"id":"https://openalex.org/W4392265934","doi":"https://doi.org/10.1109/cgo57630.2024.10444871","title":"oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation","display_name":"oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392265934","doi":"https://doi.org/10.1109/cgo57630.2024.10444871"},"language":"en","primary_location":{"id":"doi:10.1109/cgo57630.2024.10444871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5100372619","display_name":"Jianhui Li","orcid":"https://orcid.org/0009-0001-6253-9808"},"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":true,"raw_author_name":"Jianhui Li","raw_affiliation_strings":["Intel,US","Intel, US"],"affiliations":[{"raw_affiliation_string":"Intel,US","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, US","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041530198","display_name":"Zhennan Qin","orcid":null},"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":"Zhennan Qin","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081648910","display_name":"Yijie Mei","orcid":null},"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":"Yijie Mei","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013139344","display_name":"Jingze Cui","orcid":null},"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":"Jingze Cui","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102286832","display_name":"Yunfei Song","orcid":null},"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":"Yunfei Song","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068765236","display_name":"Ciyong Chen","orcid":null},"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":"Ciyong Chen","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386948","display_name":"Yifei Zhang","orcid":"https://orcid.org/0000-0003-4185-8663"},"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":"Yifei Zhang","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052635909","display_name":"Longsheng Du","orcid":null},"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":"Longsheng Du","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065800739","display_name":"Xianhang Cheng","orcid":null},"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":"Xianhang Cheng","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110957890","display_name":"Baihui Jin","orcid":null},"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":"Baihui Jin","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449363","display_name":"Yan Zhang","orcid":"https://orcid.org/0009-0002-8501-9079"},"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":"Yan Zhang","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089161617","display_name":"Jason Ye","orcid":null},"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":"Jason Ye","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079225210","display_name":"Eric K. Lin","orcid":"https://orcid.org/0000-0003-2190-7034"},"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":"Eric Lin","raw_affiliation_strings":["Intel,China","Intel, China"],"affiliations":[{"raw_affiliation_string":"Intel,China","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025616182","display_name":"Daniel J. Lavery","orcid":"https://orcid.org/0000-0002-4218-0527"},"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":"Dan Lavery","raw_affiliation_strings":["Intel,US","Intel, US"],"affiliations":[{"raw_affiliation_string":"Intel,US","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, US","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5100372619"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":7.4466,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.98254527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"460","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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":0.9815999865531921,"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":0.8719906806945801},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8117125034332275},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6549647450447083},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.6209524869918823},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5627773404121399},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47423335909843445},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4512837529182434},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4419693648815155},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4375911355018616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39065518975257874},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3337436616420746},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3269052803516388},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2819882035255432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719906806945801},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8117125034332275},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6549647450447083},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.6209524869918823},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5627773404121399},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47423335909843445},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4512837529182434},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4419693648815155},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4375911355018616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39065518975257874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3337436616420746},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3269052803516388},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2819882035255432},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo57630.2024.10444871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2043275593","https://openalex.org/W2073061372","https://openalex.org/W2516525699","https://openalex.org/W2549139847","https://openalex.org/W2786320458","https://openalex.org/W2896457183","https://openalex.org/W2925102126","https://openalex.org/W2947737663","https://openalex.org/W2954698171","https://openalex.org/W3007772124","https://openalex.org/W3096456556","https://openalex.org/W3117255825","https://openalex.org/W3119880013","https://openalex.org/W4220850685","https://openalex.org/W4226443139","https://openalex.org/W4244254628","https://openalex.org/W4288072573","https://openalex.org/W6748324931","https://openalex.org/W6752057402","https://openalex.org/W6755207826","https://openalex.org/W6760952751","https://openalex.org/W6763737044","https://openalex.org/W6774508117","https://openalex.org/W6779728309","https://openalex.org/W6784716568"],"related_works":["https://openalex.org/W2577630842","https://openalex.org/W2113798250","https://openalex.org/W1488300410","https://openalex.org/W4225492247","https://openalex.org/W2069117531","https://openalex.org/W4320560513","https://openalex.org/W2083681681","https://openalex.org/W2956382393","https://openalex.org/W1877657449","https://openalex.org/W2146865435"],"abstract_inverted_index":{"With":[0],"the":[1,14,38,46,54,76,91,100,138,151],"rapid":[2],"development":[3],"of":[4,34,49,57,75,102,123,137,161],"deep":[5,15,69,139,152],"learning":[6,16,153],"models":[7,199],"and":[8,95,130,169,175,189,197],"hardware":[9],"support":[10],"for":[11,90,133,165,192],"dense":[12,92],"computing,":[13],"(DL)":[17],"workload":[18],"characteristics":[19],"changed":[20],"significantly":[21],"from":[22,126],"a":[23,31,41,67,115,120],"few":[24,42],"hot":[25],"spots":[26],"on":[27,200],"compute-intensive":[28,43,93,108],"operations":[29,35,44,94],"to":[30,65,80],"broad":[32],"range":[33],"scattered":[36],"across":[37,106],"models.":[39],"Accelerating":[40],"using":[45,124],"expert-tuned":[47,131],"implementation":[48],"primitives":[50,190],"doesn't":[51],"fully":[52],"exploit":[53],"performance":[55,88,183],"potential":[56],"AI":[58],"hardware.":[59],"Various":[60],"efforts":[61],"have":[62],"been":[63],"made":[64],"compile":[66],"full":[68],"neural":[70,140],"network":[71,141],"(DNN)":[72],"graph.":[73,142],"One":[74],"biggest":[77],"challenges":[78,149],"is":[79],"achieve":[81],"high-performance":[82,134],"tensor":[83,116,167,187],"compilation":[84,97],"by":[85],"generating":[86],"expert-level":[87],"code":[89,135],"applying":[96],"optimization":[98,129,148,164],"at":[99],"scope":[101],"DNN":[103,194],"computation":[104,195],"graph":[105,162],"multiple":[107],"operations.":[109],"We":[110],"present":[111],"oneDNN":[112,143],"Graph":[113,144],"Compiler,":[114],"compiler":[117,128,188],"that":[118],"employs":[119],"hybrid":[121],"approach":[122],"techniques":[125],"both":[127],"kernels":[132],"generation":[136],"Compiler":[145],"addresses":[146],"unique":[147],"in":[150],"domain,":[154],"such":[155],"as":[156],"low-precision":[157],"computation,":[158],"aggressive":[159],"fusion":[160],"operations,":[163],"static":[166],"shapes":[168],"memory":[170,176],"layout,":[171],"constant":[172],"weight":[173],"optimization,":[174],"buffer":[177],"reuse.":[178],"Experimental":[179],"results":[180],"demonstrate":[181],"significant":[182],"gains":[184],"over":[185],"existing":[186],"library":[191],"performance-critical":[193],"graphs":[196],"end-to-end":[198],"Intel\u00ae":[201],"Xeon\u00ae":[202],"Scalable":[203],"Processors.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}