{"id":"https://openalex.org/W4281616485","doi":"https://doi.org/10.1145/3526241.3530316","title":"KunlunTVM: A Compilation Framework for Kunlun Chip Supporting Both Training and Inference","display_name":"KunlunTVM: A Compilation Framework for Kunlun Chip Supporting Both Training and Inference","publication_year":2022,"publication_date":"2022-06-02","ids":{"openalex":"https://openalex.org/W4281616485","doi":"https://doi.org/10.1145/3526241.3530316"},"language":"en","primary_location":{"id":"doi:10.1145/3526241.3530316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526241.3530316","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526241.3530316","source":{"id":"https://openalex.org/S4363608736","display_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3526241.3530316","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082035207","display_name":"Jun Zeng","orcid":"https://orcid.org/0000-0001-7441-0406"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Zeng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080354226","display_name":"Mingyang Kou","orcid":"https://orcid.org/0000-0002-9562-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Kou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058812423","display_name":"Hailong Yao","orcid":"https://orcid.org/0000-0002-8750-3086"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082035207"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.23713104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.815773606300354},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.786324143409729},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7468938827514648},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.5492933392524719},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5456569194793701},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49142706394195557},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4859253466129303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4705664813518524},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4172684848308563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3776478171348572},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35073012113571167},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.33526796102523804},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3245663046836853},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24345389008522034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815773606300354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.786324143409729},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7468938827514648},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.5492933392524719},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5456569194793701},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49142706394195557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4859253466129303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4705664813518524},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4172684848308563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3776478171348572},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35073012113571167},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33526796102523804},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3245663046836853},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24345389008522034},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3526241.3530316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526241.3530316","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526241.3530316","source":{"id":"https://openalex.org/S4363608736","display_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3526241.3530316","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526241.3530316","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526241.3530316","source":{"id":"https://openalex.org/S4363608736","display_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281616485.pdf","grobid_xml":"https://content.openalex.org/works/W4281616485.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1966668827","https://openalex.org/W1977177161","https://openalex.org/W1996615911","https://openalex.org/W2194775991","https://openalex.org/W2585720638","https://openalex.org/W2606722458","https://openalex.org/W2805566098","https://openalex.org/W2899915146","https://openalex.org/W2949967139","https://openalex.org/W3004659153","https://openalex.org/W3091969046","https://openalex.org/W3093977741","https://openalex.org/W3098220359","https://openalex.org/W3100518172","https://openalex.org/W3122286897","https://openalex.org/W3138578552","https://openalex.org/W3157020554","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4312200629","https://openalex.org/W4223943233","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4309045103","https://openalex.org/W4225161397","https://openalex.org/W3014300295","https://openalex.org/W3164822677","https://openalex.org/W4250304930","https://openalex.org/W2963058055"],"abstract_inverted_index":{"With":[0],"the":[1,24,67,96,107,115],"rapid":[2],"development":[3],"of":[4,15,29],"deep":[5],"learning,":[6],"training":[7,50,76,92],"big":[8],"neural":[9],"network":[10],"models":[11],"demands":[12],"huge":[13],"amount":[14],"computing":[16],"power.Therefore,":[17],"many":[18],"accelerators":[19],"are":[20,110],"designed":[21],"to":[22,47,60,90],"meet":[23],"performance":[25,38,57,93],"requirements.":[26],"Recently,":[27],"series":[28],"Kunlun":[30,54,81,101],"chips":[31],"have":[32],"been":[33],"released,":[34],"which":[35],"claim":[36],"comparable":[37],"over":[39,95],"GPUs.":[40],"However,":[41],"there":[42],"lacks":[43],"an":[44],"end-to-end":[45,69],"compiler":[46,70],"support":[48],"both":[49,75],"and":[51,77,112],"inference":[52,78],"on":[53,72,80],"chip,leaving":[55],"large":[56],"optimization":[58],"space":[59],"be":[61],"explored.":[62],"This":[63],"paper":[64],"presents":[65],"KunlunTVM,":[66],"first":[68],"based":[71],"TVM,":[73],"supporting":[74,100],"tasks":[79],"Chip.":[82],"Experimental":[83],"results":[84],"show":[85],"that":[86,106],"KunlunTVM":[87],"achieves":[88],"up":[89],"5x":[91],"improvement":[94],"existing":[97],"framework":[98,117],"PaddlePaddle":[99],"chip.":[102],"It":[103],"is":[104],"noteworthy":[105],"proposed":[108],"methods":[109],"general":[111],"extensible":[113],"for":[114],"TVM":[116],"targeting":[118],"different":[119],"backends.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}