{"id":"https://openalex.org/W2935753164","doi":null,"title":"swTVM: Exploring the Automated Compilation for Deep Learning on Sunway Architecture","display_name":"swTVM: Exploring the Automated Compilation for Deep Learning on Sunway Architecture","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2935753164","mag":"2935753164"},"language":"en","primary_location":{"id":"mag:2935753164","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.07404.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.07404.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101869479","display_name":"Changxi Liu","orcid":"https://orcid.org/0000-0001-9240-5926","observed_orcids":["https://orcid.org/0000-0001-9240-5926"]},"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":"Changxi Liu","raw_affiliation_strings":["Beihang University)"],"raw_orcid":"https://orcid.org/0000-0001-9240-5926","affiliations":[{"raw_affiliation_string":"Beihang University)","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","observed_orcids":["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)"],"raw_orcid":"https://orcid.org/0000-0003-1101-7927","affiliations":[{"raw_affiliation_string":"Beihang University)","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103130209","display_name":"Rujun Sun","orcid":"https://orcid.org/0000-0001-9037-6957","observed_orcids":["https://orcid.org/0000-0001-9037-6957"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rujun Sun","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9037-6957","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556","observed_orcids":["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)"],"raw_orcid":"https://orcid.org/0000-0002-7186-0556","affiliations":[{"raw_affiliation_string":"Beihang University)","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038750675","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-1297-4462","observed_orcids":["https://orcid.org/0000-0003-1297-4462","https://orcid.org/0000-0003-3486-6016"]},"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":"Lin Gan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0003-1297-4462","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591592","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254","observed_orcids":["https://orcid.org/0000-0002-8673-8254"]},"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":"Guangwen Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473","observed_orcids":["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)"],"raw_orcid":"https://orcid.org/0000-0002-5382-1473","affiliations":[{"raw_affiliation_string":"Beihang University)","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":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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":0.9965999722480774,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0015999999595806003,"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":0.0010000000474974513,"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/deep-learning-compilers","display_name":"deep learning compilers","score":0.6779999732971191},{"id":"https://openalex.org/keywords/tvm","display_name":"TVM","score":0.8320000171661377},{"id":"https://openalex.org/keywords/ahead-of-time-compilation","display_name":"ahead-of-time compilation","score":0.9169999957084656},{"id":"https://openalex.org/keywords/cross-compilation","display_name":"cross-compilation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.7260000109672546},{"id":"https://openalex.org/keywords/deep-neural-network-acceleration","display_name":"deep neural network acceleration","score":0.5680000185966492},{"id":"https://openalex.org/keywords/alexnet","display_name":"AlexNet","score":0.8820000290870667},{"id":"https://openalex.org/keywords/vgg19","display_name":"VGG19","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.857088565826416},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7737720608711243},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7487565279006958},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.603441059589386},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5867483019828796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5004737377166748},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4598484933376312},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2154935598373413}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2935753164","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.07404.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2935753164","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.07404.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2186615578","https://openalex.org/W2341528187","https://openalex.org/W2342840547","https://openalex.org/W2402144811","https://openalex.org/W2728256789","https://openalex.org/W2730740223","https://openalex.org/W2749559108","https://openalex.org/W2761434131","https://openalex.org/W2767373187","https://openalex.org/W2767935072","https://openalex.org/W2784561332","https://openalex.org/W2786320458","https://openalex.org/W2789228469","https://openalex.org/W2798341898","https://openalex.org/W2804032941","https://openalex.org/W2804500013","https://openalex.org/W2868091835","https://openalex.org/W2891832717","https://openalex.org/W2899133614","https://openalex.org/W2914505133","https://openalex.org/W2942862658","https://openalex.org/W2950635152"],"related_works":["https://openalex.org/W4285075806","https://openalex.org/W4386629537","https://openalex.org/W2804032941","https://openalex.org/W2728256789","https://openalex.org/W2787513823","https://openalex.org/W7102545526","https://openalex.org/W4225429124","https://openalex.org/W2790601347","https://openalex.org/W2981686346","https://openalex.org/W2899133614"],"abstract_inverted_index":{"The":[0,149,169],"flourish":[1],"of":[2,155,171,213,243],"deep":[3,34,75,144,163,214,244],"learning":[4,35,76,145,215,245],"frameworks":[5],"and":[6,23,47,74,130,177,183,194,216,223,247],"hardware":[7,24,51],"platforms":[8],"has":[9],"been":[10],"demanding":[11],"an":[12],"efficient":[13,141],"compiler":[14,207,246],"that":[15,91,236],"can":[16,239],"shield":[17],"the":[18,32,54,56,81,93,111,115,153,202,206,211,233,241],"diversity":[19],"in":[20,25,44,71,83,137,225],"both":[21,72],"software":[22],"order":[26,138],"to":[27,96,139,157,209,230],"provide":[28],"application":[29,146],"portability.":[30],"Among":[31],"exiting":[33],"compilers,":[36],"TVM":[37,95],"is":[38,201],"well":[39],"known":[40],"for":[41,66,100,121,125,134,143,161,175],"its":[42,67],"efficiency":[43,224],"code":[45,142,160,174],"generation":[46],"optimization":[48],"across":[49],"diverse":[50],"devices.":[52],"In":[53,107],"meanwhile,":[55],"Sunway":[57,248],"many-core":[58,249],"processor":[59],"renders":[60],"itself":[61],"as":[62,105,118],"a":[63],"competitive":[64],"candidate":[65],"attractive":[68],"computational":[69],"power":[70,242],"scientific":[73],"applications.":[77],"This":[78,199],"paper":[79],"combines":[80],"trends":[82],"these":[84],"two":[85],"directions.":[86],"Specifically,":[87],"we":[88,109],"propose":[89],"swTVM":[90,156,180],"extends":[92],"original":[94],"support":[97],"ahead-of-time":[98],"compilation":[99,116],"architecture":[101,112,219],"requiring":[102],"cross-compilation":[103],"such":[104,117],"Sunway.":[106,148,168],"addition,":[108],"leverage":[110],"features":[113],"during":[114],"core":[119],"group":[120],"massive":[122],"parallelism,":[123],"DMA":[124],"high":[126,217],"bandwidth":[127],"memory":[128,133],"transfer":[129],"local":[131],"device":[132],"data":[135],"locality,":[136],"generate":[140,159],"on":[147,167,186,192],"experimental":[150],"results":[151],"show":[152],"ability":[154],"automatically":[158,172],"various":[162],"neural":[164],"network":[165],"models":[166],"performance":[170,218],"generated":[173],"AlexNet":[176],"VGG-19":[178],"by":[179],"achieves":[181],"6.71x":[182],"2.45x":[184],"speedup":[185],"average":[187],"than":[188],"hand-optimized":[189],"OpenACC":[190],"implementations":[191],"convolution":[193],"fully":[195],"connected":[196],"layers":[197],"respectively.":[198],"work":[200],"first":[203],"attempt":[204],"from":[205],"perspective":[208],"bridge":[210],"gap":[212],"particularly":[220],"with":[221],"productivity":[222],"mind.":[226],"We":[227],"would":[228],"like":[229],"open":[231],"source":[232],"implementation":[234],"so":[235],"more":[237],"people":[238],"embrace":[240],"processor.":[250]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2019-04-25T00:00:00"}