{"id":"https://openalex.org/W3186047385","doi":"https://doi.org/10.23919/date51398.2021.9473984","title":"Efficient Tensor Cores support in TVM for Low-Latency Deep learning","display_name":"Efficient Tensor Cores support in TVM for Low-Latency Deep learning","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3186047385","doi":"https://doi.org/10.23919/date51398.2021.9473984","mag":"3186047385"},"language":"en","primary_location":{"id":"doi:10.23919/date51398.2021.9473984","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9473984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046339814","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-3424-9643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062737440","display_name":"Savvas Sioutas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savvas Sioutas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032436846","display_name":"Sander Stuijk","orcid":"https://orcid.org/0000-0002-2518-6847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sander Stuijk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013023665","display_name":"Andrew Nelson","orcid":"https://orcid.org/0000-0002-4071-3502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Nelson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081768631","display_name":"Henk Corporaal","orcid":"https://orcid.org/0000-0003-4506-5732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henk Corporaal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9889000058174133,"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":0.8379367589950562},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7699683904647827},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7202922105789185},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6832756400108337},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.672855019569397},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5894357562065125},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5220829844474792},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4185869097709656},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38152939081192017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3650175929069519},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16649454832077026},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14096251130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379367589950562},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7699683904647827},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7202922105789185},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6832756400108337},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.672855019569397},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5894357562065125},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5220829844474792},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4185869097709656},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38152939081192017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3650175929069519},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16649454832077026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14096251130104065},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/date51398.2021.9473984","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9473984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/186181dc-dc45-41d3-b0be-15c753f2f8dc","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/186181dc-dc45-41d3-b0be-15c753f2f8dc","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sun, W, Sioutas, S, Stuijk, S, Nelson, A & Corporaal, H 2021, Efficient Tensor Cores support in TVM for Low-Latency Deep learning. in Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021., 9473984, Institute of Electrical and Electronics Engineers, pp. 120-123, 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021, Grenoble, France, 1/02/21. https://doi.org/10.23919/DATE51398.2021.9473984","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/186181dc-dc45-41d3-b0be-15c753f2f8dc","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/186181dc-dc45-41d3-b0be-15c753f2f8dc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021, 120 - 123","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1922123711","https://openalex.org/W2055312318","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2402144811","https://openalex.org/W2565305208","https://openalex.org/W2670151302","https://openalex.org/W2791673912","https://openalex.org/W2804032941","https://openalex.org/W2804500013","https://openalex.org/W2806891462","https://openalex.org/W2889647155","https://openalex.org/W2919115771","https://openalex.org/W2945580137","https://openalex.org/W2953384591","https://openalex.org/W2954580493","https://openalex.org/W2963340555","https://openalex.org/W2963960923","https://openalex.org/W2970971581","https://openalex.org/W3028780355","https://openalex.org/W3036692157","https://openalex.org/W3096456556","https://openalex.org/W3101543398","https://openalex.org/W4249932213","https://openalex.org/W4287826815","https://openalex.org/W4295312788","https://openalex.org/W6713134421","https://openalex.org/W6740373327","https://openalex.org/W6752057402","https://openalex.org/W6754777574","https://openalex.org/W6760385162","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Deep":[0],"learning":[1,46],"algorithms":[2],"are":[3,17],"gaining":[4],"popularity":[5],"in":[6,44],"autonomous":[7],"systems.":[8],"These":[9],"systems":[10],"typically":[11],"have":[12],"stringent":[13],"latency":[14,88,104],"constraints":[15],"that":[16,85,99],"challenging":[18],"to":[19,34,81,110],"meet":[20],"given":[21],"the":[22,39,57,82,103,111],"high":[23],"computational":[24],"demands":[25],"of":[26,38,60],"these":[27],"algorithms.":[28,47],"Nvidia":[29],"introduced":[30],"Tensor":[31],"Cores":[32],"(TCs)":[33],"speed":[35],"up":[36],"some":[37],"most":[40],"commonly":[41],"used":[42],"operations":[43],"deep":[45],"Compilers":[48],"(e.g.,":[49,53],"TVM)":[50],"and":[51,119],"libraries":[52],"cuDNN)":[54],"focus":[55],"on":[56,105,114,122],"efficient":[58],"usage":[59],"TCs":[61,89],"when":[62],"performing":[63],"batch":[64,74,93],"processing.":[65,75],"Latency":[66],"sensitive":[67],"applications":[68],"can":[69],"however":[70],"not":[71],"exploit":[72],"large":[73],"This":[76],"paper":[77],"presents":[78],"an":[79,123],"extension":[80],"TVM":[83],"compiler":[84],"generates":[86],"low":[87],"implementations,":[90],"particularly":[91],"for":[92],"size":[94],"1.":[95],"Experimental":[96],"results":[97],"show":[98],"our":[100],"solution":[101],"reduces":[102],"average":[106],"by":[107,120],"14%":[108],"compared":[109],"cuDNN":[112],"library":[113],"a":[115],"Desktop":[116],"RTX2070":[117],"GPU,":[118],"49%":[121],"Embedded":[124],"Jetson":[125],"Xavier":[126],"GPU.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}