{"id":"https://openalex.org/W4297097055","doi":"https://doi.org/10.1109/hcs55958.2022.9895617","title":"VTA-NIC: Deep Learning Inference Serving in Network Interface Cards","display_name":"VTA-NIC: Deep Learning Inference Serving in Network Interface Cards","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4297097055","doi":"https://doi.org/10.1109/hcs55958.2022.9895617"},"language":"en","primary_location":{"id":"doi:10.1109/hcs55958.2022.9895617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hcs55958.2022.9895617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Hot Chips 34 Symposium (HCS)","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/A5069099139","display_name":"Kenji Tanaka","orcid":"https://orcid.org/0000-0003-2320-4535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Tanaka","raw_affiliation_strings":["NTT Device Technology Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077656627","display_name":"Yuki Arikawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Arikawa","raw_affiliation_strings":["NTT Device Technology Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036198872","display_name":"Kazutaka Morita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazutaka Morita","raw_affiliation_strings":["NTT Software Innovation Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101100781","display_name":"Tsuyoshi Ito","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuyoshi Ito","raw_affiliation_strings":["NTT Device Technology Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005066302","display_name":"Takashi Uchida","orcid":"https://orcid.org/0000-0002-8257-7334"},"institutions":[{"id":"https://openalex.org/I4210126820","display_name":"Fixstars Solutions (United States)","ror":"https://ror.org/035myfa14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126820"]},{"id":"https://openalex.org/I4388482706","display_name":"ARES (United States)","ror":"https://ror.org/03pnvey90","country_code":null,"type":"company","lineage":["https://openalex.org/I4388482706"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Uchida","raw_affiliation_strings":["Fixstars Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fixstars Corporation","institution_ids":["https://openalex.org/I4210126820","https://openalex.org/I4388482706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076106576","display_name":"Natsuko Saito","orcid":"https://orcid.org/0009-0005-4059-7491"},"institutions":[{"id":"https://openalex.org/I4210126820","display_name":"Fixstars Solutions (United States)","ror":"https://ror.org/035myfa14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126820"]},{"id":"https://openalex.org/I4388482706","display_name":"ARES (United States)","ror":"https://ror.org/03pnvey90","country_code":null,"type":"company","lineage":["https://openalex.org/I4388482706"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natsuko Saito","raw_affiliation_strings":["Fixstars Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fixstars Corporation","institution_ids":["https://openalex.org/I4210126820","https://openalex.org/I4388482706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015894637","display_name":"Shinya Kaji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126820","display_name":"Fixstars Solutions (United States)","ror":"https://ror.org/035myfa14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126820"]},{"id":"https://openalex.org/I4388482706","display_name":"ARES (United States)","ror":"https://ror.org/03pnvey90","country_code":null,"type":"company","lineage":["https://openalex.org/I4388482706"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinya Kaji","raw_affiliation_strings":["Fixstars Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fixstars Corporation","institution_ids":["https://openalex.org/I4210126820","https://openalex.org/I4388482706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037700663","display_name":"Takeshi Sakamoto","orcid":"https://orcid.org/0000-0001-6312-2249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takeshi Sakamoto","raw_affiliation_strings":["NTT Device Technology Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1084195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","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":0.6568639874458313},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.656779944896698},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47209638357162476},{"id":"https://openalex.org/keywords/microservices","display_name":"Microservices","score":0.4435116946697235},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3811536729335785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3226587474346161},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.1670438051223755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6568639874458313},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.656779944896698},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47209638357162476},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.4435116946697235},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3811536729335785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3226587474346161},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.1670438051223755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hcs55958.2022.9895617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hcs55958.2022.9895617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Hot Chips 34 Symposium (HCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2794670651","https://openalex.org/W3033527233","https://openalex.org/W4223585153"],"related_works":["https://openalex.org/W4210334847","https://openalex.org/W3181741639","https://openalex.org/W4367181468","https://openalex.org/W2767473057","https://openalex.org/W4225586032","https://openalex.org/W3003367851","https://openalex.org/W1492892507","https://openalex.org/W3119944216","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"VTA-NIC":[0,54],"Chip":[1],"ArchitectureWe":[2],"aim":[3],"to":[4,87,157],"achieve":[5],"DL":[6],"inference":[7],"serving":[8,176],"(DLIS)":[9,99],"without":[10],"CPU":[11],"interference.We":[12],"integrate":[13],"hardware":[14],"data":[15,121,123],"paths":[16],"as":[17],"a":[18,23,108],"NIC":[19],"(Network":[20],"Interface":[21],"Card),":[22],"REST":[24],"API":[25],"parser/deparser":[26],"and":[27,172],"multiple":[28],"VTAs":[29],"(Versatile":[30],"Tensor":[31],"Accelerators).ConfigurationVTA-NICProcess":[32],"node16":[33],"nm":[34],"FinFET":[35],"@Xilinx":[36],"FPGANumber":[37],"of":[38,53,60,70,102,135,148,164,174],"Cores8":[39],"VTA":[40],"CoresCore":[41],"Frequency213":[42],"MHzMACs":[43],"per":[44],"core169Memory":[45],"Throughput19.2GB/s":[46],"(DDR4-2400)Number":[47],"precisionINT8PerformancePower":[48],"EfficiencyThe":[49],"DLIS":[50,137,152,166],"power":[51],"efficiency":[52],"is":[55,81,85,100,105,178],"6.1x":[56],"better":[57],"than":[58],"that":[59],"GPU":[61],"(Nvidia":[62],"V100).Tail":[63],"LatencyAt":[64],"high":[65],"load,":[66],"the":[67,78,88,128,136,146,160,175],"tail":[68,79,153,170],"latency":[69,80,138,154],"heterogeneous":[71],"systems":[72],"unexpectedly":[73],"increases.":[74],"With":[75],"our":[76,131],"chip,":[77],"predictable":[82],"since":[83],"it":[84],"proportional":[86],"load.BackgroundRecently,":[89],"web":[90],"applications":[91],"are":[92,113],"often":[93],"built":[94],"on":[95],"microservices.DL":[96],"Inference":[97,184],"Serving":[98],"one":[101],"those":[103],"microservices1.DLIS":[104],"provisioned":[106],"with":[107],"special":[109],"accelerator":[110],"instance2.The":[111],"microservices/instances":[112],"loosely":[114],"coupled":[115],"via":[116,124],"APIs.BackgroundAccelerator":[117],"instances":[118],"risk":[119],"inefficient":[120],"movement.1.Moving":[122],"host":[125,149],"processors":[126,150],"decreases":[127],"accelerator's":[129],"utilization.3a.In":[130],"preliminary":[132],"experiments,":[133],"half":[134,173],"was":[139],"caused":[140],"by":[141,155],"moving":[142],"data.2.Under":[143],"high-load":[144],"conditions,":[145],"interference":[147],"degrades":[151],"up":[156],"100":[158],"times4.a.In":[159],"real":[161],"cloud,":[162],"9%":[163],"light":[165],"tasks":[167],"suffer":[168],"server":[169],"latency,":[171],"time":[177],"waiting":[179],"time.5Model:":[180],"ResNet-18@TensorRTPrecision:":[181],"INT8System:":[182],"Triton":[183],"ServerAccelerator:":[185],"Nvidia":[186],"V100":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}