{"id":"https://openalex.org/W4378801057","doi":"https://doi.org/10.1145/3583781.3590302","title":"High-Throughput Edge Inference for BERT Models via Neural Architecture Search and Pipeline","display_name":"High-Throughput Edge Inference for BERT Models via Neural Architecture Search and Pipeline","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378801057","doi":"https://doi.org/10.1145/3583781.3590302"},"language":"en","primary_location":{"id":"doi:10.1145/3583781.3590302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583781.3590302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","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/A5047765070","display_name":"Hung-Yang Chang","orcid":"https://orcid.org/0000-0001-9231-5613"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hung-Yang Chang","raw_affiliation_strings":["McGill University, Montr\u00e9al, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056921752","display_name":"Seyyed Hasan Mozafari","orcid":"https://orcid.org/0000-0002-0360-1747"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Seyyed Hasan Mozafari","raw_affiliation_strings":["McGill University, Montr\u00e9al, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079264223","display_name":"James J. Clark","orcid":"https://orcid.org/0000-0002-4512-6171"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James J. Clark","raw_affiliation_strings":["McGill University, Montr\u00e9al, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034701871","display_name":"Brett H. Meyer","orcid":"https://orcid.org/0000-0002-6650-3298"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brett H. Meyer","raw_affiliation_strings":["McGill University, Montr\u00e9al, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091600002","display_name":"Warren J. Gross","orcid":"https://orcid.org/0000-0002-6226-6037"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Warren J. Gross","raw_affiliation_strings":["McGill University, Montr\u00e9al, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047765070"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04696261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8590190410614014},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8277735114097595},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.8097888827323914},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7212978601455688},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6075199246406555},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5770981311798096},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.441193550825119},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42597970366477966},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36228811740875244},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.350921094417572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2785416841506958},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0894404947757721},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.061041563749313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590190410614014},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8277735114097595},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.8097888827323914},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7212978601455688},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6075199246406555},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5770981311798096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.441193550825119},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42597970366477966},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36228811740875244},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.350921094417572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2785416841506958},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0894404947757721},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.061041563749313354},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583781.3590302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583781.3590302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","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":13,"referenced_works":["https://openalex.org/W1976188373","https://openalex.org/W2085830763","https://openalex.org/W2126105956","https://openalex.org/W2922395136","https://openalex.org/W2952638691","https://openalex.org/W2963855133","https://openalex.org/W2998506323","https://openalex.org/W3015609966","https://openalex.org/W3038012435","https://openalex.org/W3105645800","https://openalex.org/W3167266074","https://openalex.org/W3177265267","https://openalex.org/W4255575499"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W3037187668","https://openalex.org/W2055243143","https://openalex.org/W2760721665","https://openalex.org/W4234772502","https://openalex.org/W2380685755","https://openalex.org/W2107954672","https://openalex.org/W2375218795","https://openalex.org/W2393010557"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"growing":[3],"interest":[4],"in":[5,48],"improving":[6],"the":[7,56],"BERT":[8,65],"inference":[9],"throughput":[10],"on":[11,75],"resource-constrained":[12],"edge":[13],"devices":[14],"for":[15,55,64],"a":[16,84],"satisfactory":[17],"user":[18],"experience.":[19],"One":[20],"methodology":[21,36],"is":[22,37],"to":[23,32,38,44,81],"employ":[24],"heterogeneous":[25],"computing,":[26],"which":[27],"utilizes":[28],"multiple":[29],"processing":[30],"elements":[31],"accelerate":[33],"inference.":[34],"Another":[35],"deploy":[39],"Neural":[40],"Architecture":[41],"Search":[42],"(NAS)":[43],"find":[45],"optimal":[46],"solutions":[47],"accuracy-throughput":[49],"design":[50],"space.":[51],"In":[52],"this":[53],"paper,":[54],"first":[57],"time,":[58],"we":[59],"incorporate":[60],"NAS":[61,71,82],"with":[62,72,83],"pipelining":[63,73],"models.":[66],"We":[67],"show":[68],"that":[69],"performing":[70],"achieves":[74],"average":[76],"53%":[77],"higher":[78],"throughput,":[79],"compared":[80],"homogeneous":[85],"system.":[86]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}