{"id":"https://openalex.org/W4200515842","doi":"https://doi.org/10.1109/hpec49654.2021.9622863","title":"Serving Machine Learning Inference Using Heterogeneous Hardware","display_name":"Serving Machine Learning Inference Using Heterogeneous Hardware","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200515842","doi":"https://doi.org/10.1109/hpec49654.2021.9622863"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5100733204","display_name":"Baolin Li","orcid":"https://orcid.org/0000-0001-9778-1023"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Baolin Li","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043450560","display_name":"Vijay Gadepally","orcid":"https://orcid.org/0000-0002-4598-2808"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gadepally","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103227438","display_name":"Siddharth Samsi","orcid":"https://orcid.org/0009-0000-2884-9688"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Samsi","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036141697","display_name":"Mark Veillette","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Veillette","raw_affiliation_strings":["MIT Lincoln Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":"https://orcid.org/0000-0002-7253-2458"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Devesh Tiwari","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100733204"],"corresponding_institution_ids":["https://openalex.org/I87182695"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51302288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9873999953269958,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861000180244446,"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/computer-science","display_name":"Computer science","score":0.8077735900878906},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7326893210411072},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6446402668952942},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5348763465881348},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.46187639236450195},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45983192324638367},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4431033432483673},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4228897988796234},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.30006492137908936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27700942754745483},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.2734465003013611},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.11989101767539978},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11939939856529236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077735900878906},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7326893210411072},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6446402668952942},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5348763465881348},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.46187639236450195},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45983192324638367},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4431033432483673},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4228897988796234},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30006492137908936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27700942754745483},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2734465003013611},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.11989101767539978},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11939939856529236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6700000166893005,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1714357736","https://openalex.org/W1901129140","https://openalex.org/W2012975714","https://openalex.org/W2016184960","https://openalex.org/W2024414272","https://openalex.org/W2069808690","https://openalex.org/W2102605133","https://openalex.org/W2179278898","https://openalex.org/W2549139847","https://openalex.org/W2604856537","https://openalex.org/W2609302349","https://openalex.org/W2798515322","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2956461999","https://openalex.org/W2962745591","https://openalex.org/W2962756146","https://openalex.org/W2963037989","https://openalex.org/W2963403751","https://openalex.org/W2963858294","https://openalex.org/W2963966702","https://openalex.org/W2964108773","https://openalex.org/W2970438301","https://openalex.org/W2979826702","https://openalex.org/W3001630685","https://openalex.org/W3005664618","https://openalex.org/W3016480885","https://openalex.org/W3016842236","https://openalex.org/W3022548332","https://openalex.org/W3030408490","https://openalex.org/W3040318838","https://openalex.org/W3043433718","https://openalex.org/W3047371394","https://openalex.org/W3096583839","https://openalex.org/W3097411828","https://openalex.org/W3104861085","https://openalex.org/W3105381414","https://openalex.org/W3130689885","https://openalex.org/W3155545507","https://openalex.org/W3167366622","https://openalex.org/W3176653330","https://openalex.org/W3210302937","https://openalex.org/W4287774547","https://openalex.org/W4288289123","https://openalex.org/W4293584584","https://openalex.org/W4297670610","https://openalex.org/W4297825594","https://openalex.org/W6628973269","https://openalex.org/W6639824700","https://openalex.org/W6696497002","https://openalex.org/W6730956707","https://openalex.org/W6735916004","https://openalex.org/W6748130322","https://openalex.org/W6750227808","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6759814162","https://openalex.org/W6765484274","https://openalex.org/W6769424276","https://openalex.org/W6778330239","https://openalex.org/W6778729859","https://openalex.org/W6782839094","https://openalex.org/W6785723781","https://openalex.org/W6794232432","https://openalex.org/W6796168768","https://openalex.org/W6803489858"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2055243143","https://openalex.org/W2760721665","https://openalex.org/W2945182031","https://openalex.org/W2995408604","https://openalex.org/W2081510580","https://openalex.org/W2943253919","https://openalex.org/W2620115225","https://openalex.org/W2765481182"],"abstract_inverted_index":{"The":[0,35,50,64],"growing":[1],"popularity":[2],"of":[3,11,80,100],"machine":[4],"learning":[5],"algorithms":[6],"and":[7,56,83,103],"the":[8,25,91,104],"wide":[9],"availability":[10],"hardware":[12,44],"accelerators":[13],"have":[14],"brought":[15],"up":[16,97,113],"new":[17],"challenges":[18],"on":[19,75],"inference":[20,29],"serving.":[21],"This":[22],"paper":[23],"explores":[24],"opportunity":[26],"to":[27,46,98,114],"serve":[28,48],"queries":[30],"with":[31],"a":[32,38,61,72],"heterogeneous":[33,43,66,93,106],"system.":[34],"system":[36,68,94,107],"has":[37],"central":[39],"optimizer":[40,51],"that":[41,90],"allocates":[42],"resources":[45],"cooperatively":[47],"queries.":[49],"supports":[52],"both":[53],"energy":[54],"minimization":[55],"throughput":[57,111],"maximization":[58],"while":[59],"satisfying":[60],"latency":[62],"target.":[63],"optimized":[65],"serving":[67],"is":[69],"evaluated":[70],"against":[71],"homogeneous":[73],"system,":[74],"two":[76],"representative":[77],"real-world":[78],"applications":[79],"radar":[81],"nowcasting":[82],"object":[84],"detection.":[85],"Our":[86],"evaluation":[87],"results":[88],"show":[89],"power-optimized":[92],"can":[95,108],"achieve":[96],"36%":[99],"power":[101],"saving,":[102],"throughput-optimized":[105],"increase":[109],"query":[110],"by":[112],"53%.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}