{"id":"https://openalex.org/W2233797083","doi":"https://doi.org/10.1145/2830772.2830810","title":"Neural acceleration for GPU throughput processors","display_name":"Neural acceleration for GPU throughput processors","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2233797083","doi":"https://doi.org/10.1145/2830772.2830810","mag":"2233797083"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830810","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830810","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070172290","display_name":"Amir Yazdanbakhsh","orcid":"https://orcid.org/0000-0001-8199-7671"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Yazdanbakhsh","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037553165","display_name":"Jongse Park","orcid":"https://orcid.org/0000-0002-6629-449X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jongse Park","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082318034","display_name":"Hardik Sharma","orcid":"https://orcid.org/0000-0003-0028-013X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hardik Sharma","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032350195","display_name":"Pejman Lotfi-Kamran","orcid":"https://orcid.org/0000-0003-3293-8274"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Pejman Lotfi-Kamran","raw_affiliation_strings":["Institute for Research in Fundamental Sciences (IPM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research in Fundamental Sciences (IPM)","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084514143","display_name":"Hadi Esmaeilzadeh","orcid":"https://orcid.org/0000-0002-8548-1039"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Esmaeilzadeh","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.8246,"has_fulltext":true,"cited_by_count":110,"citation_normalized_percentile":{"value":0.99352332,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8818524479866028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8717321753501892},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6898120641708374},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6300485134124756},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5376831889152527},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5321577787399292},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5256655812263489},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.504186749458313},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4873264729976654},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4746939539909363},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4570621848106384},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4360640347003937},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43516698479652405},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41710036993026733},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3540698289871216},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25535398721694946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16894316673278809},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.07814860343933105},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07467052340507507}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8818524479866028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717321753501892},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6898120641708374},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6300485134124756},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5376831889152527},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5321577787399292},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5256655812263489},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.504186749458313},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4873264729976654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4746939539909363},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4570621848106384},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4360640347003937},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43516698479652405},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41710036993026733},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3540698289871216},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25535398721694946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16894316673278809},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.07814860343933105},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07467052340507507},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2830772.2830810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830810","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:smartech.gatech.edu:1853/53816","is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/53816","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/2830772.2830810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830810","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1084401270","display_name":"EAGER: Language and Architecture Design for Approximation at Different Granularities","funder_award_id":"1553192","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6017102015","display_name":null,"funder_award_id":"#2014-EP-2577","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7361479938","display_name":null,"funder_award_id":"CCF #1553192","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8285063668","display_name":null,"funder_award_id":"CCF#1553192","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320308258","display_name":"Qualcomm","ror":"https://ror.org/002zrf773"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2233797083.pdf","grobid_xml":"https://content.openalex.org/works/W2233797083.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W68530641","https://openalex.org/W120098372","https://openalex.org/W1966449927","https://openalex.org/W1967519200","https://openalex.org/W1973021400","https://openalex.org/W1979527452","https://openalex.org/W1981473264","https://openalex.org/W1988290377","https://openalex.org/W1996431812","https://openalex.org/W2000873501","https://openalex.org/W2005487033","https://openalex.org/W2006312753","https://openalex.org/W2010069327","https://openalex.org/W2010468809","https://openalex.org/W2013959289","https://openalex.org/W2014423307","https://openalex.org/W2026764611","https://openalex.org/W2033982707","https://openalex.org/W2044694954","https://openalex.org/W2047001217","https://openalex.org/W2047060659","https://openalex.org/W2053287400","https://openalex.org/W2056137328","https://openalex.org/W2056616238","https://openalex.org/W2057434193","https://openalex.org/W2065439108","https://openalex.org/W2068710123","https://openalex.org/W2080592089","https://openalex.org/W2082738287","https://openalex.org/W2084732345","https://openalex.org/W2090557012","https://openalex.org/W2093043622","https://openalex.org/W2095730858","https://openalex.org/W2097243222","https://openalex.org/W2097652499","https://openalex.org/W2105102111","https://openalex.org/W2105544671","https://openalex.org/W2114703523","https://openalex.org/W2115172404","https://openalex.org/W2119299853","https://openalex.org/W2126869140","https://openalex.org/W2140145164","https://openalex.org/W2142119745","https://openalex.org/W2142883190","https://openalex.org/W2143283746","https://openalex.org/W2146065717","https://openalex.org/W2149870396","https://openalex.org/W2153331583","https://openalex.org/W2160428323","https://openalex.org/W2165448367","https://openalex.org/W2166250385","https://openalex.org/W2166773037","https://openalex.org/W2168429197","https://openalex.org/W2170382128","https://openalex.org/W2170881177","https://openalex.org/W2187230075","https://openalex.org/W2766736793","https://openalex.org/W3005822915","https://openalex.org/W4231091214","https://openalex.org/W4232168013","https://openalex.org/W4234461763","https://openalex.org/W4236433846","https://openalex.org/W4236690266","https://openalex.org/W4240237526","https://openalex.org/W4243410967","https://openalex.org/W4244884309","https://openalex.org/W4247892942","https://openalex.org/W4251054771","https://openalex.org/W4253998042"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"can":[4],"accelerate":[5],"diverse":[6,190],"classes":[7],"of":[8,21,63,84,131,137,153,192,216],"applications,":[9],"such":[10],"as":[11],"recognition,":[12],"gaming,":[13],"data":[14],"analytics,":[15],"weather":[16],"prediction,":[17],"and":[18,39,53,102,155,177,204],"multimedia.":[19],"Many":[20],"these":[22],"applications":[23,89],"are":[24,222],"amenable":[25],"to":[26,35,49,98,162,218],"approximate":[27],"execution.":[28],"This":[29,95,140],"application":[30],"characteristic":[31],"provides":[32],"an":[33],"opportunity":[34],"improve":[36],"GPU":[37,68,103,138,165],"performance":[38,52],"efficiency.":[40],"Among":[41],"approximation":[42],"techniques,":[43],"neural":[44,64,101,132,159],"accelerators":[45,65,79,104,133],"have":[46],"been":[47],"shown":[48],"provide":[50],"significant":[51],"efficiency":[54],"gains":[55],"when":[56],"augmenting":[57],"CPU":[58],"processors.":[59],"However,":[60],"the":[61,88,91,148,151,156,163,211,214],"integration":[62,130],"within":[66,183],"a":[67,76,117,144,173,178,189,200,205],"processor":[69],"has":[70],"remained":[71],"unexplored.":[72],"GPUs":[73],"are,":[74],"in":[75,87,213],"sense,":[77],"many-core":[78],"that":[80,127,146],"exploit":[81],"large":[82,135],"degrees":[83],"data-level":[85],"parallelism":[86],"through":[90],"SIMT":[92,108],"execution":[93,109],"model.":[94],"paper":[96],"aims":[97],"harmoniously":[99],"bring":[100],"together":[105],"without":[106],"hindering":[107],"or":[110],"adding":[111],"excessive":[112],"hardware":[113],"overhead.":[114,229],"We":[115],"introduce":[116],"low":[118],"overhead":[119],"neurally":[120],"accelerated":[121],"architecture":[122],"for":[123,134,170],"GPUs,":[124],"called":[125],"NGPU,":[126],"enables":[128],"scalable":[129],"number":[136],"cores.":[139],"work":[141],"also":[142],"devises":[143],"mechanism":[145,198],"controls":[147],"tradeoff":[149],"between":[150],"quality":[152,185,196,215],"results":[154,169,217],"benefits":[157,221],"from":[158],"acceleration.":[160],"Compared":[161],"baseline":[164],"architecture,":[166],"cycle-accurate":[167],"simulation":[168],"NGPU":[171],"show":[172],"2.4\u00d7":[174],"average":[175,180,202],"speedup":[176,203],"2.8\u00d7":[179],"energy":[181,207],"reduction":[182,208],"10%":[184],"loss":[186],"margin":[187],"across":[188],"set":[191],"benchmarks.":[193],"The":[194],"proposed":[195],"control":[197],"retains":[199],"1.9\u00d7":[201],"2.1\u00d7":[206],"while":[209],"reducing":[210],"degradation":[212],"2.5%.":[219],"These":[220],"achieved":[223],"by":[224],"less":[225],"than":[226],"1%":[227],"area":[228]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}