{"id":"https://openalex.org/W2765927961","doi":"https://doi.org/10.1145/3123939.3123979","title":"Scale-out acceleration for machine learning","display_name":"Scale-out acceleration for machine learning","publication_year":2017,"publication_date":"2017-10-14","ids":{"openalex":"https://openalex.org/W2765927961","doi":"https://doi.org/10.1145/3123939.3123979","mag":"2765927961"},"language":"en","primary_location":{"id":"doi:10.1145/3123939.3123979","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123939.3123979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture","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/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/A5089590312","display_name":"Divya Mahajan","orcid":"https://orcid.org/0009-0007-8184-0528"},"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":"Divya Mahajan","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/A5018716691","display_name":"Joon Kyung Kim","orcid":"https://orcid.org/0000-0002-7984-9669"},"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":"Joon Kyung Kim","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/A5074929393","display_name":"Preston Olds","orcid":null},"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":"Preston Olds","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":"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 and University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology and University of California","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"367","last_page":"381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9986000061035156,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.8311616778373718},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5297335982322693},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5201002359390259},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4466457962989807},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38158634305000305},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.327640175819397},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32739585638046265},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18300572037696838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311616778373718},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5297335982322693},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5201002359390259},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4466457962989807},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38158634305000305},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.327640175819397},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32739585638046265},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18300572037696838},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123939.3123979","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123939.3123979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3088063717","display_name":null,"funder_award_id":"YIP FA9550-17-1-0274","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6391745350","display_name":null,"funder_award_id":"CNS -1703812,ECCS-1609823,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/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1484369288","https://openalex.org/W1575115198","https://openalex.org/W1749792876","https://openalex.org/W1752712236","https://openalex.org/W1966795804","https://openalex.org/W2000967104","https://openalex.org/W2005487033","https://openalex.org/W2033882786","https://openalex.org/W2043607059","https://openalex.org/W2048266589","https://openalex.org/W2058797440","https://openalex.org/W2061570747","https://openalex.org/W2063459162","https://openalex.org/W2066443755","https://openalex.org/W2067523571","https://openalex.org/W2072566913","https://openalex.org/W2077428505","https://openalex.org/W2090850279","https://openalex.org/W2094233035","https://openalex.org/W2094756095","https://openalex.org/W2097839764","https://openalex.org/W2098257570","https://openalex.org/W2099705706","https://openalex.org/W2100905558","https://openalex.org/W2108199402","https://openalex.org/W2108948681","https://openalex.org/W2111444234","https://openalex.org/W2119697285","https://openalex.org/W2122522028","https://openalex.org/W2124093496","https://openalex.org/W2125203716","https://openalex.org/W2126760474","https://openalex.org/W2130062883","https://openalex.org/W2133156997","https://openalex.org/W2133233009","https://openalex.org/W2143609451","https://openalex.org/W2144839971","https://openalex.org/W2149328392","https://openalex.org/W2152839228","https://openalex.org/W2159400887","https://openalex.org/W2161238936","https://openalex.org/W2162942021","https://openalex.org/W2163383000","https://openalex.org/W2166029537","https://openalex.org/W2166706236","https://openalex.org/W2167008350","https://openalex.org/W2173213060","https://openalex.org/W2187230075","https://openalex.org/W2196986455","https://openalex.org/W2261808795","https://openalex.org/W2271840356","https://openalex.org/W2283962771","https://openalex.org/W2285660444","https://openalex.org/W2287011250","https://openalex.org/W2296319761","https://openalex.org/W2297100101","https://openalex.org/W2302023363","https://openalex.org/W2336650964","https://openalex.org/W2442974303","https://openalex.org/W2461217932","https://openalex.org/W2489529491","https://openalex.org/W2513554817","https://openalex.org/W2516141709","https://openalex.org/W2521149585","https://openalex.org/W2542189141","https://openalex.org/W2560912757","https://openalex.org/W2562773490","https://openalex.org/W2563587242","https://openalex.org/W2565305208","https://openalex.org/W2565851976","https://openalex.org/W2606722458","https://openalex.org/W2621285457","https://openalex.org/W2906043559","https://openalex.org/W2949198759","https://openalex.org/W2950094539","https://openalex.org/W2953212265","https://openalex.org/W2963632834","https://openalex.org/W2964174152","https://openalex.org/W2999941859","https://openalex.org/W4233112278","https://openalex.org/W4239969464","https://openalex.org/W4245199738","https://openalex.org/W4247624284","https://openalex.org/W4249932213","https://openalex.org/W4250589301","https://openalex.org/W4251575795"],"related_works":["https://openalex.org/W2778498407","https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W1980160788","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W2148915962","https://openalex.org/W4313433561","https://openalex.org/W2283866686"],"abstract_inverted_index":{"The":[0,160],"growing":[1],"scale":[2],"and":[3,42,56,76,83,115,125,133,218,242,249,326],"complexity":[4],"of":[5,15,63,100,112,146,157,168,176,185,224,227,251,288,321],"Machine":[6],"Learning":[7],"(ML)":[8],"algorithms":[9,148,171,187],"has":[10],"resulted":[11],"in":[12],"prevalent":[13],"use":[14],"distributed":[16],"general-purpose":[17],"systems.":[18],"In":[19],"a":[20,45,81,119,126,143,213,231,264,274],"rather":[21],"disjoint":[22],"effort,":[23],"the":[24,97,131,169,173,177,183,186,201,247,282,296,318],"community":[25],"is":[26,162],"focusing":[27],"mostly":[28],"on":[29,208],"high":[30],"performance":[31],"single-node":[32],"accelerators":[33],"for":[34,253,333],"learning.":[35,335],"This":[36],"work":[37],"bridges":[38],"these":[39],"two":[40],"paradigms":[41],"offers":[43,270,291,312],"CoSMIC,":[44],"full":[46],"computing":[47],"stack":[48,128],"constituting":[49],"language,":[50],"compiler,":[51],"system":[52,101,233,277],"software,":[53],"template":[54,122],"architecture,":[55],"circuit":[57],"generators,":[58],"that":[59,129,149,204,235,317],"enable":[60],"programmable":[61],"acceleration":[62,73,191,332],"learning":[64,147,170,257],"at":[65],"scale.":[66],"CoSMIC":[67,89,107,140,181,197,221,252,266,290,306,322],"enables":[68],"programmers":[69,93],"to":[70,94,163,188,198,229,295,302],"exploit":[71,200],"scale-out":[72,178,331],"using":[74,154],"FPGAs":[75,269],"Programmable":[77],"ASICs":[78],"(P-ASICs)":[79],"from":[80,136,259,300],"high-level":[82,138],"mathematical":[84],"Domain-Specific":[85],"Language":[86],"(DSL).":[87],"Nonetheless,":[88],"does":[90],"not":[91],"require":[92],"delve":[95],"into":[96],"onerous":[98],"task":[99,237],"software":[102,134,234],"development":[103],"or":[104],"hardware":[105,132],"design.":[106],"achieves":[108],"three":[109],"conflicting":[110],"objectives":[111],"efficiency,":[113],"automation,":[114],"programmability,":[116],"by":[117,211],"integrating":[118],"novel":[120],"multi-threaded":[121,190,216],"accelerator":[123],"architecture":[124],"cohesive":[127],"generates":[130],"code":[135],"its":[137],"DSL.":[139],"can":[141],"accelerate":[142],"wide":[144],"range":[145],"are":[150,205],"most":[151],"commonly":[152],"trained":[153],"parallel":[155],"variants":[156],"gradient":[158,166],"descent.":[159],"key":[161],"distribute":[164],"partial":[165],"calculations":[167],"across":[172],"accelerator-augmented":[174],"nodes":[175,304],"system.":[179],"Additionally,":[180],"leverages":[182],"parallelizability":[184],"offer":[189,230],"within":[192],"each":[193],"node.":[194],"Multi-threading":[195],"allows":[196],"efficiently":[199],"numerous":[202],"resources":[203],"becoming":[206],"available":[207],"modern":[209],"FPGAs/P-ASICs":[210],"striking":[212],"balance":[214],"between":[215],"parallelism":[217],"single-threaded":[219],"performance.":[220],"takes":[222,323],"advantage":[223],"algorithmic":[225],"properties":[226],"ML":[228],"specialized":[232],"optimizes":[236],"allocation,":[238],"role-assignment,":[239],"thread":[240],"management,":[241],"internode":[243],"communication.":[244],"We":[245],"evaluate":[246],"versatility":[248],"efficiency":[250],"10":[254],"different":[255],"machine":[256,334],"applications":[258],"various":[260],"domains.":[261],"On":[262],"average,":[263],"16-node":[265,275],"with":[267,278,305],"UltraScale+":[268],"18.8\u00d7":[271],"speedup":[272],"over":[273],"Spark":[276,311],"Xeon":[279],"processors":[280],"while":[281],"programmer":[283],"only":[284],"writes":[285],"22--55":[286],"lines":[287],"code.":[289],"higher":[292],"scalability":[293],"compared":[294],"state-of-the-art":[297],"Spark;":[298],"scaling":[299],"4":[301],"16":[303],"yields":[307],"2.7\u00d7":[308],"improvements":[309],"whereas":[310],"1.8\u00d7.":[313],"These":[314],"results":[315],"confirm":[316],"full-stack":[319],"approach":[320],"an":[324],"effective":[325],"vital":[327],"step":[328],"towards":[329],"enabling":[330]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}