{"id":"https://openalex.org/W2897709121","doi":"https://doi.org/10.1145/3243176.3243188","title":"In-DRAM near-data approximate acceleration for GPUs","display_name":"In-DRAM near-data approximate acceleration for GPUs","publication_year":2018,"publication_date":"2018-10-10","ids":{"openalex":"https://openalex.org/W2897709121","doi":"https://doi.org/10.1145/3243176.3243188","mag":"2897709121"},"language":"en","primary_location":{"id":"doi:10.1145/3243176.3243188","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243176.3243188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","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/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":true,"raw_author_name":"Amir Yazdanbakhsh","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076082641","display_name":"Choungki Song","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choungki Song","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005767422","display_name":"Jacob Sacks","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":"Jacob Sacks","raw_affiliation_strings":["Georgia Institute of Technology"],"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)"],"affiliations":[{"raw_affiliation_string":"Institute for Research in Fundamental Sciences (IPM)","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084514143","display_name":"Hadi Esmaeilzadeh","orcid":"https://orcid.org/0000-0002-8548-1039"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Esmaeilzadeh","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070172290"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.5247,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89868003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"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":0.9991000294685364,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.9580361843109131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811165452003479},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7256903648376465},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5795791149139404},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5284250378608704},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5065480470657349},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5049248337745667},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4956580400466919},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.48512396216392517},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4733158349990845},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.45310965180397034},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.4396679401397705},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.43697303533554077},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.26952481269836426},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10416632890701294},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09832599759101868},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0790601372718811},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.07709139585494995},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.07565784454345703},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07209524512290955}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.9580361843109131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811165452003479},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7256903648376465},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5795791149139404},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5284250378608704},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5065480470657349},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5049248337745667},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4956580400466919},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.48512396216392517},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4733158349990845},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.45310965180397034},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.4396679401397705},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.43697303533554077},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26952481269836426},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10416632890701294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09832599759101868},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0790601372718811},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.07709139585494995},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.07565784454345703},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07209524512290955},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3243176.3243188","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243176.3243188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W579519726","https://openalex.org/W622311454","https://openalex.org/W1510369796","https://openalex.org/W1651324627","https://openalex.org/W1749461670","https://openalex.org/W1963998358","https://openalex.org/W1964108470","https://openalex.org/W1969349120","https://openalex.org/W1969529818","https://openalex.org/W1974307224","https://openalex.org/W1975237352","https://openalex.org/W1976186353","https://openalex.org/W1979527452","https://openalex.org/W1980136882","https://openalex.org/W1981943579","https://openalex.org/W1996231863","https://openalex.org/W1997352364","https://openalex.org/W1998259214","https://openalex.org/W2005487033","https://openalex.org/W2010069327","https://openalex.org/W2013959289","https://openalex.org/W2014423307","https://openalex.org/W2014641514","https://openalex.org/W2015184411","https://openalex.org/W2023999916","https://openalex.org/W2024122052","https://openalex.org/W2024818089","https://openalex.org/W2027806965","https://openalex.org/W2042404124","https://openalex.org/W2045431893","https://openalex.org/W2045525968","https://openalex.org/W2047001217","https://openalex.org/W2047060659","https://openalex.org/W2052872270","https://openalex.org/W2056137328","https://openalex.org/W2057096112","https://openalex.org/W2062430565","https://openalex.org/W2065562952","https://openalex.org/W2078141470","https://openalex.org/W2082375193","https://openalex.org/W2084732345","https://openalex.org/W2093043622","https://openalex.org/W2093524602","https://openalex.org/W2094332102","https://openalex.org/W2100799353","https://openalex.org/W2100926301","https://openalex.org/W2105102111","https://openalex.org/W2105544671","https://openalex.org/W2110195531","https://openalex.org/W2110432093","https://openalex.org/W2112980698","https://openalex.org/W2114440330","https://openalex.org/W2118703320","https://openalex.org/W2124969960","https://openalex.org/W2133721425","https://openalex.org/W2141443190","https://openalex.org/W2142119745","https://openalex.org/W2143283746","https://openalex.org/W2152484003","https://openalex.org/W2160428323","https://openalex.org/W2161679325","https://openalex.org/W2163687928","https://openalex.org/W2164886383","https://openalex.org/W2166250385","https://openalex.org/W2170382128","https://openalex.org/W2187230075","https://openalex.org/W2233797083","https://openalex.org/W2263306508","https://openalex.org/W2293746900","https://openalex.org/W2332254524","https://openalex.org/W2335240678","https://openalex.org/W2442974303","https://openalex.org/W2513721464","https://openalex.org/W2518511512","https://openalex.org/W2554131156","https://openalex.org/W2562213348","https://openalex.org/W2605347906","https://openalex.org/W2612654866","https://openalex.org/W2906043559","https://openalex.org/W2964299589","https://openalex.org/W2998897738","https://openalex.org/W3005426916","https://openalex.org/W3022971582","https://openalex.org/W4233147525","https://openalex.org/W4239722617","https://openalex.org/W4240237526","https://openalex.org/W4251054771","https://openalex.org/W4251362763","https://openalex.org/W4254648244"],"related_works":["https://openalex.org/W4293430534","https://openalex.org/W2342813629","https://openalex.org/W3150934690","https://openalex.org/W2335743642","https://openalex.org/W4297812927","https://openalex.org/W2800412005","https://openalex.org/W1976244802","https://openalex.org/W2083934844","https://openalex.org/W1992487929","https://openalex.org/W4386903460"],"abstract_inverted_index":{"GPUs":[0],"are":[1,168],"bottlenecked":[2],"by":[3,177],"the":[4,21,34,60,65,72,88,128,134,138,172],"off-chip":[5],"communication":[6],"bandwidth":[7,37],"and":[8,29,70,155],"its":[9],"energy":[10,157],"cost;":[11],"hence":[12],"near-data":[13],"acceleration":[14],"is":[15,44],"particularly":[16],"attractive":[17],"for":[18],"GPUs.":[19],"Integrating":[20],"accelerators":[22,50],"within":[23],"DRAM":[24,115,139,174],"can":[25],"mitigate":[26],"these":[27],"bottlenecks":[28],"additionally":[30],"expose":[31],"them":[32],"to":[33,82,86],"higher":[35],"internal":[36,135],"of":[38,56,67,79,92,137,183],"DRAM.":[39],"However,":[40],"such":[41],"an":[42,180],"integration":[43,125],"challenging,":[45],"as":[46],"it":[47],"requires":[48],"low-overhead":[49],"while":[51,170],"supporting":[52],"a":[53,97,103,160],"diverse":[54,77],"set":[55],"applications.":[57],"To":[58],"enable":[59],"integration,":[61],"this":[62,110,124],"work":[63,111],"leverages":[64],"approximability":[66],"GPU":[68,162],"applications":[69],"utilizes":[71],"neural":[73],"transformation,":[74],"which":[75],"converts":[76],"regions":[78],"code":[80],"mainly":[81],"Multiply-Accumulate":[83],"(MAC).":[84],"Furthermore,":[85],"preserve":[87],"SIMT":[89],"execution":[90],"model":[91],"GPUs,":[93],"we":[94],"also":[95],"propose":[96],"novel":[98,114],"approximate":[99,119],"MAC":[100,120],"unit":[101],"with":[102,143,163,179],"significantly":[104],"smaller":[105],"area":[106,181],"overhead.":[107],"As":[108],"such,":[109],"introduces":[112],"AxRam---a":[113],"architecture---that":[116],"integrates":[117],"several":[118],"units.":[121],"AxRam":[122,151],"offers":[123],"without":[126],"increasing":[127],"memory":[129],"column":[130],"pitch":[131],"or":[132],"modifying":[133],"architecture":[136],"banks.":[140],"Our":[141],"results":[142],"10":[144],"GPGPU":[145],"benchmarks":[146],"show":[147],"that,":[148],"on":[149],"average,":[150],"provides":[152],"2.6\u00d7":[153],"speedup":[154],"13.3\u00d7":[156],"reduction":[158],"over":[159],"baseline":[161],"no":[164],"acceleration.":[165],"These":[166],"benefits":[167],"achieved":[169],"reducing":[171],"overall":[173],"system":[175],"power":[176],"26%":[178],"cost":[182],"merely":[184],"2.1%.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}