{"id":"https://openalex.org/W1990962327","doi":"https://doi.org/10.1145/2541228.2541231","title":"Optimizing GPU energy efficiency with 3D die-stacking graphics memory and reconfigurable memory interface","display_name":"Optimizing GPU energy efficiency with 3D die-stacking graphics memory and reconfigurable memory interface","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1990962327","doi":"https://doi.org/10.1145/2541228.2541231","mag":"1990962327"},"language":"en","primary_location":{"id":"doi:10.1145/2541228.2541231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2541228.2541231","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2541228.2541231","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2541228.2541231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077387335","display_name":"Jishen Zhao","orcid":"https://orcid.org/0000-0002-1969-743X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jishen Zhao","raw_affiliation_strings":["Pennsylvania State University CSE Department","Pennsylvania State University CSE Department#TAB#"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University CSE Department","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University CSE Department#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850376","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0001-6436-0820"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102835155","display_name":"Gabriel H. Loh","orcid":"https://orcid.org/0000-0002-4616-0144"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gabriel H. Loh","raw_affiliation_strings":["Advanced Micro Devices, Inc. AMD Research","Advanced Micro Devices, Inc. AMD Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc. AMD Research","institution_ids":["https://openalex.org/I1311921367"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc. AMD Research#TAB#","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Pennsylvania State University CSE Department","Pennsylvania State University CSE Department#TAB#"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University CSE Department","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University CSE Department#TAB#","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077387335"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":4.7572,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94781261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8441609144210815},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6064800024032593},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5138869285583496},{"id":"https://openalex.org/keywords/registered-memory","display_name":"Registered memory","score":0.4577637314796448},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43857502937316895},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4358081817626953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4310765862464905},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4304419159889221},{"id":"https://openalex.org/keywords/non-volatile-random-access-memory","display_name":"Non-volatile random-access memory","score":0.4288161098957062},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.419036328792572},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4181376099586487},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.38326209783554077},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3530861437320709},{"id":"https://openalex.org/keywords/computer-memory","display_name":"Computer memory","score":0.3403811454772949},{"id":"https://openalex.org/keywords/memory-refresh","display_name":"Memory refresh","score":0.22268131375312805},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15771251916885376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441609144210815},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6064800024032593},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5138869285583496},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.4577637314796448},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43857502937316895},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4358081817626953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4310765862464905},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4304419159889221},{"id":"https://openalex.org/C34172316","wikidata":"https://www.wikidata.org/wiki/Q499024","display_name":"Non-volatile random-access memory","level":5,"score":0.4288161098957062},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.419036328792572},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4181376099586487},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.38326209783554077},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3530861437320709},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.3403811454772949},{"id":"https://openalex.org/C87907426","wikidata":"https://www.wikidata.org/wiki/Q6815755","display_name":"Memory refresh","level":4,"score":0.22268131375312805},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15771251916885376},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2541228.2541231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2541228.2541231","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2541228.2541231","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133641","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-133641","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/2541228.2541231","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2541228.2541231","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2541228.2541231","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5301363178","display_name":null,"funder_award_id":"1017277","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6901979050","display_name":null,"funder_award_id":"0903432","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8137092113","display_name":null,"funder_award_id":"1213052","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8556691660","display_name":null,"funder_award_id":"0903432, 1017277","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1990962327.pdf","grobid_xml":"https://content.openalex.org/works/W1990962327.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1598520402","https://openalex.org/W1778630082","https://openalex.org/W1970419561","https://openalex.org/W1974624971","https://openalex.org/W1979527452","https://openalex.org/W1979979548","https://openalex.org/W1980364632","https://openalex.org/W1993089791","https://openalex.org/W2032512814","https://openalex.org/W2071208935","https://openalex.org/W2080592089","https://openalex.org/W2081379617","https://openalex.org/W2082499523","https://openalex.org/W2096370786","https://openalex.org/W2096661534","https://openalex.org/W2100516830","https://openalex.org/W2101166204","https://openalex.org/W2101903894","https://openalex.org/W2102032581","https://openalex.org/W2110999878","https://openalex.org/W2115412309","https://openalex.org/W2117816012","https://openalex.org/W2122636510","https://openalex.org/W2125356053","https://openalex.org/W2131413854","https://openalex.org/W2139730616","https://openalex.org/W2140440478","https://openalex.org/W2141973190","https://openalex.org/W2152165066","https://openalex.org/W2153039279","https://openalex.org/W2155702343","https://openalex.org/W2164516366","https://openalex.org/W2167357818","https://openalex.org/W2170382128","https://openalex.org/W2185926888","https://openalex.org/W2994143592","https://openalex.org/W3139689176","https://openalex.org/W4247470388","https://openalex.org/W4285719527","https://openalex.org/W6600020421"],"related_works":["https://openalex.org/W2898989424","https://openalex.org/W4285257158","https://openalex.org/W4293159259","https://openalex.org/W4238754064","https://openalex.org/W2087924605","https://openalex.org/W2742331047","https://openalex.org/W1971689948","https://openalex.org/W2561005478","https://openalex.org/W2188534734","https://openalex.org/W2615320339"],"abstract_inverted_index":{"The":[0,94,227,248],"performance":[1,25],"of":[2,16,30,39,43,117,146,173,201,272],"graphics":[3,17,56,77,83],"processing":[4],"unit":[5],"(GPU)":[6],"systems":[7,32],"is":[8,33,47,60,97,106,123,149],"improving":[9],"rapidly":[10],"to":[11,37,62,198,209],"accommodate":[12],"the":[13,40,50,64,102,115,120,125,141,144,154,161,168,178,199,211,232,255],"increasing":[14],"demands":[15],"and":[18,119,135,171,216,219,224,261],"high-performance":[19],"computing":[20,131],"applications.":[21,203,226],"With":[22],"such":[23],"a":[24,44,87,91,98,190,267],"improvement,":[26],"however,":[27],"power":[28,42,58,65,163,270],"consumption":[29,59,164],"GPU":[31,45,88,121,130,212,234,240],"dramatically":[34],"increased.":[35],"Up":[36],"30%":[38],"total":[41],"system":[46,213,241,256,262,269],"consumed":[48],"by":[49,153,165,244,259,264],"graphic":[51],"memory":[52,57,78,104,109,133,136,147,162,174,184,192,235,250],"itself.":[53],"Therefore,":[54],"reducing":[55],"critical":[61],"mitigate":[63],"challenge.":[66],"In":[67,186],"this":[68],"article,":[69],"we":[70,188],"propose":[71,205],"an":[72],"energy-efficient":[73],"reconfigurable":[74,191,249],"3D":[75,107],"die-stacking":[76],"design":[79,189],"that":[80,194,231],"integrates":[81],"wide-interface":[82],"DRAMs":[84],"side-by-side":[85],"with":[86,110],"processor":[89,122],"on":[90],"silicon":[92],"interposer.":[93],"proposed":[95,233],"architecture":[96,236],"\u201c3D+2.5D\u201d":[99],"system,":[100],"where":[101],"DRAM":[103,118],"itself":[105],"stacked":[108],"through-silicon":[111],"via":[112],"(TSV),":[113],"whereas":[114],"integration":[116],"through":[124],"interposer":[126],"solution":[127],"(2.5D).":[128],"Since":[129],"units,":[132],"controllers,":[134],"are":[137],"all":[138],"integrated":[139],"in":[140],"same":[142,179],"package,":[143],"number":[145],"I/Os":[148],"no":[150],"longer":[151],"constrained":[152],"package\u2019s":[155],"pin":[156],"count.":[157],"We":[158,204],"can":[159,195,237,252],"reduce":[160],"scaling":[166],"down":[167],"supply":[169],"voltage":[170],"frequency":[172],"interface":[175,193,251],"while":[176],"maintaining":[177],"or":[180],"even":[181],"higher":[182],"peak":[183],"bandwidth.":[185],"addition,":[187],"dynamically":[196],"adapt":[197],"requirements":[200],"various":[202],"two":[206],"reconfiguration":[207],"mechanisms":[208],"optimize":[210],"energy":[214,242,257],"efficiency":[215,243,258],"throughput,":[217],"respectively,":[218],"thus":[220],"benefit":[221],"both":[222],"memory-intensive":[223],"compute-intensive":[225],"experimental":[228],"results":[229],"show":[230],"effectively":[238],"improve":[239,254],"21%,":[245],"without":[246],"reconfiguration.":[247],"further":[253],"26%,":[260],"throughput":[263],"31%":[265],"under":[266],"capped":[268],"budget":[271],"240W.":[273]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}