{"id":"https://openalex.org/W2141973190","doi":"https://doi.org/10.1109/iccd.2009.5413147","title":"3D GPU architecture using cache stacking: Performance, cost, power and thermal analysis","display_name":"3D GPU architecture using cache stacking: Performance, cost, power and thermal analysis","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2141973190","doi":"https://doi.org/10.1109/iccd.2009.5413147","mag":"2141973190"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2009.5413147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2009.5413147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Computer Design","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/A5000192652","display_name":"Ahmed Al Maashri","orcid":"https://orcid.org/0000-0002-7018-5026"},"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":"Ahmed Al Maashri","raw_affiliation_strings":["Department of Computer Science and Engineering, Penn State University, USA","Department of Computer Science and Engineering, Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University","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/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":"Guangyu Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, Penn State University, USA","Department of Computer Science and Engineering, Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083960440","display_name":"Xiangyu Dong","orcid":"https://orcid.org/0009-0003-5638-7558"},"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":"Xiangyu Dong","raw_affiliation_strings":["Department of Computer Science and Engineering, Penn State University, USA","Department of Computer Science and Engineering, Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051232628","display_name":"Vijay Narayanan","orcid":"https://orcid.org/0009-0008-8433-963X"},"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":"Vijay Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering, Penn State University, USA","Department of Computer Science and Engineering, Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"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":["Department of Computer Science and Engineering, Penn State University, USA","Department of Computer Science and Engineering, Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Penn State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.2803,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.80322074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"254","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.996999979019165,"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":0.8012994527816772},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.702907383441925},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6573436260223389},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5603383779525757},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5149927735328674},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5026342868804932},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5007476806640625},{"id":"https://openalex.org/keywords/three-dimensional-integrated-circuit","display_name":"Three-dimensional integrated circuit","score":0.48115479946136475},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46055853366851807},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4336233139038086},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4241178035736084},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4230364263057709},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3548412322998047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1653251349925995},{"id":"https://openalex.org/keywords/integrated-circuit","display_name":"Integrated circuit","score":0.10270452499389648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012994527816772},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.702907383441925},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6573436260223389},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5603383779525757},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5149927735328674},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5026342868804932},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5007476806640625},{"id":"https://openalex.org/C59088047","wikidata":"https://www.wikidata.org/wiki/Q229370","display_name":"Three-dimensional integrated circuit","level":3,"score":0.48115479946136475},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46055853366851807},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4336233139038086},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4241178035736084},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4230364263057709},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3548412322998047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1653251349925995},{"id":"https://openalex.org/C530198007","wikidata":"https://www.wikidata.org/wiki/Q80831","display_name":"Integrated circuit","level":2,"score":0.10270452499389648},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccd.2009.5413147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2009.5413147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Computer Design","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-155023","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-155023","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":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W40887843","https://openalex.org/W1982132112","https://openalex.org/W2105331022","https://openalex.org/W2108792719","https://openalex.org/W2117228145","https://openalex.org/W2119428232","https://openalex.org/W2133044942","https://openalex.org/W2134860672","https://openalex.org/W2139340565","https://openalex.org/W2139730616","https://openalex.org/W2139774022","https://openalex.org/W2141736089","https://openalex.org/W2146048051","https://openalex.org/W2154857344","https://openalex.org/W2543205889","https://openalex.org/W2763753778","https://openalex.org/W3136310872","https://openalex.org/W6601653709","https://openalex.org/W6680835552","https://openalex.org/W6681627329"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W1989916619"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"offer":[4],"tremendous":[5],"computational":[6],"and":[7,16,22,87,108],"processing":[8],"power.":[9],"The":[10],"architecture":[11],"requires":[12],"high":[13],"communication":[14],"bandwidth":[15],"lower":[17],"latency":[18],"between":[19],"computation":[20],"units":[21],"caches.":[23],"3D":[24,49,65,77],"die-stacking":[25],"technology":[26,50,66],"is":[27],"a":[28,98],"promising":[29],"approach":[30],"to":[31],"meet":[32],"such":[33],"requirements.":[34],"To":[35],"the":[36,46,58,64,73,91],"best":[37],"of":[38,48,60,75,90],"our":[39],"knowledge":[40],"no":[41],"other":[42],"study":[43,57],"has":[44],"investigated":[45],"implementation":[47],"in":[51],"GPUs.":[52,81],"In":[53],"this":[54],"paper,":[55],"we":[56],"impact":[59],"stacking":[61],"caches":[62],"using":[63,76],"on":[67,80],"GPU":[68],"performance.":[69],"We":[70],"also":[71],"investigate":[72],"benefits":[74],"stacked":[78],"MRAM":[79],"Our":[82,95],"work":[83],"includes":[84],"cost,":[85],"power,":[86],"thermal":[88],"analysis":[89],"proposed":[92],"architectural":[93],"designs.":[94],"results":[96],"show":[97],"53%":[99],"geometric":[100],"mean":[101],"performance":[102],"speedup":[103],"for":[104,111],"iso-cycle":[105],"time":[106],"architectures":[107],"about":[109],"19%":[110],"iso-cost":[112],"architectures.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
