{"id":"https://openalex.org/W4290716987","doi":"https://doi.org/10.1109/lca.2022.3196932","title":"Overcoming Memory Capacity Wall of GPUs With Heterogeneous Memory Stack","display_name":"Overcoming Memory Capacity Wall of GPUs With Heterogeneous Memory Stack","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4290716987","doi":"https://doi.org/10.1109/lca.2022.3196932"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2022.3196932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3196932","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-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/A5062791122","display_name":"Jeongmin Hong","orcid":"https://orcid.org/0000-0002-5492-5346"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Hong","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-5492-5346","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102903741","display_name":"Sungjun Cho","orcid":"https://orcid.org/0000-0002-8609-6183"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjun Cho","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8609-6183","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334897","display_name":"Gwangsun Kim","orcid":"https://orcid.org/0000-0001-5749-5794"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gwangsun Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5749-5794","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.6377,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67814277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"21","issue":"2","first_page":"61","last_page":"64"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9977999925613403,"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":0.8528637886047363},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7844401597976685},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.7107257843017578},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6843730211257935},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.5760412812232971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5619762539863586},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5183371305465698},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5090703368186951},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.5059141516685486},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.4579651653766632},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.42344430088996887},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4030711352825165},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4006490707397461},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.385949045419693},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.3211197853088379},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24081802368164062},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.19076231122016907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528637886047363},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7844401597976685},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.7107257843017578},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6843730211257935},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.5760412812232971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5619762539863586},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5183371305465698},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5090703368186951},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.5059141516685486},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.4579651653766632},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.42344430088996887},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4030711352825165},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4006490707397461},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.385949045419693},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.3211197853088379},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24081802368164062},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.19076231122016907}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2022.3196932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3196932","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/116349","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/116349","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang 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/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1975274780","https://openalex.org/W1995287338","https://openalex.org/W2021211271","https://openalex.org/W2034861439","https://openalex.org/W2065653320","https://openalex.org/W2080592089","https://openalex.org/W2082982763","https://openalex.org/W2128120785","https://openalex.org/W2273440736","https://openalex.org/W2725159389","https://openalex.org/W2753463544","https://openalex.org/W2899741796","https://openalex.org/W2903659818","https://openalex.org/W2934021599","https://openalex.org/W3011293047","https://openalex.org/W3080191630","https://openalex.org/W3102510044","https://openalex.org/W3113606433","https://openalex.org/W3206857466","https://openalex.org/W4221032334","https://openalex.org/W4226045897","https://openalex.org/W6682110900","https://openalex.org/W6694513646","https://openalex.org/W6763585923","https://openalex.org/W6781887395","https://openalex.org/W6862640317"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2114386333","https://openalex.org/W2118932116","https://openalex.org/W2363769136","https://openalex.org/W2396934146","https://openalex.org/W2535115842","https://openalex.org/W2148571123","https://openalex.org/W2539712666","https://openalex.org/W2126408955","https://openalex.org/W2734782074"],"abstract_inverted_index":{"We":[0],"propose":[1,81,100],"to":[2,65,110,179],"overcome":[3],"the":[4,30,35,38,45,53,61,167,170],"memory":[5,25,51,62,175],"capacity":[6,128],"limitation":[7],"of":[8,44,60,95,107,113,125],"GPUs":[9],"with":[10,148],"aHeterogeneous":[11],"Memory":[12,18],"Stack":[13],"(HMS)that":[14],"integrates":[15],"Storage":[16],"Class":[17],"(SCM)":[19],"and":[20,41,116],"DRAM":[21,31,77,83,89,114,118,136,142,155],"in":[22,145],"a":[23,33,57,69,75,82,101,146,149],"3D":[24],"stack.":[26],"By":[27],"effectively":[28],"utilizing":[29],"as":[32],"cache,":[34],"HMS":[36,54,168],"addresses":[37],"latency,":[39],"bandwidth,":[40],"energy":[42],"challenges":[43],"SCM.":[46],"For":[47],"workloads":[48],"that":[49,87,166],"mandate":[50],"oversubscription,":[52],"can":[55],"capture":[56],"larger":[58],"fraction":[59],"footprint":[63],"compared":[64],"an":[66],"HBM,":[67],"providing":[68],"significant":[70],"performance":[71],"uplift.":[72],"To":[73],"enable":[74],"performant":[76],"cache":[78,84,90,109,119,127,137,156],"architecture,":[79],"we":[80,99],"bypass":[85],"mechanism":[86],"avoids":[88],"thrashing":[91],"by":[92,177],"100,000":[93],"s":[94],"GPU":[96],"threads.":[97],"Furthermore,":[98],"Tag":[102,131,160],"Cache":[103,161],"which":[104],"uses":[105],"part":[106],"L2":[108,126],"hold":[111],"tags":[112,144],"cachelines":[115],"reduce":[117],"probe":[120,157],"traffic,":[121],"while":[122],"enabling":[123],"adjustment":[124],"used":[129],"for":[130],"Cache.":[132],"In":[133],"addition,":[134],"our":[135],"organization":[138],"enables":[139],"fetching":[140],"all":[141],"cacheline":[143],"row":[147],"single":[150],"column":[151],"access,":[152],"avoiding":[153],"excessive":[154],"traffic":[158],"from":[159],"misses.":[162],"Our":[163],"results":[164],"show":[165],"outperforms":[169],"baseline":[171],"HBM":[172],"system":[173],"under":[174],"oversubscription":[176],"up":[178],"9.8\u00d7":[180],"(2.8\u00d7":[181],"on":[182],"average).":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}