{"id":"https://openalex.org/W4395106434","doi":"https://doi.org/10.1145/3620666.3651353","title":"GMT: GPU Orchestrated Memory Tiering for the Big Data Era","display_name":"GMT: GPU Orchestrated Memory Tiering for the Big Data Era","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106434","doi":"https://doi.org/10.1145/3620666.3651353"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","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/A5101893835","display_name":"Chia-Hao Chang","orcid":"https://orcid.org/0009-0002-6711-0071"},"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":"Chia-Hao Chang","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-6711-0071","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942968","display_name":"Jihoon Han","orcid":"https://orcid.org/0009-0008-0496-1462"},"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":"Jihoon Han","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0009-0008-0496-1462","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"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":"Anand Sivasubramaniam","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6173-687X","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041724753","display_name":"Vikram Sharma Mailthody","orcid":"https://orcid.org/0000-0002-9611-8075"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram Sharma Mailthody","raw_affiliation_strings":["NVIDIA Research, Santa Clara, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9611-8075","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046830079","display_name":"Zaid Qureshi","orcid":"https://orcid.org/0000-0003-1766-1289"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Qureshi","raw_affiliation_strings":["NVIDIA Research, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-1766-1289","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei Hwu","raw_affiliation_strings":["NVIDIA Research, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-2532-5349","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"464","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8419753313064575},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5936897993087769},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5070650577545166},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46133553981781006},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.45622095465660095},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.45523715019226074},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4483892321586609},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4259053170681},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35044747591018677},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34938597679138184},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.21724912524223328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419753313064575},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5936897993087769},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5070650577545166},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46133553981781006},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.45622095465660095},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.45523715019226074},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4483892321586609},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4259053170681},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35044747591018677},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34938597679138184},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.21724912524223328},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3651353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1483258120","https://openalex.org/W1987225815","https://openalex.org/W2009387496","https://openalex.org/W2010133494","https://openalex.org/W2024717934","https://openalex.org/W2035080386","https://openalex.org/W2047447065","https://openalex.org/W2072873664","https://openalex.org/W2080592089","https://openalex.org/W2097336080","https://openalex.org/W2109432325","https://openalex.org/W2139357537","https://openalex.org/W2147122795","https://openalex.org/W2156064678","https://openalex.org/W2164705472","https://openalex.org/W2604595776","https://openalex.org/W2765292551","https://openalex.org/W2766191055","https://openalex.org/W2803723124","https://openalex.org/W2901994046","https://openalex.org/W2928156253","https://openalex.org/W2934584470","https://openalex.org/W3106620263","https://openalex.org/W3158149042","https://openalex.org/W3167720200","https://openalex.org/W3206341493","https://openalex.org/W4230315356","https://openalex.org/W4244144927","https://openalex.org/W4245074222","https://openalex.org/W4245987560","https://openalex.org/W4253114834","https://openalex.org/W4253438286","https://openalex.org/W4280630845","https://openalex.org/W4318541614","https://openalex.org/W4327930439","https://openalex.org/W4360832442","https://openalex.org/W4387723591","https://openalex.org/W6638337918","https://openalex.org/W7047442821","https://openalex.org/W7074642923"],"related_works":["https://openalex.org/W1975522091","https://openalex.org/W4389476357","https://openalex.org/W2606565524","https://openalex.org/W2140286994","https://openalex.org/W2811273125","https://openalex.org/W575672070","https://openalex.org/W3108003711","https://openalex.org/W254684032","https://openalex.org/W4352974250","https://openalex.org/W2115061140"],"abstract_inverted_index":{"As":[0],"the":[1,29,41,61,88,98,121,126,142,180,190],"demand":[2],"for":[3],"processing":[4],"larger":[5],"datasets":[6],"increases,":[7],"GPUs":[8],"need":[9],"to":[10,17,32,53,59,136,145,160],"reach":[11,33],"deeper":[12],"into":[13],"their":[14],"(memory)":[15],"hierarchy":[16,112],"directly":[18,68],"access":[19,69,210],"capacities":[20],"that":[21,82,128,174,194],"only":[22],"storage":[23,34],"systems":[24],"(SSDs)":[25],"can":[26],"hold.":[27],"However,":[28],"state-of-the-art":[30,181,191],"mechanisms":[31],"either":[35],"employ":[36],"software":[37],"stacks":[38],"running":[39],"on":[40,169],"host":[42,89,116,146,198],"CPUs":[43,199],"as":[44,91],"intermediaries":[45],"(e.g.":[46],"Dragon,":[47],"HMM),":[48],"which":[49,75],"has":[50],"been":[51],"noted":[52],"perform":[54,161],"poorly":[55],"and":[56,100,118,151,167,185],"not":[57,77,137],"able":[58],"meet":[60],"throughput":[62],"needs":[63],"of":[64,102,125,204],"GPU":[65,103,114,122,143,205],"cores,":[66],"or":[67],"SSDs":[70],"through":[71],"NVMe":[72],"queues":[73],"(BaM)":[74,184],"does":[76],"benefit":[78],"from":[79,141],"lower":[80],"latencies":[81],"may":[83],"be":[84],"possible":[85],"by":[86,107,197],"having":[87],"memory":[90,117,144,147,209],"an":[92,149,170],"intermediate":[93],"tier.":[94],"This":[95],"paper":[96],"presents":[97],"design":[99],"implementation":[101,166],"Memory":[104],"Tiering":[105],"(GMT)":[106],"implementing":[108],"a":[109,154,202],"GPU-orchestrated":[110],"3-tier":[111,192],"comprising":[113],"memory,":[115],"SSDs,":[119],"where":[120],"orchestrates":[123],"most":[124],"transfers":[127],"are":[129],"bandwidth/latency":[130],"sensitive.":[131],"Additionally,":[132],"it":[133],"is":[134,195],"important":[135],"blindly":[138],"transfer":[139],"pages":[140],"upon":[148],"eviction,":[150],"GMT":[152,175],"employs":[153],"reuse-prediction":[155],"based":[156],"practical":[157],"insertion":[158],"policy":[159],"discretionary":[162],"page":[163],"placement/bypass.":[164],"An":[165],"evaluation":[168],"actual":[171],"platform":[172],"demonstrates":[173],"performs":[176],"50%":[177],"better":[178,188],"than":[179,189],"2-tier":[182],"strategy":[183,193],"over":[186,201],"350%":[187],"orchestrated":[196],"(HMM),":[200],"number":[203],"applications":[206],"with":[207],"diverse":[208],"characteristics.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}