{"id":"https://openalex.org/W7124191701","doi":"https://doi.org/10.1109/icpads67057.2025.11323104","title":"THDP: Temporal History Based Dynamic Prefetching for GPU Memory Oversubscription","display_name":"THDP: Temporal History Based Dynamic Prefetching for GPU Memory Oversubscription","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124191701","doi":"https://doi.org/10.1109/icpads67057.2025.11323104"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5122997774","display_name":"Minghui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minghui Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123015164","display_name":"Guangping Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangping Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730225","display_name":"Mingyuan Ding","orcid":"https://orcid.org/0009-0008-3400-505X"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyuan Ding","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123038529","display_name":"Zitong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Tianjin,China","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122997774"],"corresponding_institution_ids":["https://openalex.org/I136765683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70810085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.900600016117096,"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":0.900600016117096,"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":0.03229999914765358,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.014299999922513962,"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/speedup","display_name":"Speedup","score":0.640999972820282},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.5652999877929688},{"id":"https://openalex.org/keywords/page-fault","display_name":"Page fault","score":0.5293999910354614},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46380001306533813},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4291999936103821},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.3571999967098236},{"id":"https://openalex.org/keywords/storage-management","display_name":"Storage management","score":0.3562999963760376},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758000135421753},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.640999972820282},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6036999821662903},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.5652999877929688},{"id":"https://openalex.org/C193343404","wikidata":"https://www.wikidata.org/wiki/Q1928607","display_name":"Page fault","level":5,"score":0.5293999910354614},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4291999936103821},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C2984984529","wikidata":"https://www.wikidata.org/wiki/Q7619925","display_name":"Storage management","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.3547999858856201},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.32679998874664307},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.3138999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C197298091","wikidata":"https://www.wikidata.org/wiki/Q5318963","display_name":"Dynamic data","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.28209999203681946},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.2736000120639801},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6544744968414307,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3965892995","display_name":null,"funder_award_id":"61971309","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2489529491","https://openalex.org/W2549139847","https://openalex.org/W2752782242","https://openalex.org/W2901994046","https://openalex.org/W2913640523","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W4213060431","https://openalex.org/W4318541551","https://openalex.org/W4384656510","https://openalex.org/W4384705429","https://openalex.org/W4388671996"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"of":[3,100],"deep":[4,87],"learning":[5,88],"models":[6,25,89],"and":[7,41,74,105],"growing":[8],"GPU":[9],"memory":[10,13,29,66],"demands":[11],"exacerbate":[12],"management":[14],"challenges.":[15],"Unified":[16],"Memory":[17],"(UM)":[18],"offers":[19],"a":[20,52,76],"transparent":[21],"solution":[22],"by":[23,109],"enabling":[24],"to":[26,64,80],"exceed":[27],"hardware":[28],"limits,":[30],"yet":[31],"it":[32],"suffers":[33],"from":[34],"performance":[35],"bottlenecks":[36],"such":[37],"as":[38],"prefetching":[39,72],"delays":[40],"frequent":[42],"page":[43,107],"faults":[44,108],"during":[45],"training.":[46],"To":[47],"address":[48],"this,":[49],"we":[50],"propose":[51],"Temporal":[53],"History-based":[54],"Dynamic":[55],"Prefetching":[56],"(THDP)":[57],"approach,":[58],"which":[59],"leverages":[60],"kernel":[61],"execution":[62],"history":[63],"predict":[65],"access":[67],"patterns.":[68],"THDP":[69,92],"dynamically":[70],"adjusts":[71],"windows":[73],"employs":[75],"reference-countbased":[77],"eviction":[78],"strategy":[79],"optimize":[81],"data":[82],"migration.":[83],"Evaluations":[84],"across":[85],"diverse":[86],"demonstrate":[90],"that":[91],"significantly":[93],"outperforms":[94],"baselines,":[95],"achieving":[96],"an":[97],"average":[98],"speedup":[99],"<tex":[101],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.04":[103],"\\times$</tex>":[104],"reducing":[106],"over":[110],"90%.":[111]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-15T00:00:00"}