{"id":"https://openalex.org/W4401408774","doi":"https://doi.org/10.1145/3673038.3673069","title":"SyncMalloc: A Synchronized Host-Device Co-Management System for GPU Dynamic Memory Allocation across All Scales","display_name":"SyncMalloc: A Synchronized Host-Device Co-Management System for GPU Dynamic Memory Allocation across All Scales","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408774","doi":"https://doi.org/10.1145/3673038.3673069"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673069","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089401815","display_name":"Jiajian Zhang","orcid":"https://orcid.org/0000-0003-2903-9411"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]},{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Jiajian Zhang","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China and The University of Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China and The University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397","https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Wu","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111910380","display_name":"Hai Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jiang","raw_affiliation_strings":["Bejing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Bejing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115599767","display_name":"Guangliang Cheng","orcid":"https://orcid.org/0000-0001-8686-9513"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["Department of Computer Science, The University of Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086905984","display_name":"Genlang Chen","orcid":"https://orcid.org/0009-0008-6964-8143"},"institutions":[{"id":"https://openalex.org/I159389169","display_name":"Ningbo University of Technology","ror":"https://ror.org/037dym702","country_code":"CN","type":"education","lineage":["https://openalex.org/I159389169"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genlang Chen","raw_affiliation_strings":["School of Computer and Data Engineering, NingboTech University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Data Engineering, NingboTech University, China","institution_ids":["https://openalex.org/I159389169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053452551","display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-0918-4606"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiufeng Wang","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089401815"],"corresponding_institution_ids":["https://openalex.org/I146655781","https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.5198,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9973999857902527,"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":0.9952999949455261,"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":0.7681443095207214},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.7367384433746338},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.5829311609268188},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43243855237960815},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.4145898222923279},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36595332622528076},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.12375888228416443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681443095207214},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.7367384433746338},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.5829311609268188},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43243855237960815},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.4145898222923279},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36595332622528076},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.12375888228416443},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6200000047683716,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408774.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1842317227","https://openalex.org/W2016931788","https://openalex.org/W2039820867","https://openalex.org/W2128274900","https://openalex.org/W2902924632","https://openalex.org/W2911544077","https://openalex.org/W2947508157","https://openalex.org/W3038173700","https://openalex.org/W3096257365","https://openalex.org/W3129251009","https://openalex.org/W4200262957","https://openalex.org/W4243654888","https://openalex.org/W4282963247","https://openalex.org/W4293093511","https://openalex.org/W4310054974","https://openalex.org/W4312191310","https://openalex.org/W4381327218","https://openalex.org/W4386709686","https://openalex.org/W4386709703","https://openalex.org/W4388544075","https://openalex.org/W4388661952"],"related_works":["https://openalex.org/W2117112636","https://openalex.org/W2001981265","https://openalex.org/W1964027849","https://openalex.org/W2001367608","https://openalex.org/W3148512624","https://openalex.org/W2244179743","https://openalex.org/W1797879553","https://openalex.org/W2188391409","https://openalex.org/W2146707680","https://openalex.org/W3022541129"],"abstract_inverted_index":{"Dynamic":[0],"memory":[1,26,53,57,78,110,118],"allocation":[2,54],"on":[3,59],"GPUs,":[4],"increasingly":[5],"crucial":[6],"for":[7],"applications":[8,153],"with":[9,21,107],"dynamic":[10,52,77,166],"computational":[11],"patterns,":[12],"encounters":[13],"significant":[14],"challenges":[15],"due":[16],"to":[17,74,111,120,147,172],"the":[18,36,84,122,149,160],"complex":[19],"calculations":[20],"intricate":[22],"branches":[23],"and":[24,46,88,96,130,144],"substantial":[25],"resources":[27],"consumed":[28],"by":[29],"metadata":[30],"from":[31,170,174],"massive":[32],"thread":[33],"allocations.":[34],"Despite":[35],"current":[37],"research,":[38],"there":[39],"is":[40,71,180],"a":[41,44,65,138],"lack":[42],"of":[43,80,86,124,151,162],"scalable":[45],"flexible":[47],"solution":[48],"that":[49,70],"effectively":[50,92],"manages":[51],"while":[55],"minimizing":[56],"usage":[58],"GPUs.":[60],"This":[61],"paper":[62],"introduces":[63],"SyncMalloc,":[64],"synchronized":[66],"Host-Device":[67],"Co-Management":[68],"system":[69],"specifically":[72],"designed":[73],"adeptly":[75],"handle":[76],"allocations":[79,168],"diverse":[81],"magnitudes.":[82],"Through":[83],"integration":[85,106],"pipelining":[87],"producer-consumer":[89],"mechanisms,":[90],"SyncMalloc":[91,115,163],"reduces":[93],"communication":[94],"overhead":[95,131],"resolves":[97],"architectural":[98],"mismatches,":[99],"further":[100],"enhancing":[101],"its":[102],"capability":[103],"through":[104],"synergistic":[105],"CUDA\u2019s":[108],"unified":[109],"facilitate":[112],"oversubscription.":[113],"Moreover,":[114],"advances":[116],"slab-based":[117],"management":[119],"enhance":[121],"efficiency":[123],"small":[125],"allocations,":[126],"reducing":[127],"conflict":[128],"probabilities":[129],"in":[132,164],"high-activity":[133],"scenarios.":[134],"Finally,":[135],"we":[136],"present":[137],"comprehensive":[139],"performance":[140,150],"evaluation,":[141],"expanding":[142],"benchmarks":[143],"measurement":[145],"dimensions":[146],"reflect":[148],"real-world":[152],"more":[154],"accurately.":[155],"The":[156],"experimental":[157],"results":[158],"demonstrate":[159],"effectiveness":[161],"supporting":[165],"GPU":[167],"scaled":[169],"4B":[171],"200GB":[173],"multiple":[175],"perspectives.":[176],"Our":[177],"source":[178],"code":[179],"available":[181],"at":[182],"https://github.com/jjZhang94/SyncMalloc.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}