{"id":"https://openalex.org/W3131109761","doi":"https://doi.org/10.1145/3437801.3441612","title":"Are dynamic memory managers on GPUs slow?","display_name":"Are dynamic memory managers on GPUs slow?","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3131109761","doi":"https://doi.org/10.1145/3437801.3441612","mag":"3131109761"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5044793967","display_name":"Martin Winter","orcid":"https://orcid.org/0000-0002-7778-9770"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Martin Winter","raw_affiliation_strings":["University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073507738","display_name":"Mathias Parger","orcid":"https://orcid.org/0000-0002-9074-4374"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mathias Parger","raw_affiliation_strings":["University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089625200","display_name":"Daniel Mlakar","orcid":"https://orcid.org/0000-0002-4500-0325"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Daniel Mlakar","raw_affiliation_strings":["University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014594342","display_name":"Markus Steinberger","orcid":"https://orcid.org/0000-0001-5977-8536"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Steinberger","raw_affiliation_strings":["University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044793967"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":3.5145,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92617761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"233"},"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":0.9991999864578247,"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/T10772","display_name":"Distributed systems and fault tolerance","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8721279501914978},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6365538835525513},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6092333793640137},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5863375663757324},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.515468180179596},{"id":"https://openalex.org/keywords/c-dynamic-memory-allocation","display_name":"C dynamic memory allocation","score":0.5020091533660889},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.499971866607666},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4786580801010132},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.46763208508491516},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4562245011329651},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4276973605155945},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.42205560207366943},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.42122071981430054},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2601836323738098},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25456327199935913},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.1052660346031189}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721279501914978},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6365538835525513},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6092333793640137},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5863375663757324},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.515468180179596},{"id":"https://openalex.org/C34339311","wikidata":"https://www.wikidata.org/wiki/Q1050390","display_name":"C dynamic memory allocation","level":4,"score":0.5020091533660889},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.499971866607666},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4786580801010132},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.46763208508491516},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4562245011329651},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4276973605155945},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.42205560207366943},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.42122071981430054},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2601836323738098},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25456327199935913},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.1052660346031189},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437801.3441612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4683568552","display_name":null,"funder_award_id":"I 3007","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W324754135","https://openalex.org/W1214620947","https://openalex.org/W1842317227","https://openalex.org/W1981393723","https://openalex.org/W1983540755","https://openalex.org/W2016931788","https://openalex.org/W2036177174","https://openalex.org/W2039820867","https://openalex.org/W2128274900","https://openalex.org/W2902093742","https://openalex.org/W2902924632","https://openalex.org/W2911544077","https://openalex.org/W2914086833","https://openalex.org/W2965005859","https://openalex.org/W3038173700","https://openalex.org/W4206486352","https://openalex.org/W4243654888","https://openalex.org/W4249713879"],"related_works":["https://openalex.org/W2167102554","https://openalex.org/W2349791858","https://openalex.org/W45732507","https://openalex.org/W2584932762","https://openalex.org/W3022541129","https://openalex.org/W1964027849","https://openalex.org/W3148512624","https://openalex.org/W116159913","https://openalex.org/W3213866906","https://openalex.org/W2939884503"],"abstract_inverted_index":{"Dynamic":[0],"memory":[1,25,73,96,166,191],"management":[2],"on":[3,59,64,193],"GPUs":[4],"is":[5],"generally":[6],"understood":[7],"to":[8,33,56,67,91,160],"be":[9],"a":[10,60,88,99,128,157],"challenging":[11],"topic.":[12],"On":[13],"current":[14],"GPUs,":[15],"hundreds":[16],"of":[17,19,102,143,163,185],"thousands":[18],"threads":[20],"might":[21],"concurrently":[22],"allocate":[23],"new":[24],"or":[26],"free":[27],"previously":[28],"allocated":[29],"memory.":[30],"This":[31],"leads":[32],"problems":[34],"with":[35,189],"thread":[36],"contention,":[37],"synchronization":[38],"overhead":[39],"and":[40,52,108,118,124,141,146,171],"fragmentation.":[41],"Various":[42],"approaches":[43],"have":[44],"been":[45],"proposed":[46],"in":[47,98],"the":[48,69,139,150,164,186,194],"last":[49],"ten":[50],"years":[51],"we":[53,86,181],"set":[54,101],"out":[55],"evaluate":[57,92,110],"them":[58,174],"level":[61],"playing":[62],"field":[63],"modern":[65],"hardware":[66],"answer":[68],"question,":[70],"if":[71],"dynamic":[72,135,190],"managers":[74,97,167,192],"are":[75],"as":[76,78,114,116,131,133],"slow":[77],"commonly":[79],"thought":[80],"of.":[81],"In":[82],"this":[83],"survey":[84],"paper,":[85],"provide":[87,147,156],"consistent":[89],"framework":[90],"all":[93],"publicly":[94],"available":[95],"large":[100],"scenarios.":[103],"We":[104,137,155],"summarize":[105],"each":[106,144],"approach":[107,145],"thoroughly":[109],"allocation":[111],"performance":[112,121,126],"(thread-based":[113],"well":[115,132],"warp-based),":[117],"look":[119],"at":[120],"scaling,":[122],"fragmentation":[123],"real-world":[125],"considering":[127],"synthetic":[129],"workload":[130],"updating":[134],"graphs.":[136],"discuss":[138],"strengths":[140],"weaknesses":[142],"guidelines":[148],"for":[149,175],"respective":[151],"best":[152],"usage":[153],"scenario.":[154],"unified":[158],"interface":[159],"integrate":[161],"any":[162],"tested":[165],"into":[168],"an":[169],"application":[170],"switch":[172],"between":[173],"benchmarking":[176],"purposes.":[177],"Given":[178],"our":[179],"results,":[180],"can":[182],"dispel":[183],"some":[184],"dread":[187],"associated":[188],"GPU.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}