{"id":"https://openalex.org/W3011293047","doi":"https://doi.org/10.1145/3373376.3378529","title":"Batch-Aware Unified Memory Management in GPUs for Irregular Workloads","display_name":"Batch-Aware Unified Memory Management in GPUs for Irregular Workloads","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3011293047","doi":"https://doi.org/10.1145/3373376.3378529","mag":"3011293047"},"language":"en","primary_location":{"id":"doi:10.1145/3373376.3378529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373376.3378529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","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/A5066623182","display_name":"Hyojong Kim","orcid":"https://orcid.org/0000-0002-5476-2372"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyojong Kim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaewoong Sim","raw_affiliation_strings":["Intel Labs, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Portland, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010507285","display_name":"Prasun Gera","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasun Gera","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046221045","display_name":"Ramyad Hadidi","orcid":"https://orcid.org/0000-0002-8731-1084"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramyad Hadidi","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066623182"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":9.9006,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98801635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1357","last_page":"1370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.8770729899406433},{"id":"https://openalex.org/keywords/demand-paging","display_name":"Demand paging","score":0.8336930274963379},{"id":"https://openalex.org/keywords/page-fault","display_name":"Page fault","score":0.780645489692688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6391357779502869},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5859042406082153},{"id":"https://openalex.org/keywords/paging","display_name":"Paging","score":0.5521647930145264},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.49344339966773987},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.4923967123031616},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.45946311950683594},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.45527806878089905},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4373372197151184},{"id":"https://openalex.org/keywords/page","display_name":"Page","score":0.422539085149765},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.37674474716186523},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3528589606285095},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.21038392186164856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770729899406433},{"id":"https://openalex.org/C188873839","wikidata":"https://www.wikidata.org/wiki/Q5255045","display_name":"Demand paging","level":5,"score":0.8336930274963379},{"id":"https://openalex.org/C193343404","wikidata":"https://www.wikidata.org/wiki/Q1928607","display_name":"Page fault","level":5,"score":0.780645489692688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6391357779502869},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5859042406082153},{"id":"https://openalex.org/C50954386","wikidata":"https://www.wikidata.org/wiki/Q656083","display_name":"Paging","level":2,"score":0.5521647930145264},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.49344339966773987},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.4923967123031616},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.45946311950683594},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.45527806878089905},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4373372197151184},{"id":"https://openalex.org/C33925742","wikidata":"https://www.wikidata.org/wiki/Q361698","display_name":"Page","level":2,"score":0.422539085149765},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.37674474716186523},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3528589606285095},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.21038392186164856},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373376.3378529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373376.3378529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1883226873","https://openalex.org/W1975274780","https://openalex.org/W1994182141","https://openalex.org/W2049403384","https://openalex.org/W2056816375","https://openalex.org/W2062430565","https://openalex.org/W2066636486","https://openalex.org/W2068768832","https://openalex.org/W2082000934","https://openalex.org/W2087866311","https://openalex.org/W2093828978","https://openalex.org/W2094224753","https://openalex.org/W2097643185","https://openalex.org/W2100926301","https://openalex.org/W2101482453","https://openalex.org/W2102843684","https://openalex.org/W2120138088","https://openalex.org/W2120715680","https://openalex.org/W2123608497","https://openalex.org/W2125551452","https://openalex.org/W2126987530","https://openalex.org/W2147393894","https://openalex.org/W2149859020","https://openalex.org/W2156299749","https://openalex.org/W2156703074","https://openalex.org/W2156898111","https://openalex.org/W2330672121","https://openalex.org/W2335115745","https://openalex.org/W2472987663","https://openalex.org/W2517837804","https://openalex.org/W2613639279","https://openalex.org/W2764065518","https://openalex.org/W2793599434","https://openalex.org/W2793655593","https://openalex.org/W2885000039","https://openalex.org/W2934021599","https://openalex.org/W2949486320","https://openalex.org/W4235366964","https://openalex.org/W4240476789"],"related_works":["https://openalex.org/W1990596024","https://openalex.org/W2017276153","https://openalex.org/W4241723377","https://openalex.org/W4235954812","https://openalex.org/W2059368477","https://openalex.org/W2139847837","https://openalex.org/W3095732246","https://openalex.org/W2797349320","https://openalex.org/W1993535731","https://openalex.org/W2397278003"],"abstract_inverted_index":{"While":[0],"unified":[1],"virtual":[2],"memory":[3],"and":[4,102,118,140,153,202],"demand":[5,105],"paging":[6,106],"in":[7,38,44,52],"modern":[8,45],"GPUs":[9],"provide":[10,28],"convenient":[11],"abstractions":[12],"to":[13,98],"programmers":[14],"for":[15,107],"working":[16],"with":[17,162,169],"large-scale":[18,77],"applications,":[19],"they":[20],"come":[21],"at":[22],"a":[23,59,114],"significant":[24],"performance":[25],"cost.":[26],"We":[27,67,86,191,213],"the":[29,49,55,82,124,128,137,142,159,177,187,197,204,217],"first":[30],"comprehensive":[31],"analysis":[32],"of":[33,62,73,130,144,184,207],"major":[34],"inefficiencies":[35,101],"that":[36,69,79,91,121,176,193,216],"arise":[37],"page":[39,64,74,131,156,171,189],"fault":[40,53],"handling":[41],"mechanisms":[42],"employed":[43],"GPUs.":[46,108],"To":[47,109],"amortize":[48],"high":[50],"costs":[51],"handling,":[54],"GPU":[56,63,115],"runtime":[57,116],"processes":[58],"large":[60],"number":[61,129,143,206],"faults":[65,75,132],"together.":[66],"observe":[68],"this":[70,110],"batched":[71],"processing":[72,220],"introduces":[76],"serialization":[78],"greatly":[80],"hurts":[81],"GPU's":[83],"execution":[84],"throughput.":[85],"show":[87,192,215],"real":[88],"machine":[89],"measurements":[90],"corroborate":[92],"our":[93,194],"findings.":[94],"Our":[95,173],"goal":[96],"is":[97,222],"mitigate":[99],"these":[100],"enable":[103],"efficient":[104],"end,":[111],"we":[112],"propose":[113],"software":[117],"hardware":[119,164],"solution":[120,179,195],"(1)":[122],"increases":[123,196],"batch":[125,198,219],"size":[126,199],"(i.e.,":[127],"handled":[133],"together),":[134],"thereby":[135],"amortizing":[136],"\u00f8verheadName":[138],"time,":[139],"reduces":[141,203],"batches":[145,208],"by":[146,166,200,209,224],"supporting":[147],"CPU-like":[148],"thread":[149],"block":[150],"context":[151],"switching,":[152],"(2)":[154],"takes":[155],"eviction":[157],"off":[158],"critical":[160],"path":[161],"no":[163],"changes":[165],"overlapping":[167],"evictions":[168],"CPU-to-GPU":[170],"migrations.":[172],"evaluation":[174],"demonstrates":[175],"proposed":[178],"provides":[180],"an":[181],"average":[182,218],"speedup":[183],"2x":[185],"over":[186],"state-of-the-art":[188],"prefetching.":[190],"2.27x":[201],"total":[205],"51%":[210],"on":[211],"average.":[212],"also":[214],"time":[221],"reduced":[223],"27%.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}