{"id":"https://openalex.org/W7134970142","doi":"https://doi.org/10.1145/3779212.3790130","title":"Asynchrony and GPUs: Bridging this Dichotomy for I/O with AGIO","display_name":"Asynchrony and GPUs: Bridging this Dichotomy for I/O with AGIO","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134970142","doi":"https://doi.org/10.1145/3779212.3790130"},"language":null,"primary_location":{"id":"doi:10.1145/3779212.3790130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779212.3790130","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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, PA, USA"],"raw_orcid":"https://orcid.org/0009-0008-0496-1462","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, 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, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6173-687X","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128719094","display_name":"Chia-Hao Chang","orcid":null},"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":"Chia-Hao Chang","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0002-6711-0071","affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128786340","display_name":"Vikram Sharma Mailthody","orcid":null},"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, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9611-8075","affiliations":[{"raw_affiliation_string":"Nvidia Research, Santa Clara, CA, USA","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, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1766-1289","affiliations":[{"raw_affiliation_string":"Nvidia Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128799247","display_name":"Wen-Mei Hwu","orcid":null},"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, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2532-5349","affiliations":[{"raw_affiliation_string":"Nvidia Research, Santa Clara, CA, 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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.7915999889373779,"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":0.7915999889373779,"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":0.1800999939441681,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0052999998442828655,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.6596999764442444},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.641700029373169},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.640999972820282},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6215000152587891},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.555400013923645},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46799999475479126},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.42899999022483826},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723999857902527},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6596999764442444},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.641700029373169},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.640999972820282},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6298999786376953},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779212.3790130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779212.3790130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1981393723","https://openalex.org/W1996511977","https://openalex.org/W1997162567","https://openalex.org/W2049875313","https://openalex.org/W2050513283","https://openalex.org/W2067313328","https://openalex.org/W2080592089","https://openalex.org/W2117689653","https://openalex.org/W2127510911","https://openalex.org/W2134427337","https://openalex.org/W2294751222","https://openalex.org/W2402285027","https://openalex.org/W2509091023","https://openalex.org/W2788517652","https://openalex.org/W2805009828","https://openalex.org/W2891759099","https://openalex.org/W2901994046","https://openalex.org/W2934584470","https://openalex.org/W2937574366","https://openalex.org/W2945773196","https://openalex.org/W2949486320","https://openalex.org/W3011293047","https://openalex.org/W3042369493","https://openalex.org/W3167720200","https://openalex.org/W3178293493","https://openalex.org/W4253088820","https://openalex.org/W4318541614","https://openalex.org/W4321782107","https://openalex.org/W4367684987","https://openalex.org/W4387723591","https://openalex.org/W4395106434"],"related_works":[],"abstract_inverted_index":{"GPUs":[0],"rely":[1],"on":[2,17],"a":[3,74,229,249],"largely":[4],"synchronous":[5,150,207,260],"programming":[6],"and":[7,66,73,96],"execution":[8],"model.":[9],"With":[10],"increasing":[11],"need":[12],"to":[13,39,47,80,104,111,133,143,167,170,185,195,221],"access":[14,125],"data":[15,161,210],"residing":[16],"SSDs,":[18],"GPU":[19,44,78,250],"threads":[20,45,79,169],"can":[21,137,242],"incur":[22],"significant":[23],"latencies":[24,51],"for":[25,77,234],"such":[26],"accesses":[27],"when":[28],"using":[29,248],"blocking/synchronous":[30],"I/O":[31,84,99,116,173,189,193],"mechanisms.":[32],"There":[33],"is":[34,119,164,182],"little":[35,183],"hardware/systems":[36],"support":[37],"today":[38],"perform":[40,82],"non-blocking/asynchronous":[41],"operations":[42,85],"from":[43,101,215],"directly":[46,81],"tolerate":[48],"microsecond":[49],"level":[50],"incurred":[52],"in":[53,94,109,122,158,209],"SSD":[54],"accesses.":[55],"To":[56],"fix":[57],"this":[58,60],"dichotomy,":[59],"paper":[61],"presents":[62],"the":[63,98,115,165,192,206,225,246,255],"design,":[64],"implementation":[65],"evaluation":[67],"of":[68,114,141,155,232,258],"AGIO,":[69,156],"which":[70],"provides":[71],"APIs":[72],"runtime":[75],"environment":[76],"asynchronous":[83],"(fully":[86],"GPU-orchestrated":[87],"without":[88],"CPU":[89],"involvement).":[90],"AGIO":[91,135,218,241],"decouples,":[92],"both":[93],"time":[95],"space,":[97],"initiation":[100,214],"its":[102,149,259],"completion,":[103],"allow":[105,168],"useful":[106,121],"computation":[107],"in-between,":[108],"order":[110],"hide":[112],"much":[113],"latency.":[117],"This":[118],"particularly":[120,157],"applications":[123,159],"with":[124,160,224,251],"patterns":[126],"known":[127],"at":[128],"compile":[129],"time,":[130],"where":[131],"similar":[132],"prefetching,":[134],"I/Os":[136],"be":[138],"introduced":[139],"ahead":[140],"need,":[142],"yield":[144],"65%":[145],"better":[146,203],"performance":[147,204,247],"than":[148,205,253],"counterpart.":[151],"A":[152],"non-intuitive":[153],"benefit":[154],"dependent":[162,211],"accesses,":[163],"ability":[166],"proceed":[171],"beyond":[172],"initiation,":[174],"towards":[175],"initiating":[176],"more":[177,196,219],"I/O,":[178],"even":[179],"if":[180],"there":[181],"compute":[184,256],"overlap.":[186],"Such":[187],"pro-active":[188],"issuance":[190],"increases":[191],"parallelism":[194],"fully":[197],"utilize":[198],"underlying":[199],"bandwidths,":[200],"yielding":[201],"32%":[202],"alternative":[208],"executions.":[212],"Decoupling":[213],"completion":[216],"makes":[217],"adaptive":[220],"dataset":[222],"characteristics,":[223],"programmer":[226],"not":[227],"needing":[228],"priori":[230],"knowledge":[231],"inputs":[233],"effective":[235],"performance.":[236],"We":[237],"also":[238],"show":[239],"that":[240],"meet":[243],"(or":[244],"better)":[245],"fewer":[252],"half":[254],"engines":[257],"counterparts.":[261]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-12T00:00:00"}
