{"id":"https://openalex.org/W4308273116","doi":"https://doi.org/10.1109/nas55553.2022.9925516","title":"Quantifying Performance Gains of GPUDirect Storage","display_name":"Quantifying Performance Gains of GPUDirect Storage","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4308273116","doi":"https://doi.org/10.1109/nas55553.2022.9925516"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas55553.2022.9925516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5024970673","display_name":"Devasena Inupakutika","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devasena Inupakutika","raw_affiliation_strings":["Samsung, San Diego, California"],"affiliations":[{"raw_affiliation_string":"Samsung, San Diego, California","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073984193","display_name":"Bridget Davis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bridget Davis","raw_affiliation_strings":["Samsung, San Diego, California"],"affiliations":[{"raw_affiliation_string":"Samsung, San Diego, California","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059783635","display_name":"Qirui Yang","orcid":"https://orcid.org/0000-0003-0885-1830"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qirui Yang","raw_affiliation_strings":["Samsung, San Diego, California"],"affiliations":[{"raw_affiliation_string":"Samsung, San Diego, California","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372601","display_name":"Daniel Kim","orcid":"https://orcid.org/0000-0003-4422-341X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kim","raw_affiliation_strings":["Samsung, San Diego, California"],"affiliations":[{"raw_affiliation_string":"Samsung, San Diego, California","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072524717","display_name":"David Akopian","orcid":"https://orcid.org/0000-0001-5977-9969"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Akopian","raw_affiliation_strings":["UTSA, San Antonio, Texas"],"affiliations":[{"raw_affiliation_string":"UTSA, San Antonio, Texas","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.506,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.593776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":75,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995,"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":0.9995,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11478","display_name":"Caching and Content Delivery","score":0.993,"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/performance-improvement","display_name":"Performance Improvement","score":0.41913474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8703587},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.77924705},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5170139},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5142195},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46880773},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.45703685},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45433196},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43750733},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.41913474},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3842384},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3482437},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08343962},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas55553.2022.9925516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42,"display_name":"Industry, innovation and infrastructure"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":7,"referenced_works":["https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2252556718","https://openalex.org/W2509331106","https://openalex.org/W2741003467","https://openalex.org/W3118094115","https://openalex.org/W3138303811"],"related_works":["https://openalex.org/W4382618745","https://openalex.org/W2898981446","https://openalex.org/W2885125400","https://openalex.org/W2748922771","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W1973775000"],"abstract_inverted_index":{"Rapid":[0],"growth":[1],"in":[2,43],"data":[3,48,69,207],"collection":[4],"has":[5,60,83],"led":[6],"to":[7,33,87,122,222,226],"a":[8,55,81,131,147,243,258],"need":[9,121],"for":[10,238,251,264],"reconditioning":[11],"the":[12,27,47,65,94,117,124,128,193,202,220,239],"underlying":[13],"computation":[14],"and":[15,24,39,52,74,109,156,170,188,209,254,266],"storage":[16,53,76,155,181,268],"solutions.":[17],"In":[18,159],"data-intensive":[19],"workloads":[20,45,187,190,213],"involving":[21],"machine":[22,211],"learning":[23,212],"large-scale":[25],"simulations,":[26],"computations":[28],"are":[29,232],"shifting":[30],"from":[31,195],"CPUs":[32],"GPUs.":[34],"The":[35],"overhead":[36],"of":[37,68,174,204,242,261],"input":[38],"output":[40],"(IO)":[41],"operations":[42],"these":[44,196],"during":[46],"transfer":[49],"between":[50,71,150],"GPU":[51,72,112,157,244],"becomes":[54],"new":[56,132],"performance":[57,203,240,263],"bottleneck.":[58],"It":[59],"thus":[61],"become":[62],"evident":[63],"that":[64,77,191],"traditional":[66],"approach":[67,97],"transfers":[70],"memory":[73],"device":[75],"involves":[78],"CPU":[79,99,118,171],"as":[80,179],"buffer,":[82],"limited":[84],"GPUs'":[85],"ability":[86],"utilize":[88,123,219],"their":[89],"vast":[90],"resources":[91],"efficiently.":[92],"Additionally,":[93],"bounce":[95],"buffer":[96],"wastes":[98],"cycles":[100],"spent":[101],"on":[102,139],"transferring":[103],"data.":[104,125],"These":[105],"paths":[106],"introduce":[107],"latency,":[108],"reduce":[110],"overall":[111],"processing":[113],"performance,":[114],"especially":[115],"if":[116],"does":[119],"not":[120],"To":[126],"solve":[127],"resulting":[129],"bottlenecks,":[130],"technology,":[133],"NVIDIA":[134,140],"GPUDirect":[135],"Storage":[136],"(GDS)":[137],"supported":[138,248],"GPU,":[141],"accelerates":[142],"GPU-storage":[143],"communication":[144],"by":[145],"establishing":[146],"direct":[148],"path":[149],"local":[151,252,265],"NVMe":[152,253],"or":[153],"remote":[154,180,267],"memory.":[158],"this":[160],"work,":[161],"we":[162,218],"quantify":[163],"high":[164],"throughput":[165],"gains,":[166],"low":[167],"latency":[168],"achievements,":[169],"utilization":[172],"savings":[173],"GDS":[175,247,262],"technology":[176],"with":[177,185,215,228,246],"Weka":[178],"cluster.":[182],"We":[183,199],"experiment":[184],"various":[186],"identify":[189],"benefit":[192],"most":[194],"employed":[197],"technologies.":[198],"systematically":[200],"measure":[201],"synthetic":[205],"representative":[206],"read":[208],"real":[210],"optimized":[214],"GDS.":[216,229],"Finally,":[217],"findings":[221],"discuss":[223],"correlated":[224],"implications":[225],"systems":[227,250],"Demonstration":[230],"results":[231],"twofold:":[233],"a)":[234],"A":[235],"testing":[236],"methodology":[237],"evaluation":[241],"client":[245],"file":[249],"Weka,":[255],"b)":[256],"Establish":[257],"baseline":[259],"level":[260],"devices.":[269]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4308273116","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-04-22T14:39:49.629957","created_date":"2022-11-10"}