{"id":"https://openalex.org/W3137898237","doi":"https://doi.org/10.1145/3422575.3422784","title":"DELTA: Validate GPU Memory Profiling with Microbenchmarks","display_name":"DELTA: Validate GPU Memory Profiling with Microbenchmarks","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3137898237","doi":"https://doi.org/10.1145/3422575.3422784","mag":"3137898237"},"language":"en","primary_location":{"id":"doi:10.1145/3422575.3422784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422575.3422784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Symposium on Memory 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/A5100757684","display_name":"Xianwei Zhang","orcid":"https://orcid.org/0000-0002-9534-1929"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xianwei Zhang","raw_affiliation_strings":["AMD Inc, United States"],"affiliations":[{"raw_affiliation_string":"AMD Inc, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026774559","display_name":"Evgeny Shcherb\u0430kov","orcid":"https://orcid.org/0000-0001-5120-2380"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evgeny Shcherbakov","raw_affiliation_strings":["AMD Inc, United States"],"affiliations":[{"raw_affiliation_string":"AMD Inc, United States","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100757684"],"corresponding_institution_ids":["https://openalex.org/I4210137977"],"apc_list":null,"apc_paid":null,"fwci":0.231,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53324623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9969000220298767,"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":0.7153946757316589},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6229159832000732},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4001593291759491},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24710562825202942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153946757316589},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6229159832000732},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4001593291759491},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24710562825202942}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3422575.3422784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422575.3422784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Symposium on Memory Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1592895353","https://openalex.org/W2019143817","https://openalex.org/W2027806965","https://openalex.org/W2110195531","https://openalex.org/W2117610793","https://openalex.org/W2121717408","https://openalex.org/W2134633067","https://openalex.org/W2163687928","https://openalex.org/W2761132374","https://openalex.org/W2887659847","https://openalex.org/W2899578192","https://openalex.org/W2934426651","https://openalex.org/W2961904511","https://openalex.org/W2977438086","https://openalex.org/W2979340153","https://openalex.org/W2996807164","https://openalex.org/W4239813889","https://openalex.org/W4256231890","https://openalex.org/W4256477861"],"related_works":["https://openalex.org/W2348361596","https://openalex.org/W1604898313","https://openalex.org/W2117014006","https://openalex.org/W3018118667","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1491899005","https://openalex.org/W2521117258","https://openalex.org/W2998249817","https://openalex.org/W4230635966"],"abstract_inverted_index":{"With":[0],"the":[1,33,39,47,63,82,96,107,116,119,136,160,171,186,198,205,210,216],"advent":[2],"of":[3,42,106,118,130,192],"GPU":[4],"computing,":[5],"profiling":[6,64,72,121,172,217],"tools":[7,22,65,73,173],"are":[8,23,132,140,157,174,212],"now":[9],"widely":[10],"used":[11],"to":[12,30,35,50,61,78,114,142,146,158,164,214],"assist":[13],"developers":[14],"in":[15],"identifying":[16],"and":[17,45,85,92,123,163,181,189,194,201,204],"solving":[18],"performance":[19,28],"bottlenecks.":[20],"Those":[21],"commonly":[24],"relying":[25],"on":[26,104,135,197],"hardware":[27,55],"counters":[29],"grant":[31],"users":[32],"access":[34],"low-level":[36],"activities.":[37],"Considering":[38],"increasing":[40],"complexity":[41],"modern":[43],"GPUs":[44,200],"also":[46],"efforts":[48],"needed":[49],"associate":[51],"program":[52,83,144],"behaviors":[53,84,145],"with":[54,66,177],"events,":[56],"it":[57],"is":[58],"not":[59],"trivial":[60],"construct":[62],"assured":[67],"correctness.":[68],"As":[69],"a":[70,100],"result,":[71],"should":[74],"be":[75,89],"strictly":[76],"validated":[77],"make":[79],"sure":[80],"that":[81,209],"resource":[86],"usages":[87],"can":[88],"correctly":[90,175],"captured":[91],"analyzed.":[93],"To":[94],"aid":[95],"validation,":[97],"we":[98],"create":[99],"testing":[101],"prototype":[102],"DELTA,":[103],"top":[105],"open-source":[108],"Radeon":[109],"Open":[110],"Compute":[111],"platform":[112],"(ROCm),":[113],"investigate":[115],"values":[117],"derived":[120],"metrics":[122],"their":[124],"underlying":[125],"basic":[126],"counters.":[127],"The":[128],"tests":[129,156,211],"DELTA":[131],"generally":[133],"based":[134],"classical":[137],"microbenchmarks,":[138],"which":[139],"capable":[141],"control":[143],"generate":[147],"predictable":[148],"statistics.":[149],"Differing":[150],"from":[151],"prior":[152],"dissecting":[153],"works,":[154],"our":[155],"examine":[159],"profiled":[161],"results":[162,191],"compare":[165],"against":[166],"desired":[167],"patterns,":[168],"reporting":[169],"whether":[170],"working":[176],"appropriate":[178],"data":[179],"collection":[180],"processing.":[182],"This":[183],"paper":[184],"presents":[185],"validation":[187],"methodology":[188],"experimental":[190],"cache":[193],"main":[195],"memory":[196],"recent":[199],"ROCm":[202],"platform,":[203],"case":[206],"studies":[207],"demonstrate":[208],"helpful":[213],"scrutinize":[215],"tools.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}