{"id":"https://openalex.org/W3136358373","doi":"https://doi.org/10.1109/cgo51591.2021.9370339","title":"GPA: A GPU Performance Advisor Based on Instruction Sampling","display_name":"GPA: A GPU Performance Advisor Based on Instruction Sampling","publication_year":2021,"publication_date":"2021-02-27","ids":{"openalex":"https://openalex.org/W3136358373","doi":"https://doi.org/10.1109/cgo51591.2021.9370339","mag":"3136358373"},"language":"en","primary_location":{"id":"doi:10.1109/cgo51591.2021.9370339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5063326523","display_name":"Keren Zhou","orcid":"https://orcid.org/0000-0002-7977-3182"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Keren Zhou","raw_affiliation_strings":["Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027198310","display_name":"Xiaozhu Meng","orcid":"https://orcid.org/0000-0003-3716-9072"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhu Meng","raw_affiliation_strings":["Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047472245","display_name":"Ryuichi Sai","orcid":"https://orcid.org/0000-0001-8372-401X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryuichi Sai","raw_affiliation_strings":["Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089709469","display_name":"John Mellor\u2010Crummey","orcid":"https://orcid.org/0000-0002-9026-5453"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Mellor-Crummey","raw_affiliation_strings":["Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063326523"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":3.224,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91827075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"125"},"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":0.9987999796867371,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846280574798584},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8125985264778137},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7177096605300903},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6027027368545532},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5476155281066895},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5467215776443481},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4936610162258148},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4905911982059479},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.46883314847946167},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46680334210395813},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4447260797023773},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4107401371002197},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2552475929260254},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1732690930366516},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.17142903804779053},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1349567174911499},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.10707828402519226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846280574798584},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8125985264778137},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7177096605300903},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6027027368545532},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5476155281066895},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5467215776443481},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4936610162258148},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4905911982059479},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.46883314847946167},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46680334210395813},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4447260797023773},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4107401371002197},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2552475929260254},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1732690930366516},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.17142903804779053},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1349567174911499},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.10707828402519226},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo51591.2021.9370339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W960901134","https://openalex.org/W1507654557","https://openalex.org/W1517652255","https://openalex.org/W1575775940","https://openalex.org/W1902930330","https://openalex.org/W2013062050","https://openalex.org/W2043218878","https://openalex.org/W2080592089","https://openalex.org/W2093226410","https://openalex.org/W2098290747","https://openalex.org/W2136434791","https://openalex.org/W2142079700","https://openalex.org/W2290349115","https://openalex.org/W2535644961","https://openalex.org/W2580538010","https://openalex.org/W2767346422","https://openalex.org/W2789572737","https://openalex.org/W2796649226","https://openalex.org/W2883504296","https://openalex.org/W2944853139","https://openalex.org/W2952416601","https://openalex.org/W2979340153","https://openalex.org/W2989165654","https://openalex.org/W2999812057","https://openalex.org/W3015338905","https://openalex.org/W3040626038","https://openalex.org/W3040971560","https://openalex.org/W3132094421","https://openalex.org/W4245644062","https://openalex.org/W4248267595","https://openalex.org/W4249818463","https://openalex.org/W6634454564"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Developing":[0],"efficient":[1],"GPU":[2,12,96,148],"kernels":[3],"can":[4],"be":[5],"difficult":[6],"because":[7],"of":[8,11,51,62,65,109,160],"the":[9,26,63,95,106],"complexity":[10],"architectures":[13],"and":[14,57,69,87,94,127],"programming":[15],"models.":[16],"Existing":[17],"performance":[18,38,67,117,137],"tools":[19],"only":[20],"provide":[21],"coarse-grained":[22],"tuning":[23],"advice":[24],"at":[25,48],"kernel":[27],"level,":[28],"if":[29],"any.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,113,141],"describe":[35],"GPA,":[36,140],"a":[37,49,91,145,157],"advisor":[39],"for":[40],"NVIDIA":[41],"GPUs":[42],"that":[43,130],"suggests":[44],"potential":[45,107],"code":[46],"optimizations":[47],"hierarchy":[50],"levels,":[52],"including":[53],"individual":[54],"lines,":[55],"loops,":[56],"functions.":[58],"To":[59,104],"relieve":[60],"users":[61],"burden":[64],"interpreting":[66],"counters":[68],"analyzing":[70],"bottlenecks,":[71],"GPA":[72,131],"uses":[73,88],"data":[74],"flow":[75],"analysis":[76],"to":[77,83,97,119,135,153],"approximately":[78],"attribute":[79],"measured":[80],"instruction":[81],"stalls":[82],"their":[84],"root":[85],"causes":[86],"information":[89],"about":[90],"program's":[92],"structure":[93],"match":[98],"inefficiency":[99],"patterns":[100],"with":[101,125,156],"optimization":[102,111],"strategies.":[103],"quantify":[105],"benefits":[108],"each":[110],"strategy,":[112],"developed":[114],"PC":[115],"sampling-based":[116],"models":[118],"estimate":[120],"its":[121],"speedup.":[122],"Our":[123],"experiments":[124],"benchmarks":[126],"applications":[128],"show":[129],"provides":[132],"insightful":[133],"reports":[134],"guide":[136],"optimization.":[138],"Using":[139],"obtained":[142],"speedups":[143],"on":[144],"Volta":[146],"V100":[147],"ranging":[149],"from":[150],"1.01":[151],"x":[152],"3.58":[154],"\u00d7,":[155],"geometric":[158],"mean":[159],"1.22":[161],"x.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}