{"id":"https://openalex.org/W2028145761","doi":"https://doi.org/10.1109/asap.2014.6868641","title":"Performance modeling for highly-threaded many-core GPUs","display_name":"Performance modeling for highly-threaded many-core GPUs","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2028145761","doi":"https://doi.org/10.1109/asap.2014.6868641","mag":"2028145761"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2014.6868641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2014.6868641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors","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/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University in Sl. Louis","Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in Sl. Louis","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006814645","display_name":"Roger D. Chamberlain","orcid":"https://orcid.org/0000-0002-7207-6106"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger D. Chamberlain","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University in Sl. Louis","Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in Sl. Louis","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035990793","display_name":"Kunal Agrawal","orcid":"https://orcid.org/0000-0001-5882-6647"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Agrawal","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University in Sl. Louis","Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in Sl. Louis","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Washington Univ. in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017116858"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":3.9842,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93711194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"91"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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":0.9011055827140808},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.715757429599762},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5649731755256653},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5444000363349915},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4805367588996887},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.387629896402359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9011055827140808},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.715757429599762},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5649731755256653},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5444000363349915},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4805367588996887},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.387629896402359},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2014.6868641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2014.6868641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W73629738","https://openalex.org/W1983929828","https://openalex.org/W1985291160","https://openalex.org/W2014661416","https://openalex.org/W2045271686","https://openalex.org/W2063186542","https://openalex.org/W2108792719","https://openalex.org/W2111252763","https://openalex.org/W2113282196","https://openalex.org/W2115654888","https://openalex.org/W2116508956","https://openalex.org/W2118127549","https://openalex.org/W2118558147","https://openalex.org/W2122817518","https://openalex.org/W2127007746","https://openalex.org/W2128912557","https://openalex.org/W2130336316","https://openalex.org/W2133741166","https://openalex.org/W2137919745","https://openalex.org/W2142769604","https://openalex.org/W2153495590","https://openalex.org/W2156467710","https://openalex.org/W2167334577","https://openalex.org/W2616131264","https://openalex.org/W2949619969","https://openalex.org/W3141650078","https://openalex.org/W4241553019","https://openalex.org/W4246219036","https://openalex.org/W6677013061","https://openalex.org/W6679367475","https://openalex.org/W6737651413"],"related_works":["https://openalex.org/W2128523353","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2074886298"],"abstract_inverted_index":{"Highly-threaded":[0],"many-core":[1],"GPUs":[2],"can":[3],"provide":[4],"high":[5],"throughput":[6],"for":[7,85],"a":[8,24],"wide":[9],"range":[10],"of":[11,23,27,47,53,142],"algorithms":[12],"and":[13,29,50,69,80,96,106],"applications.":[14],"Such":[15],"machines":[16],"hide":[17],"memory":[18,31],"latencies":[19],"via":[20],"the":[21,39,43,45,51,73,82,99,104,119,129,135],"use":[22],"large":[25,30],"number":[26],"threads":[28],"bandwidth.":[32],"The":[33,110],"achieved":[34],"performance,":[35],"therefore,":[36],"depends":[37],"on":[38,89],"parallelism":[40],"exploited":[41],"by":[42,134],"algorithm,":[44],"effectiveness":[46],"latency":[48],"hiding,":[49],"utilization":[52],"multiprocessors":[54],"(occupancy).":[55],"In":[56,71,117],"this":[57],"paper,":[58],"we":[59],"extend":[60],"previously":[61],"proposed":[62],"analytical":[63],"models,":[64],"jointly":[65],"addressing":[66],"parallelism,":[67],"latency-hiding,":[68],"occupancy.":[70],"particular,":[72],"model":[74,111,120],"not":[75],"only":[76],"helps":[77],"to":[78,122],"explore":[79],"reduce":[81],"configuration":[83],"space":[84],"tuning":[86],"kernel":[87],"execution":[88],"GPUs,":[90],"but":[91],"also":[92],"reflects":[93],"performance":[94],"bottlenecks":[95],"predicts":[97],"how":[98],"runtime":[100],"will":[101],"trend":[102],"as":[103],"problem":[105],"other":[107],"parameters":[108],"scale.":[109],"is":[112],"validated":[113],"with":[114],"empirical":[115],"experiments.":[116],"addition,":[118],"points":[121],"at":[123],"least":[124],"one":[125],"circumstance":[126],"in":[127,140],"which":[128],"occupancy":[130],"decisions":[131],"automatically":[132],"made":[133],"scheduler":[136],"are":[137],"clearly":[138],"sub-optimal":[139],"terms":[141],"runtime.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
