{"id":"https://openalex.org/W2100415730","doi":"https://doi.org/10.1109/ispass.2011.5762730","title":"Where is the data? Why you cannot debate CPU vs. GPU performance without the answer","display_name":"Where is the data? Why you cannot debate CPU vs. GPU performance without the answer","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2100415730","doi":"https://doi.org/10.1109/ispass.2011.5762730","mag":"2100415730"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2011.5762730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","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/A5031642246","display_name":"Chris Gregg","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Gregg","raw_affiliation_strings":["Department of Computer Science, University of Virginia, USA","Department of Computer Science, University of Virginia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Computer Science, University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046756907","display_name":"Kim Hazelwood","orcid":"https://orcid.org/0000-0002-2713-8507"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim Hazelwood","raw_affiliation_strings":["Department of Computer Science, University of Virginia, USA","Department of Computer Science, University of Virginia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Computer Science, University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031642246"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":26.6713,"has_fulltext":false,"cited_by_count":282,"citation_normalized_percentile":{"value":0.99823797,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"134","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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":0.8772364854812622},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6812435984611511},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6697720289230347},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5616783499717712},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5539174675941467},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5285053849220276},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5062524676322937},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5025901794433594},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4912413954734802},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4811081290245056},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4294183850288391},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4162190854549408},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41552940011024475},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.37917789816856384},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29860222339630127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11209648847579956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772364854812622},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6812435984611511},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6697720289230347},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5616783499717712},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5539174675941467},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5285053849220276},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5062524676322937},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5025901794433594},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4912413954734802},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4811081290245056},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4294183850288391},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4162190854549408},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41552940011024475},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.37917789816856384},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29860222339630127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11209648847579956},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2011.5762730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W31392012","https://openalex.org/W1975778423","https://openalex.org/W1984222112","https://openalex.org/W1992851788","https://openalex.org/W2001488415","https://openalex.org/W2008185810","https://openalex.org/W2017086619","https://openalex.org/W2036477303","https://openalex.org/W2095894588","https://openalex.org/W2103877122","https://openalex.org/W2112828875","https://openalex.org/W2115496473","https://openalex.org/W2127766448","https://openalex.org/W2128022558","https://openalex.org/W2128853364","https://openalex.org/W2130561688","https://openalex.org/W2141579716","https://openalex.org/W2153808006","https://openalex.org/W2159481344","https://openalex.org/W2295862081","https://openalex.org/W2406413350","https://openalex.org/W3087399931","https://openalex.org/W4241790656","https://openalex.org/W4250981202","https://openalex.org/W6601288215","https://openalex.org/W6677283519","https://openalex.org/W6713725621","https://openalex.org/W6782847938"],"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/W2080146221","https://openalex.org/W2153506571","https://openalex.org/W3104348697","https://openalex.org/W1972148443"],"abstract_inverted_index":{"General":[0],"purpose":[1],"GPU":[2,113,149,165],"Computing":[3],"(GPGPU)":[4],"has":[5],"taken":[6],"off":[7],"in":[8,83,178,207],"the":[9,23,63,79,84,89,93,148,176],"past":[10],"few":[11],"years,":[12],"with":[13,120],"great":[14],"promises":[15],"for":[16,175,184,197],"increased":[17],"desktop":[18],"processing":[19,150],"power":[20],"due":[21],"to":[22,91,95,140,143,157,168,203],"large":[24],"number":[25,117],"of":[26,81,112,118],"fast":[27],"computing":[28],"cores":[29],"on":[30,51,115],"high-end":[31],"graphics":[32],"cards.":[33],"Many":[34],"publications":[35],"have":[36,41,56,107],"demonstrated":[37],"phenomenal":[38],"performance":[39,64],"and":[40,88,101,123,188],"reported":[42],"speedups":[43],"as":[44,46],"much":[45],"1000\u00d7":[47],"over":[48],"code":[49,61],"running":[50],"multi-core":[52],"CPUs.":[53],"Other":[54],"studies":[55],"claimed":[57],"that":[58,69,127,191],"well-tuned":[59],"CPU":[60],"reduces":[62],"gap":[65],"significantly.":[66],"We":[67,106,180],"demonstrate":[68],"this":[70,171,192],"important":[71,202],"discussion":[72],"is":[73,155,172,193,201],"missing":[74],"a":[75,109,116,145,182],"key":[76],"aspect,":[77],"specifically":[78],"question":[80],"where":[82,96],"system":[85],"data":[86,94],"resides,":[87],"overhead":[90,162],"move":[92],"it":[97,134,154],"will":[98],"be":[99],"used,":[100],"back":[102],"again":[103],"if":[104],"necessary.":[105],"benchmarked":[108],"broad":[110],"set":[111],"kernels":[114],"platforms":[119],"different":[121],"GPUs":[122],"our":[124],"results":[125],"show":[126],"when":[128,163],"memory":[129,160],"transfer":[130,161],"times":[131],"are":[132],"included,":[133],"can":[135],"easily":[136],"take":[137],"between":[138],"2":[139],"50\u00d7":[141],"longer":[142],"run":[144],"kernel":[146],"than":[147],"time":[151],"alone.":[152],"Therefore,":[153],"necessary":[156],"either":[158],"include":[159],"reporting":[164,198],"performance,":[166,199],"or":[167],"explain":[169],"why":[170],"not":[173,194],"relevant":[174],"application":[177],"question.":[179],"suggest":[181],"taxonomy":[183],"future":[185],"CPU/GPU":[186],"comparisons,":[187],"we":[189],"argue":[190],"only":[195],"germane":[196],"but":[200],"heterogeneous":[204],"scheduling":[205],"research":[206],"general.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":25}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}