{"id":"https://openalex.org/W2084660366","doi":"https://doi.org/10.1109/sbac-pad.2014.30","title":"Predicting GPU Performance from CPU Runs Using Machine Learning","display_name":"Predicting GPU Performance from CPU Runs Using Machine Learning","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2084660366","doi":"https://doi.org/10.1109/sbac-pad.2014.30","mag":"2084660366"},"language":"en","primary_location":{"id":"doi:10.1109/sbac-pad.2014.30","doi":"https://doi.org/10.1109/sbac-pad.2014.30","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2014.30","pdf_url":null,"source":{"id":"https://openalex.org/S4210215238","display_name":"International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","issn_l":"1550-6533","issn":["1550-6533","2643-3001"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5073341059","display_name":"Ioana Baldini","orcid":"https://orcid.org/0000-0002-8257-9866","observed_orcids":["https://orcid.org/0000-0002-8257-9866"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioana Baldini","raw_affiliation_strings":["IBM Research","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111447845","display_name":"Stephen J. Fink","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen J. Fink","raw_affiliation_strings":["IBM Research","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040828024","display_name":"Erik Altman","orcid":"https://orcid.org/0009-0001-0978-0360","observed_orcids":["https://orcid.org/0009-0001-0978-0360"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Altman","raw_affiliation_strings":["IBM Research","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":1.1299,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.74954552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"254","last_page":"261"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.8880000114440918},{"id":"https://openalex.org/keywords/dynamic-profiling","display_name":"dynamic profiling","score":0.7379999756813049},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.6909999847412109},{"id":"https://openalex.org/keywords/parallel-benchmarks","display_name":"parallel benchmarks","score":0.6710000038146973},{"id":"https://openalex.org/keywords/gpu-porting","display_name":"GPU porting","score":0.6169999837875366},{"id":"https://openalex.org/keywords/speedup-prediction","display_name":"speedup prediction","score":0.7570000290870667},{"id":"https://openalex.org/keywords/performance-modeling","display_name":"performance modeling","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9588586091995239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819197416305542},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5968028903007507},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.554976224899292},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5482927560806274},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5298635363578796},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5261582732200623},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5118116736412048},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5003011226654053},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.4944734573364258},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.47039780020713806},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4382103681564331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3430330753326416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32381200790405273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1858043372631073},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1286049485206604},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12081381678581238},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sbac-pad.2014.30","doi":"https://doi.org/10.1109/sbac-pad.2014.30","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-pad.2014.30","pdf_url":null,"source":{"id":"https://openalex.org/S4210215238","display_name":"International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","issn_l":"1550-6533","issn":["1550-6533","2643-3001"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W173229765","https://openalex.org/W1805440014","https://openalex.org/W1981896890","https://openalex.org/W1982020565","https://openalex.org/W1989157207","https://openalex.org/W2080592089","https://openalex.org/W2089841364","https://openalex.org/W2100787464","https://openalex.org/W2107773544","https://openalex.org/W2130336316","https://openalex.org/W2132219981","https://openalex.org/W2133990480","https://openalex.org/W2142769604","https://openalex.org/W2147623728","https://openalex.org/W2152513418","https://openalex.org/W2154713585","https://openalex.org/W2157070686","https://openalex.org/W2159481344","https://openalex.org/W2164818318","https://openalex.org/W2167209023","https://openalex.org/W2167334577","https://openalex.org/W2168029744","https://openalex.org/W2273440736","https://openalex.org/W3003483880","https://openalex.org/W3147501999","https://openalex.org/W3152118992","https://openalex.org/W4230415451","https://openalex.org/W4239510810","https://openalex.org/W4239813889","https://openalex.org/W4300937065"],"related_works":["https://openalex.org/W7120605363","https://openalex.org/W2559932280","https://openalex.org/W2624209381","https://openalex.org/W2239144794","https://openalex.org/W4297569227","https://openalex.org/W2038666141","https://openalex.org/W2259067957","https://openalex.org/W2948929415","https://openalex.org/W2952965520","https://openalex.org/W2475875537"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"can":[4,58,110,141],"deliver":[5],"considerable":[6],"performance":[7,15],"gains":[8],"over":[9],"general":[10,90],"purpose":[11,91],"processors.":[12,92],"However,":[13],"GPU":[14,64,115],"improvement":[16],"vary":[17],"considerably":[18],"across":[19],"applications.":[20],"Porting":[21],"applications":[22,42],"to":[23,39,48,76,146],"GPUs":[24],"by":[25],"rewriting":[26],"code":[27],"with":[28,122,150],"GPU-specific":[29],"languages":[30],"requires":[31],"significant":[32],"effort.":[33],"In":[34],"consequence,":[35],"it":[36],"is":[37],"desirable":[38],"predict":[40,111,142],"which":[41,71],"would":[43],"benefit":[44],"most":[45],"before":[46],"porting":[47],"the":[49,100,112,131,143],"GPU.":[50],"This":[51,66],"paper":[52],"shows":[53],"that":[54,103],"machine":[55],"learning":[56,74],"techniques":[57],"build":[59],"accurate":[60],"predictive":[61,78],"models":[62,140],"for":[63],"acceleration.":[65],"study":[67],"presents":[68],"an":[69,148,151],"approach":[70],"applies":[72],"supervised":[73],"algorithms":[75],"infer":[77],"models,":[79],"based":[80],"on":[81,89,117,130],"dynamic":[82],"profile":[83],"data":[84],"collected":[85],"via":[86],"instrumented":[87],"runs":[88],"For":[93,136],"a":[94,104],"set":[95,106],"of":[96,107,114,154],"18":[97],"parallel":[98],"benchmarks,":[99],"results":[101],"show":[102],"small":[105],"easily-obtainable":[108],"features":[109],"magnitude":[113],"speedups":[116],"two":[118],"different":[119],"high-end":[120],"GPUs,":[121],"accuracies":[123],"varying":[124],"between":[125],"77%":[126],"and":[127,134],"90%,":[128],"depending":[129],"prediction":[132],"mechanism":[133],"scenario.":[135],"already-ported":[137],"applications,":[138],"similar":[139],"best":[144],"device":[145],"run":[147],"application":[149],"effective":[152],"accuracy":[153],"91%.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}