{"id":"https://openalex.org/W2899387410","doi":"https://doi.org/10.1109/hpcs.2018.00095","title":"OpenCL Performance Prediction using Architecture-Independent Features","display_name":"OpenCL Performance Prediction using Architecture-Independent Features","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2899387410","doi":"https://doi.org/10.1109/hpcs.2018.00095","mag":"2899387410"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2018.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.00156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074912565","display_name":"Beau Johnston","orcid":"https://orcid.org/0000-0001-5426-1415"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Beau Johnston","raw_affiliation_strings":["Research School of Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067122110","display_name":"Greg Falzon","orcid":"https://orcid.org/0000-0002-1989-9357"},"institutions":[{"id":"https://openalex.org/I90745801","display_name":"University of New England","ror":"https://ror.org/04r659a56","country_code":"AU","type":"education","lineage":["https://openalex.org/I90745801"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gregory Falzon","raw_affiliation_strings":["School of Science and Technology, University of New England, Armidale, Australia"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, University of New England, Armidale, Australia","institution_ids":["https://openalex.org/I90745801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034216883","display_name":"Josh Milthorpe","orcid":"https://orcid.org/0000-0002-3588-9896"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Josh Milthorpe","raw_affiliation_strings":["Research School of Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.348,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":9,"citation_normalized_percentile":{"value":0.690814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"569"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9999,"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":0.9999,"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":0.9997,"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":0.9991,"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/software-portability","display_name":"Software portability","score":0.80966455},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.52661073},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance Prediction","score":0.49216217},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.46469352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9103835},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.80966455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.59941137},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.531662},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.53080374},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.52661073},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.49216217},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4751092},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.46469352},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4625015},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.43056887},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26710227},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12158394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.094937384},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2018.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.00156","pdf_url":"https://arxiv.org/pdf/1811.00156","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.00156","pdf_url":"https://arxiv.org/pdf/1811.00156","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1512154564","https://openalex.org/W1958965543","https://openalex.org/W1966128391","https://openalex.org/W2033676590","https://openalex.org/W2094999780","https://openalex.org/W2095569799","https://openalex.org/W2095668076","https://openalex.org/W2108343462","https://openalex.org/W2113755305","https://openalex.org/W2114719509","https://openalex.org/W2156697773","https://openalex.org/W2157395790","https://openalex.org/W2802355373","https://openalex.org/W2911964244","https://openalex.org/W2964064079","https://openalex.org/W3102027041","https://openalex.org/W4289698263"],"related_works":["https://openalex.org/W4386869550","https://openalex.org/W4308090451","https://openalex.org/W2137086253","https://openalex.org/W2077030552","https://openalex.org/W2075436644","https://openalex.org/W2066992028","https://openalex.org/W2040385792","https://openalex.org/W1993991287","https://openalex.org/W1584537303","https://openalex.org/W107105315"],"abstract_inverted_index":{"OpenCL":[0,37,74],"is":[1,29,44,215],"an":[2,145],"attractive":[3],"programming":[4],"model":[5,96],"for":[6,36,111,208],"heterogeneous":[7],"high-performance":[8],"computing":[9],"systems,":[10],"with":[11],"wide":[12],"support":[13,22],"from":[14,139],"hardware":[15],"vendors":[16],"and":[17,51,130,150,175],"significant":[18],"performance":[19,34,59,185],"portability.":[20],"To":[21],"efficient":[23],"scheduling":[24,221],"on":[25,39,119],"HPC":[26,220],"systems":[27],"it":[28],"necessary":[30],"to":[31,47,72,77,93,107,152,160,164,183,218],"perform":[32],"accurate":[33],"predictions":[35,134],"workloads":[38],"varied":[40],"compute":[41],"devices,":[42],"which":[43,55,214],"challenging":[45],"due":[46],"diverse":[48],"computation,":[49],"communication":[50],"memory":[52],"access":[53],"characteristics":[54],"result":[56],"in":[57,180],"varying":[58],"between":[60],"devices.":[61,193],"The":[62,133,194],"Architecture":[63],"Independent":[64],"Workload":[65],"Characterization":[66],"(AIWC)":[67],"tool":[68],"can":[69,171],"be":[70,172],"used":[71,92,104],"characterize":[73],"kernels":[75,117],"according":[76,163],"a":[78,86,95,112,124,209],"set":[79,113],"of":[80,98,114,127,147,157,191,203],"architecture-independent":[81],"features.":[82],"This":[83],"work":[84],"presents":[85],"methodology":[87,106,199],"where":[88],"AIWC":[89,177],"features":[90],"are":[91,135],"form":[94],"capable":[97],"predicting":[99],"accelerator":[100],"execution":[101,109,154],"times.":[102],"We":[103],"this":[105,198],"predict":[108],"times":[110],"37":[115],"computational":[116],"running":[118],"15":[120],"different":[121],"devices":[122],"representing":[123],"broad":[125],"range":[126,190],"CPU,":[128],"GPU":[129],"MIC":[131],"architectures.":[132],"highly":[136,216],"accurate,":[137],"differing":[138],"the":[140,176,181,188,204,219],"measured":[141],"experimental":[142],"run-times":[143],"by":[144],"average":[146],"only":[148],"1.2%,":[149],"correspond":[151],"actual":[153],"time":[155],"mispredictions":[156],"9":[158],"ps":[159],"1":[161],"sec":[162],"problem":[165],"size.":[166],"A":[167],"previously":[168,210],"unencountered":[169],"code":[170],"instrumented":[173],"once":[174],"metrics":[178],"embedded":[179],"kernel,":[182],"allow":[184],"prediction":[186],"across":[187],"full":[189],"modelled":[192],"results":[195],"suggest":[196],"that":[197],"supports":[200],"correct":[201],"selection":[202],"most":[205],"appropriate":[206],"device":[207],"unen-":[211],"countered":[212],"code,":[213],"relevant":[217],"setting.":[222]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2899387410","counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2024-12-13T14:09:53.510525","created_date":"2018-11-09"}