{"id":"https://openalex.org/W2971086374","doi":"https://doi.org/10.1109/tpds.2019.2937295","title":"Efficient and Portable Workgroup Size Tuning","display_name":"Efficient and Portable Workgroup Size Tuning","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2971086374","doi":"https://doi.org/10.1109/tpds.2019.2937295","mag":"2971086374"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2019.2937295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2937295","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5022361454","display_name":"Chia-Lin Yu","orcid":"https://orcid.org/0000-0003-4530-3665"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chia-Lin Yu","raw_affiliation_strings":["Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011677008","display_name":"Shiao\u2010Li Tsao","orcid":"https://orcid.org/0000-0002-7097-9045"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shiao-Li Tsao","raw_affiliation_strings":["Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022361454"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.18,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49201408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":"2","first_page":"455","last_page":"469"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9940000176429749,"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":0.9940000176429749,"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/workgroup","display_name":"Workgroup","score":0.967909574508667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8570401668548584},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8142112493515015},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6900687217712402},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6708637475967407},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5482542514801025},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.508873701095581},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42187532782554626},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3871561884880066},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35818731784820557},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17340314388275146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13257816433906555}],"concepts":[{"id":"https://openalex.org/C95423123","wikidata":"https://www.wikidata.org/wiki/Q622178","display_name":"Workgroup","level":2,"score":0.967909574508667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8570401668548584},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8142112493515015},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6900687217712402},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6708637475967407},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5482542514801025},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.508873701095581},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42187532782554626},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3871561884880066},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35818731784820557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17340314388275146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13257816433906555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2019.2937295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2937295","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1048005391","display_name":null,"funder_award_id":"108-2218-E-009-052-","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G5865035748","display_name":null,"funder_award_id":"107-2622-8-009-019-TA","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G783665914","display_name":null,"funder_award_id":"108-2321-B-009-004-","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G8838921246","display_name":null,"funder_award_id":"107-2218-E-009-001","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W192356505","https://openalex.org/W1790519466","https://openalex.org/W1904624772","https://openalex.org/W1968667899","https://openalex.org/W1972541532","https://openalex.org/W1978236660","https://openalex.org/W1984222112","https://openalex.org/W1987823408","https://openalex.org/W2016618963","https://openalex.org/W2029822446","https://openalex.org/W2033486618","https://openalex.org/W2033597569","https://openalex.org/W2038666141","https://openalex.org/W2045128810","https://openalex.org/W2062368747","https://openalex.org/W2063099138","https://openalex.org/W2080592089","https://openalex.org/W2099891946","https://openalex.org/W2101628736","https://openalex.org/W2110195531","https://openalex.org/W2130336316","https://openalex.org/W2142769604","https://openalex.org/W2144011502","https://openalex.org/W2144264070","https://openalex.org/W2159441376","https://openalex.org/W2167334577","https://openalex.org/W2169559170","https://openalex.org/W2222053960","https://openalex.org/W2273440736","https://openalex.org/W2293015622","https://openalex.org/W2758013740","https://openalex.org/W2897830517","https://openalex.org/W2899387410","https://openalex.org/W2964279072","https://openalex.org/W2997701623","https://openalex.org/W3005101099","https://openalex.org/W3006997840","https://openalex.org/W3103983137","https://openalex.org/W3105204543","https://openalex.org/W3136856850","https://openalex.org/W4250047567","https://openalex.org/W6607730395","https://openalex.org/W6644912577","https://openalex.org/W6675256520","https://openalex.org/W6689031217","https://openalex.org/W6694513646","https://openalex.org/W6755919064"],"related_works":["https://openalex.org/W624647371","https://openalex.org/W2168235705","https://openalex.org/W3149960746","https://openalex.org/W3130903168","https://openalex.org/W2096268347","https://openalex.org/W2156026376","https://openalex.org/W385597202","https://openalex.org/W1559015588","https://openalex.org/W2392746182","https://openalex.org/W2016659453"],"abstract_inverted_index":{"The":[0,122],"performance":[1,23,172],"of":[2,60,64,98,112,152,173],"an":[3],"OpenCL":[4,129],"program":[5],"is":[6,125],"strongly":[7],"influenced":[8],"by":[9],"both":[10,135],"hardware":[11,99],"and":[12,53,68,80,131,137,175],"software":[13],"attributes.":[14],"To":[15],"achieve":[16,170],"superior":[17],"performance,":[18],"developers":[19],"may":[20],"leverage":[21],"automatic":[22],"tuning":[24,41,78],"techniques":[25],"to":[26,85,120],"determine":[27],"the":[28,32,61,75,87,92,103,110,153,161,165,181],"optimal":[29,182],"parameters":[30,100],"on":[31,127,157],"target":[33,45,113],"device.":[34],"Although":[35],"existing":[36],"approaches":[37],"have":[38],"shown":[39],"promising":[40],"results":[42,140],"in":[43],"their":[44],"scenarios,":[46],"other":[47],"requirements":[48],"such":[49],"as":[50],"efficiency,":[51],"portability,":[52],"usability":[54],"should":[55],"also":[56],"be":[57,107],"considered":[58],"because":[59],"rapid":[62],"growth":[63],"heterogeneous":[65],"computing":[66],"applications":[67],"platforms.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"re-examine":[74],"workgroup":[76,155,162,183],"size":[77,163],"problem":[79],"propose":[81],"a":[82,96],"novel":[83],"approach":[84,105,124,147],"meet":[86],"aforementioned":[88],"requirements.":[89],"We":[90],"abstract":[91],"architectural":[93],"details":[94],"into":[95],"set":[97],"so":[101],"that":[102],"proposed":[104,123],"can":[106,169],"applied":[108],"without":[109],"presence":[111],"devices,":[114,133],"which":[115],"makes":[116],"it":[117],"more":[118],"accessible":[119],"developers.":[121],"evaluated":[126],"20":[128],"kernels":[130],"six":[132],"including":[134],"CPUs":[136],"GPUs.":[138],"Experimental":[139],"demonstrate":[141],"that,":[142],"with":[143,180],"negligible":[144],"overhead,":[145],"our":[146],"filters":[148],"out":[149],"88.6":[150],"percent":[151],"possible":[154],"sizes":[156],"average.":[158],"Among":[159],"all":[160],"candidates,":[164],"bestand":[166],"worst-performing":[167],"candidates":[168],"average":[171],"95.5":[174],"92.1":[176],"percent,":[177],"respectively,":[178],"compared":[179],"size.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}