{"id":"https://openalex.org/W3002400545","doi":"https://doi.org/10.1109/tpds.2019.2958343","title":"Efficient Performance Estimation and Work-Group Size Pruning for OpenCL Kernels on GPUs","display_name":"Efficient Performance Estimation and Work-Group Size Pruning for OpenCL Kernels on GPUs","publication_year":2020,"publication_date":"2020-01-21","ids":{"openalex":"https://openalex.org/W3002400545","doi":"https://doi.org/10.1109/tpds.2019.2958343","mag":"3002400545"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2019.2958343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2958343","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/A5047495874","display_name":"Xiebing Wang","orcid":"https://orcid.org/0000-0002-4885-4959"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiebing Wang","raw_affiliation_strings":["Department of Informatics, Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4885-4959","affiliations":[{"raw_affiliation_string":"Department of Informatics, Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047215143","display_name":"Xuehai Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuehai Qian","raw_affiliation_strings":["Ming Hsieh Department of Electrical Engineering, Department of Computer Science, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical Engineering, Department of Computer Science, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Department of Informatics, Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, School of Data and Computer Science, Sun Yat-sen University, Guangzhou, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0359-7810","affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, School of Data and Computer Science, Sun Yat-sen University, Guangzhou, P. R. China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6823,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64373247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"31","issue":"5","first_page":"1089","last_page":"1106"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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":0.9980999827384949,"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":0.891264796257019},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6499486565589905},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6091166734695435},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.609054446220398},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.587405800819397},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5383326411247253},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.524456262588501},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.5176509022712708},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4189668893814087},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40693289041519165},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.24671444296836853},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1292923092842102},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10091722011566162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891264796257019},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6499486565589905},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6091166734695435},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.609054446220398},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.587405800819397},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5383326411247253},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.524456262588501},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.5176509022712708},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4189668893814087},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40693289041519165},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.24671444296836853},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1292923092842102},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10091722011566162},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/tpds.2019.2958343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2958343","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":[],"awards":[{"id":"https://openalex.org/G137388161","display_name":null,"funder_award_id":"NSF-CNS-1717984","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2562865718","display_name":null,"funder_award_id":"NSF-CCF-1750656","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3323652710","display_name":null,"funder_award_id":"NSF-CCF-1717754","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5615208386","display_name":null,"funder_award_id":"201506270152","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G6608418980","display_name":null,"funder_award_id":"NSF-CCF-1657333","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7955115152","display_name":"\u6df7\u5408\u5173\u952e\u7ea7\u7cfb\u7edf\u7ebf\u4e0a\u81ea\u9002\u5e94\u8d44\u6e90\u7ba1\u7406\u53ca\u8c03\u5ea6\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61872393","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W799594534","https://openalex.org/W1573046885","https://openalex.org/W1601084247","https://openalex.org/W1790519466","https://openalex.org/W1904624772","https://openalex.org/W1965214876","https://openalex.org/W1979527452","https://openalex.org/W1990832096","https://openalex.org/W1991056822","https://openalex.org/W1994272002","https://openalex.org/W2004618348","https://openalex.org/W2038666141","https://openalex.org/W2045271686","https://openalex.org/W2048441570","https://openalex.org/W2062368747","https://openalex.org/W2080592089","https://openalex.org/W2084660366","https://openalex.org/W2100218206","https://openalex.org/W2101111919","https://openalex.org/W2103316736","https://openalex.org/W2105545110","https://openalex.org/W2107483876","https://openalex.org/W2110195531","https://openalex.org/W2112029501","https://openalex.org/W2113282196","https://openalex.org/W2122297544","https://openalex.org/W2128046183","https://openalex.org/W2130336316","https://openalex.org/W2151195685","https://openalex.org/W2153185479","https://openalex.org/W2153492376","https://openalex.org/W2154786353","https://openalex.org/W2163687928","https://openalex.org/W2167334577","https://openalex.org/W2169559170","https://openalex.org/W2170059648","https://openalex.org/W2203203427","https://openalex.org/W2234148183","https://openalex.org/W2239144794","https://openalex.org/W2286635931","https://openalex.org/W2314321304","https://openalex.org/W2554796001","https://openalex.org/W2559932280","https://openalex.org/W2583218561","https://openalex.org/W2619500264","https://openalex.org/W2757759139","https://openalex.org/W2758013740","https://openalex.org/W2758264231","https://openalex.org/W2930604630","https://openalex.org/W2963926583","https://openalex.org/W2997701623","https://openalex.org/W3103983137","https://openalex.org/W3105204543","https://openalex.org/W3127459981","https://openalex.org/W3137551601","https://openalex.org/W3152199537","https://openalex.org/W4241847236","https://openalex.org/W4246166885","https://openalex.org/W4250047567","https://openalex.org/W6675743430"],"related_works":["https://openalex.org/W3013976982","https://openalex.org/W2982613029","https://openalex.org/W2794923745","https://openalex.org/W2095501793","https://openalex.org/W2086643394","https://openalex.org/W1678662003","https://openalex.org/W3015799701","https://openalex.org/W4250047567","https://openalex.org/W1981557297","https://openalex.org/W1997955449"],"abstract_inverted_index":{"Graphic":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"play":[4],"a":[5,39,57,75,95,111],"vital":[6],"role":[7],"in":[8],"state-of-the-art":[9],"high-performance":[10],"scientific":[11],"computing":[12],"realm":[13],"and":[14,53,63,83,110,147,163,194],"research":[15],"work":[16],"towards":[17],"its":[18],"performance":[19,27,61,81,162,186],"analysis":[20,133],"is":[21,134],"crucial":[22],"but":[23],"nontrivial.":[24],"Extant":[25],"GPU":[26,36,67],"models":[28],"are":[29],"far":[30],"from":[31,105],"practical":[32],"use,":[33],"while":[34],"fine-grained":[35],"simulation":[37],"requires":[38],"considerably":[40],"large":[41],"time":[42],"cost.":[43],"Moreover,":[44],"massive":[45],"amounts":[46],"of":[47,65,87,191,203],"designs":[48],"with":[49,143,187],"various":[50],"program":[51,157,197],"inputs":[52],"parameter":[54],"settings":[55],"pose":[56],"challenge":[58],"for":[59,78],"efficient":[60,80],"estimation":[62,82],"tuning":[64],"parallel":[66],"applications.":[68],"To":[69],"this":[70,72],"end,":[71],"article":[73],"presents":[74],"hybrid":[76],"framework":[77,93,152,181],"the":[79,101,106,117,123,127,139,161,165,180,184,196],"work-group":[84,141],"size":[85],"pruning":[86],"OpenCL":[88],"workloads":[89],"on":[90,171],"GPUs.":[91],"The":[92,150],"contains":[94],"static":[96],"module":[97,113],"used":[98,114],"to":[99,115,121,136,159],"extract":[100],"kernel":[102,118],"execution":[103,119,145],"trace":[104],"high-level":[107],"source":[108],"code":[109],"dynamical":[112],"mimic":[116],"flow":[120],"estimate":[122,160],"runtime":[124,185],"performance.":[125],"For":[126],"design":[128,198],"space":[129,199],"pruning,":[130],"an":[131,188,201],"extra":[132],"performed":[135],"filter":[137],"out":[138],"redundant":[140],"sizes":[142],"duplicated":[144],"traces":[146],"inferior":[148],"pipelines.":[149],"proposed":[151],"does":[153],"not":[154],"require":[155],"any":[156],"runs":[158],"find":[164],"optimal":[166],"or":[167],"near-optimal":[168],"designs.":[169],"Experiments":[170],"four":[172],"Commercial":[173],"Off-The-Shelf":[174],"(COTS)":[175],"Nvidia":[176],"GPUs":[177],"show":[178],"that":[179],"can":[182],"predict":[183],"average":[189,202],"error":[190],"17.04":[192],"percent":[193],"reduce":[195],"by":[200],"78.47":[204],"percent.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}