{"id":"https://openalex.org/W2786865931","doi":"https://doi.org/10.1109/hpcc-smartcity-dss.2017.58","title":"Automatically Selecting Profitable Thread Block Sizes for Accelerated Kernels","display_name":"Automatically Selecting Profitable Thread Block Sizes for Accelerated Kernels","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786865931","doi":"https://doi.org/10.1109/hpcc-smartcity-dss.2017.58","mag":"2786865931"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc-smartcity-dss.2017.58","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058860316","display_name":"Tiffany A. Connors","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"funder","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiffany A. Connors","raw_affiliation_strings":["Computer Science Dept, Texas State University, San Marcos, TX"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept, Texas State University, San Marcos, TX","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112322145","display_name":"Apan Qasem","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"funder","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apan Qasem","raw_affiliation_strings":["Computer Science Dept, Texas State University, San Marcos, TX"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept, Texas State University, San Marcos, TX","institution_ids":["https://openalex.org/I13511017"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.512,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":9,"citation_normalized_percentile":{"value":0.776435,"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":"442","last_page":"449"},"is_retracted":false,"is_paratext":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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993,"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":0.999,"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/block-size","display_name":"Block size","score":0.75142574},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5401285},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4180641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78809893},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.75142574},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6748089},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5401285},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.46949556},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4558363},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45038605},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.43671143},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4180641},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26053864},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.094649225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09097925},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc-smartcity-dss.2017.58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.57}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W1894701209","https://openalex.org/W1978236660","https://openalex.org/W1994256395","https://openalex.org/W2005232436","https://openalex.org/W2014244478","https://openalex.org/W2027177485","https://openalex.org/W2032136713","https://openalex.org/W2038666141","https://openalex.org/W2067479799","https://openalex.org/W2081984813","https://openalex.org/W2089806214","https://openalex.org/W2095127626","https://openalex.org/W2142079700","https://openalex.org/W2149040884","https://openalex.org/W2156560068","https://openalex.org/W2156803948","https://openalex.org/W2166879008","https://openalex.org/W2180890913","https://openalex.org/W2563030477","https://openalex.org/W3100760381","https://openalex.org/W3136856850"],"related_works":["https://openalex.org/W654418082","https://openalex.org/W4237177615","https://openalex.org/W2972896947","https://openalex.org/W2379153735","https://openalex.org/W2355105570","https://openalex.org/W2170146914","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W2046172023","https://openalex.org/W2015567081"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"provide":[4,61,143],"high":[5],"performance":[6,65,140,150],"at":[7],"low":[8],"power":[9],"consumption":[10],"as":[11,13],"long":[12],"resources":[14],"are":[15],"well":[16],"utilized.":[17],"Thread":[18],"block":[19,44,56,106,129],"size":[20,45,112],"is":[21,30,40,73,90,100,113],"one":[22],"factor":[23],"in":[24,76],"determining":[25],"a":[26,31],"kernel's":[27],"occupancy,":[28,63],"which":[29],"metric":[32],"for":[33,87,149],"measuring":[34],"GPU":[35],"utilization.":[36],"A":[37],"general":[38],"guideline":[39],"to":[41,48,104,125],"find":[42],"the":[43,49,101,110,146],"that":[46,134],"leads":[47],"highest":[50,62],"occupancy.":[51],"However,":[52],"many":[53],"combinations":[54],"of":[55,82],"and":[57,92],"grid":[58],"sizes":[59],"can":[60,66,142],"but":[64,108],"vary":[67],"significantly":[68],"between":[69,152],"different":[70,80,153],"configurations.":[71,154],"This":[72],"because":[74],"variation":[75],"thread":[77,93],"structure":[78,94],"yields":[79],"utilization":[81],"hardware":[83],"resources.":[84],"Thus,":[85],"optimizing":[86],"occupancy":[88],"alone":[89],"insufficient":[91],"must":[95],"also":[96],"be":[97],"considered.":[98],"It":[99],"programmer's":[102],"responsibility":[103],"set":[105],"size,":[107],"selecting":[109],"right":[111],"not":[114],"always":[115],"intuitive.":[116],"In":[117],"this":[118],"paper,":[119],"we":[120,132],"propose":[121],"using":[122],"machine":[123,135],"learning":[124,136],"automatically":[126],"select":[127],"profitable":[128],"sizes.":[130],"Additionally,":[131],"show":[133],"techniques":[137],"coupled":[138],"with":[139],"counters":[141],"insight":[144],"into":[145],"underlying":[147],"reasons":[148],"variance":[151]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2786865931","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-03-04T00:42:54.260135","created_date":"2018-02-23"}