{"id":"https://openalex.org/W2951815798","doi":"https://doi.org/10.1145/3330345.3330377","title":"Efficient hierarchical online-autotuning","display_name":"Efficient hierarchical online-autotuning","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2951815798","doi":"https://doi.org/10.1145/3330345.3330377","mag":"2951815798"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-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/A5087085639","display_name":"Philip Pfaffe","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Philip Pfaffe","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055618037","display_name":"Tobias Grosser","orcid":"https://orcid.org/0000-0003-3874-6003"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tobias Grosser","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053838170","display_name":"Martin Tillmann","orcid":"https://orcid.org/0000-0001-7172-8398"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Tillmann","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087085639"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":3.13,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91834073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"354","last_page":"366"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9883000254631042,"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":0.9876000285148621,"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":0.8587298393249512},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7420971393585205},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6702837944030762},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.598704993724823},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5278133153915405},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"Performance tuning","score":0.4666716158390045},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4477159082889557},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44142091274261475},{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.4391424357891083},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36747241020202637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35209235548973083},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33657485246658325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587298393249512},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7420971393585205},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6702837944030762},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.598704993724823},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5278133153915405},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.4666716158390045},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4477159082889557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44142091274261475},{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.4391424357891083},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36747241020202637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35209235548973083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33657485246658325},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330345.3330377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6692108190","display_name":null,"funder_award_id":"299215159","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320314786","display_name":"Xilinx","ror":"https://ror.org/01rb7bk56"},{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W95852487","https://openalex.org/W243738321","https://openalex.org/W288065879","https://openalex.org/W1191262899","https://openalex.org/W1525215176","https://openalex.org/W1529511812","https://openalex.org/W1547909858","https://openalex.org/W1562841074","https://openalex.org/W1565751843","https://openalex.org/W1583652109","https://openalex.org/W1782174992","https://openalex.org/W1964031104","https://openalex.org/W1968197401","https://openalex.org/W2000873501","https://openalex.org/W2007451249","https://openalex.org/W2009488259","https://openalex.org/W2020505145","https://openalex.org/W2033088400","https://openalex.org/W2033485113","https://openalex.org/W2055312318","https://openalex.org/W2065705265","https://openalex.org/W2069230794","https://openalex.org/W2077143534","https://openalex.org/W2078845975","https://openalex.org/W2084917734","https://openalex.org/W2098220211","https://openalex.org/W2099059741","https://openalex.org/W2100218206","https://openalex.org/W2104324382","https://openalex.org/W2108737583","https://openalex.org/W2123680107","https://openalex.org/W2135653967","https://openalex.org/W2136628731","https://openalex.org/W2140707050","https://openalex.org/W2142079700","https://openalex.org/W2147505032","https://openalex.org/W2147543317","https://openalex.org/W2148542244","https://openalex.org/W2158626113","https://openalex.org/W2166536280","https://openalex.org/W2166906890","https://openalex.org/W2171074980","https://openalex.org/W2346144740","https://openalex.org/W2397454561","https://openalex.org/W2516525699","https://openalex.org/W2520810317","https://openalex.org/W2594730095","https://openalex.org/W2605317797","https://openalex.org/W2725201101","https://openalex.org/W2728600909","https://openalex.org/W2752451204","https://openalex.org/W2772612468","https://openalex.org/W2779253217","https://openalex.org/W2786202634","https://openalex.org/W2898885257","https://openalex.org/W3113163436","https://openalex.org/W3146578712","https://openalex.org/W4234960108","https://openalex.org/W4236293132","https://openalex.org/W4245394119","https://openalex.org/W4247136841","https://openalex.org/W4248073216","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2154107929","https://openalex.org/W4290057712","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2168846948","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2778498407","https://openalex.org/W2140163540","https://openalex.org/W2115197825"],"abstract_inverted_index":{"Identifying":[0],"the":[1,20,25,97,101,129,150,167,171,191],"(near)":[2],"optimal":[3],"program":[4],"variants":[5],"an":[6,36],"optimizing":[7],"and":[8,44,100,115,119,165],"parallelizing":[9,143],"compiler":[10,144],"should":[11,38],"generate":[12],"is":[13,19,61,161,174],"known":[14,68],"to":[15,23,33,93,105,124,181,184],"be":[16,34,46,74],"difficult.":[17],"Autotuning":[18],"best":[21],"solution":[22],"navigate":[24],"often":[26],"high-dimensional":[27],"space":[28,99,131],"of":[29,50,135,152,170,179,193],"possible":[30],"options.":[31],"However,":[32],"practical":[35],"autotuner":[37],"(a)":[39],"have":[40],"high":[41],"convergence":[42,59,81,107,168],"speed":[43,60,108,169],"(b)":[45],"robust":[47],"in":[48,80,96,117],"face":[49],"varying":[51],"inputs.":[52],"Current":[53],"techniques":[54],"for":[55,67,145],"offline":[56],"tuning,":[57],"where":[58],"less":[62],"important,":[63],"provide":[64],"solutions":[65],"only":[66],"inputs,":[69],"whereas":[70],"online":[71,110],"tuning":[72,103,172,188],"can":[73],"input":[75],"sensitive":[76],"but":[77],"currently":[78],"lacks":[79],"speed.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,127,147,189],"present":[87],"hierarchical":[88,187],"online-autotuning,":[89],"a":[90,141,153,177],"novel":[91],"technique":[92],"exploit":[94],"structure":[95],"search":[98,130],"underlying":[102],"problem":[104],"increase":[106],"during":[109],"tuning.":[111],"By":[112],"modeling":[113],"symmetries":[114],"redundancies":[116],"configurations":[118],"by":[120,133,163,176],"exploiting":[121],"domain":[122],"knowledge":[123],"predict":[125],"performance":[126,151],"reduce":[128],"size":[132],"orders":[134],"magnitudes.":[136],"Combining":[137],"our":[138],"tuner":[139],"with":[140,158],"polyhedral":[142],"GPUs,":[146],"show":[148],"that":[149,166],"GEMM":[154],"GPU":[155],"kernel":[156],"generated":[157],"default":[159],"parameters":[160],"increased":[162,175],"6\u00d7":[164],"process":[173],"factor":[178],"up":[180],"1.7":[182],"compared":[183],"OpenTuner.":[185],"With":[186],"make":[190],"deployment":[192],"always-on":[194],"online-autotuning":[195],"practical.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}