{"id":"https://openalex.org/W2962952032","doi":"https://doi.org/10.1145/3337821.3337908","title":"Massively Parallel Automated Software Tuning","display_name":"Massively Parallel Automated Software Tuning","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2962952032","doi":"https://doi.org/10.1145/3337821.3337908","mag":"2962952032"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337908","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337908","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062373552","display_name":"Yaohung M. Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaohung M. Tsai","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Gates","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077268543","display_name":"Ahmad Abdelfattah","orcid":"https://orcid.org/0000-0001-5054-4784"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Abdelfattah","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9979000091552734,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008962869644165},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.7346957921981812},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.646223247051239},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6245437860488892},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5813775658607483},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5201500058174133},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4884132742881775},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4662308692932129},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4640803337097168},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.45025622844696045},{"id":"https://openalex.org/keywords/posix-threads","display_name":"POSIX Threads","score":0.43840503692626953},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3336944580078125},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3324720859527588},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33128684759140015},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10732835531234741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008962869644165},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.7346957921981812},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.646223247051239},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6245437860488892},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5813775658607483},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5201500058174133},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4884132742881775},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4662308692932129},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4640803337097168},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.45025622844696045},{"id":"https://openalex.org/C41138395","wikidata":"https://www.wikidata.org/wiki/Q928112","display_name":"POSIX Threads","level":3,"score":0.43840503692626953},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3336944580078125},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3324720859527588},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33128684759140015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10732835531234741},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"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:10.1145/3337821.3337908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337908","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3337821.3337908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337908","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5049692813","display_name":"SI2-SSE: BONSAI: An Open Software Infrastructure for Parallel Autotuning of Computational Kernels","funder_award_id":"1642441","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962952032.pdf","grobid_xml":"https://content.openalex.org/works/W2962952032.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1947563839","https://openalex.org/W1961470747","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1978642402","https://openalex.org/W2096070062","https://openalex.org/W2099021415","https://openalex.org/W2099625934","https://openalex.org/W2100218206","https://openalex.org/W2104512032","https://openalex.org/W2118746782","https://openalex.org/W2136628731","https://openalex.org/W2163491234","https://openalex.org/W2169631286","https://openalex.org/W2500595894","https://openalex.org/W2885184702","https://openalex.org/W2990714382","https://openalex.org/W4237885920","https://openalex.org/W4243796884","https://openalex.org/W4251235123"],"related_works":["https://openalex.org/W2115561485","https://openalex.org/W2488080660","https://openalex.org/W4294310504","https://openalex.org/W1985089255","https://openalex.org/W2010970156","https://openalex.org/W2153202644","https://openalex.org/W2338363223","https://openalex.org/W2105895556","https://openalex.org/W2377593213","https://openalex.org/W2733115356"],"abstract_inverted_index":{"This":[0,72],"article":[1],"presents":[2],"an":[3],"implementation":[4],"of":[5,13,28,40,60,80,88],"a":[6],"distributed":[7],"autotuning":[8,42],"engine":[9],"developed":[10],"as":[11],"part":[12],"the":[14,38,76,81,85,89,102],"Bench-testing":[15],"OpenN":[16],"Software":[17],"Autotuning":[18],"Infrastructure":[19],"project.":[20],"The":[21,48],"system":[22,82],"is":[23],"geared":[24],"towards":[25],"performance":[26,93],"optimization":[27],"computational":[29],"kernels":[30],"for":[31,37,62],"graphics":[32],"processing":[33],"units,":[34],"and":[35,57,65,83,101],"allows":[36],"deployment":[39],"vast":[41],"sweeps":[43],"to":[44,54,69],"massively":[45],"parallel":[46,63],"machines.":[47],"software":[49],"implements":[50],"dynamic":[51],"work":[52],"scheduling":[53],"distributed-memory":[55],"resources":[56],"takes":[58],"advantage":[59],"multithreading":[61],"compilation":[64],"dispatches":[66],"kernel":[67],"launches":[68],"multiple":[70],"accelerators.":[71],"paper":[73],"lays":[74],"out":[75],"main":[77],"design":[78],"principles":[79],"discusses":[84],"basic":[86],"mechanics":[87],"initial":[90],"implementation.":[91],"Preliminary":[92],"results":[94],"are":[95,99,105],"presented,":[96],"encountered":[97],"challenges":[98],"discussed,":[100],"future":[103],"directions":[104],"outlined.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}