{"id":"https://openalex.org/W2030859425","doi":"https://doi.org/10.1145/1810085.1810120","title":"Speeding up Nek5000 with autotuning and specialization","display_name":"Speeding up Nek5000 with autotuning and specialization","publication_year":2010,"publication_date":"2010-06-02","ids":{"openalex":"https://openalex.org/W2030859425","doi":"https://doi.org/10.1145/1810085.1810120","mag":"2030859425"},"language":"en","primary_location":{"id":"doi:10.1145/1810085.1810120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5023732376","display_name":"Jaewook Shin","orcid":"https://orcid.org/0000-0002-0342-1834"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaewook Shin","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary W. Hall","raw_affiliation_strings":["University of Utah, Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057351225","display_name":"Jacqueline Chame","orcid":null},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacqueline Chame","raw_affiliation_strings":["USC / ISI, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC / ISI, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103956520","display_name":"Chun Chen","orcid":"https://orcid.org/0009-0005-8416-9587"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun Chen","raw_affiliation_strings":["University of Utah, Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081088881","display_name":"Paul Fischer","orcid":"https://orcid.org/0000-0002-6506-4502"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul F. Fischer","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067040957","display_name":"Paul Hovland","orcid":"https://orcid.org/0000-0002-0907-2567"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul D. Hovland","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023732376"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":3.285,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92372803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10232","display_name":"Optical Network Technologies","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8664267063140869},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7945505380630493},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7389177083969116},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5491481423377991},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.5316187739372253},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"Performance tuning","score":0.527299165725708},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5259870886802673},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.484609454870224},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4825684130191803},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.46058979630470276},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45974260568618774},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4283914864063263},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.42520010471343994},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3786289393901825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664267063140869},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7945505380630493},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7389177083969116},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5491481423377991},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.5316187739372253},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.527299165725708},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5259870886802673},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.484609454870224},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4825684130191803},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.46058979630470276},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45974260568618774},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4283914864063263},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.42520010471343994},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3786289393901825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1810085.1810120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.5313","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.5313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/%7Ejaewook/papers/ICS_2010_0115.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.607.5413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.607.5413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/uploads/cels/papers/P1705A.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2819736101","display_name":null,"funder_award_id":"DE-AC02-06CH11357DE-SC00003777","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G367743051","display_name":null,"funder_award_id":"DE-AC02-06CH11357DE-SC00003777","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"}],"funders":[{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W190064633","https://openalex.org/W1513509033","https://openalex.org/W1580643653","https://openalex.org/W1631114303","https://openalex.org/W1779740778","https://openalex.org/W1793062632","https://openalex.org/W1965351873","https://openalex.org/W1972209410","https://openalex.org/W1979677378","https://openalex.org/W2007451249","https://openalex.org/W2008968423","https://openalex.org/W2031775479","https://openalex.org/W2047352485","https://openalex.org/W2047656763","https://openalex.org/W2099059741","https://openalex.org/W2099625934","https://openalex.org/W2101924328","https://openalex.org/W2104736438","https://openalex.org/W2111334029","https://openalex.org/W2112502633","https://openalex.org/W2118031182","https://openalex.org/W2121546953","https://openalex.org/W2135653967","https://openalex.org/W2136952590","https://openalex.org/W2139143992","https://openalex.org/W2158626113","https://openalex.org/W2252549844","https://openalex.org/W2314944927","https://openalex.org/W2969262004","https://openalex.org/W4233894383","https://openalex.org/W4243796884","https://openalex.org/W6652485469"],"related_works":["https://openalex.org/W2391861012","https://openalex.org/W2488336788","https://openalex.org/W1933077055","https://openalex.org/W2058021293","https://openalex.org/W2091772480","https://openalex.org/W1975914334","https://openalex.org/W2140163540","https://openalex.org/W2044280736","https://openalex.org/W4214517608","https://openalex.org/W4221075948"],"abstract_inverted_index":{"Autotuning":[0],"technology":[1],"has":[2],"emerged":[3],"recently":[4],"as":[5],"a":[6,14,24,32,65],"systematic":[7],"process":[8],"for":[9,23,50,83],"evaluating":[10],"alternative":[11],"implementations":[12],"of":[13,35,55,72,139,151],"computation,":[15],"in":[16],"order":[17],"to":[18,31,61,141],"select":[19],"the":[20,132,144,152],"best-performing":[21],"solution":[22],"particular":[25,33],"architecture.":[26],"Specialization":[27],"optimizes":[28],"code":[29],"customized":[30],"class":[34],"input":[36],"data":[37,52],"set.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,91],"demonstrate":[43,122],"how":[44],"compiler-based":[45],"autotuning":[46,88],"that":[47,116],"incorporates":[48],"specialization":[49],"expected":[51],"set":[53],"sizes":[54],"key":[56],"computations":[57],"can":[58,92],"be":[59],"used":[60],"speed":[62],"up":[63,140],"Nek5000,":[64],"spectral-element":[66],"code.":[67],"Nek5000":[68],"makes":[69],"heavy":[70],"use":[71],"what":[73],"are":[74,109],"effectively":[75],"Basic":[76],"Linear":[77],"Algebra":[78],"Subroutine":[79],"(BLAS)":[80],"calls,":[81],"but":[82],"very":[84],"small":[85],"matrices.":[86],"Through":[87],"and":[89,103,137],"specialization,":[90],"achieve":[93],"significant":[94],"performance":[95,107,126],"gains":[96,108,127],"over":[97,131],"hand-tuned":[98],"libraries":[99],"(e.g.,":[100],"Goto,":[101],"ATLAS,":[102],"ACML":[104],"BLAS).":[105],"Additional":[106],"obtained":[110],"from":[111],"using":[112],"higher-level":[113],"compiler":[114],"optimizations":[115],"aggregate":[117],"multiple":[118],"BLAS":[119],"calls.":[120],"We":[121],"more":[123],"than":[124],"2.2X":[125],"on":[128,143,148],"an":[129],"Opteron":[130],"original":[133],"manually":[134],"tuned":[135],"implementation,":[136],"speedups":[138],"1.26X":[142],"entire":[145],"application":[146],"running":[147],"256":[149],"nodes":[150],"Cray":[153],"XT5":[154],"Jaguar":[155],"system":[156],"at":[157],"Oak":[158],"Ridge.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}