{"id":"https://openalex.org/W2032787403","doi":"https://doi.org/10.1145/1152154.1152182","title":"Fast, automatic, procedure-level performance tuning","display_name":"Fast, automatic, procedure-level performance tuning","publication_year":2006,"publication_date":"2006-09-16","ids":{"openalex":"https://openalex.org/W2032787403","doi":"https://doi.org/10.1145/1152154.1152182","mag":"2032787403"},"language":"en","primary_location":{"id":"doi:10.1145/1152154.1152182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","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/A5050338403","display_name":"Zhelong Pan","orcid":"https://orcid.org/0009-0006-6192-9608"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhelong Pan","raw_affiliation_strings":["Purdue University, West Lafayette, IN","Purdue University, School of ECE, West Lafayette, IN#TAB#"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, School of ECE, West Lafayette, IN#TAB#","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045622261","display_name":"Rudolf Eigenmann","orcid":"https://orcid.org/0000-0003-1651-827X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudolf Eigenmann","raw_affiliation_strings":["Purdue University, West Lafayette, IN","Purdue University, School of ECE, West Lafayette, IN#TAB#"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, School of ECE, West Lafayette, IN#TAB#","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050338403"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":4.2571,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94142174,"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":"173","last_page":"181"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9965999722480774,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9945999979972839,"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/pentium","display_name":"Pentium","score":0.9167193174362183},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8245136737823486},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"Performance tuning","score":0.7405582666397095},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6633199453353882},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.6523411273956299},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6270185112953186},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6005718111991882},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.5481604933738708},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5238456726074219},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.49339213967323303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.471417635679245},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4456534683704376},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43677711486816406},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41614261269569397},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34446001052856445},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24448508024215698},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1762600839138031},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12602630257606506}],"concepts":[{"id":"https://openalex.org/C46268123","wikidata":"https://www.wikidata.org/wiki/Q214314","display_name":"Pentium","level":2,"score":0.9167193174362183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245136737823486},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.7405582666397095},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6633199453353882},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.6523411273956299},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6270185112953186},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6005718111991882},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.5481604933738708},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5238456726074219},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.49339213967323303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.471417635679245},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4456534683704376},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43677711486816406},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41614261269569397},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34446001052856445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24448508024215698},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1762600839138031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12602630257606506},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":3,"locations":[{"id":"doi:10.1145/1152154.1152182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1363","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/356","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.4089","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.4089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.purdue.edu/~eigenman/reports/pact2006.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1584183132","https://openalex.org/W2052900991","https://openalex.org/W2110652915","https://openalex.org/W2118937112","https://openalex.org/W2135653967","https://openalex.org/W2135992106","https://openalex.org/W2143040477","https://openalex.org/W2144433126","https://openalex.org/W2157310776","https://openalex.org/W2170216784","https://openalex.org/W4206504442"],"related_works":["https://openalex.org/W2032192148","https://openalex.org/W2099845707","https://openalex.org/W4247967619","https://openalex.org/W2142970371","https://openalex.org/W2950655732","https://openalex.org/W2152397470","https://openalex.org/W2126913665","https://openalex.org/W4246264663","https://openalex.org/W1988661923","https://openalex.org/W2058021293"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"automated":[4],"performance":[5,148],"tuning":[6,16,56,69,86,101,130],"solution,":[7],"which":[8,38],"partitions":[9,51],"a":[10,13,52,64,105,167],"program":[11,53,143],"into":[12,54],"number":[14,107],"of":[15,23,44,63,91,108,110,115,149],"sections":[17],"and":[18,78,87],"finds":[19],"the":[20,40,61,68,80,84,88,92,116,147,162],"best":[21],"combination":[22],"compiler":[24],"options":[25],"for":[26],"each":[27,45,111],"section.":[28,46],"Our":[29,47,95],"solution":[30],"builds":[31],"on":[32,35,138,157,166],"prior":[33],"work":[34],"feedback-driven":[36],"optimization,":[37],"tuned":[39],"whole":[41],"program,":[42,81],"instead":[43,114],"key":[48],"novel":[49],"algorithm":[50],"appropriate":[55],"sections.":[57],"We":[58],"also":[59],"present":[60],"architecture":[62],"system":[65],"that":[66,76],"automates":[67],"process;":[70],"it":[71],"includes":[72],"several":[73],"pre-tuning":[74],"steps":[75],"partition":[77],"instrument":[79],"followed":[82],"by":[83,103,154],"actual":[85],"post-tuning":[89],"assembly":[90],"individuallyoptimized":[93],"parts.":[94],"system,":[96],"called":[97],"PEAK,":[98],"achieves":[99],"fast":[100],"speed":[102],"measuring":[104],"small":[106],"invocations":[109],"code":[112],"section,":[113],"whole-program":[117],"execution":[118],"time,":[119],"as":[120],"in":[121],"common":[122],"solutions.":[123],"Compared":[124],"to":[125,135],"these":[126],"solutions":[127],"PEAK":[128,145],"reduces":[129],"time":[131],"from":[132],"2.19":[133],"hours":[134],"5.85":[136],"minutes":[137],"average,":[139],"while":[140],"achieving":[141],"similar":[142],"performance.":[144],"improves":[146],"SPEC":[150],"CPU2000":[151],"FP":[152],"benchmarks":[153],"12":[155],"%":[156],"average":[158],"over":[159],"GCC":[160],"O3,":[161],"highest":[163],"optimization":[164],"level,":[165],"Pentium":[168],"IV":[169],"machine.":[170]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}