{"id":"https://openalex.org/W2018931757","doi":"https://doi.org/10.1145/2304576.2304584","title":"Fast loop-level data dependence profiling","display_name":"Fast loop-level data dependence profiling","publication_year":2012,"publication_date":"2012-06-25","ids":{"openalex":"https://openalex.org/W2018931757","doi":"https://doi.org/10.1145/2304576.2304584","mag":"2018931757"},"language":"en","primary_location":{"id":"doi:10.1145/2304576.2304584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th 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/A5110344672","display_name":"Hongtao Yu","orcid":"https://orcid.org/0000-0002-1426-8580"},"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":"Hongtao Yu","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337924","display_name":"Zhiyuan Li","orcid":"https://orcid.org/0000-0001-8446-0319"},"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":"Zhiyuan Li","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110344672"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":3.1906,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91558928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9990000128746033,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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/profiling","display_name":"Profiling (computer programming)","score":0.8287050127983093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8238579630851746},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.581863284111023},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.577765703201294},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.536860466003418},{"id":"https://openalex.org/keywords/alias","display_name":"Alias","score":0.5032951235771179},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.45124030113220215},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41405871510505676},{"id":"https://openalex.org/keywords/reentrancy","display_name":"Reentrancy","score":0.4133448600769043},{"id":"https://openalex.org/keywords/dependence-analysis","display_name":"Dependence analysis","score":0.41191551089286804},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32923775911331177},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18597936630249023},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17302808165550232}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8287050127983093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238579630851746},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.581863284111023},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.577765703201294},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.536860466003418},{"id":"https://openalex.org/C46681722","wikidata":"https://www.wikidata.org/wiki/Q4725589","display_name":"Alias","level":2,"score":0.5032951235771179},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.45124030113220215},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41405871510505676},{"id":"https://openalex.org/C161406801","wikidata":"https://www.wikidata.org/wiki/Q963635","display_name":"Reentrancy","level":2,"score":0.4133448600769043},{"id":"https://openalex.org/C27390822","wikidata":"https://www.wikidata.org/wiki/Q320724","display_name":"Dependence analysis","level":2,"score":0.41191551089286804},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32923775911331177},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18597936630249023},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17302808165550232}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2304576.2304584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W190163119","https://openalex.org/W1494930385","https://openalex.org/W1550371161","https://openalex.org/W1596439539","https://openalex.org/W1965604953","https://openalex.org/W1999517284","https://openalex.org/W2008039167","https://openalex.org/W2011039300","https://openalex.org/W2021468834","https://openalex.org/W2028240990","https://openalex.org/W2034567497","https://openalex.org/W2038687965","https://openalex.org/W2048115596","https://openalex.org/W2052497937","https://openalex.org/W2053155247","https://openalex.org/W2056579078","https://openalex.org/W2102058849","https://openalex.org/W2108112890","https://openalex.org/W2115920894","https://openalex.org/W2121319784","https://openalex.org/W2125340270","https://openalex.org/W2129370612","https://openalex.org/W2131135493","https://openalex.org/W2135531618","https://openalex.org/W2137735282","https://openalex.org/W2144465510","https://openalex.org/W2147801215","https://openalex.org/W2149237601","https://openalex.org/W2151307463","https://openalex.org/W2152960795","https://openalex.org/W2153510998","https://openalex.org/W2156858199","https://openalex.org/W2159055648","https://openalex.org/W2531563875","https://openalex.org/W4206818640","https://openalex.org/W4230415451","https://openalex.org/W4239813889","https://openalex.org/W4254615111","https://openalex.org/W4256238177"],"related_works":["https://openalex.org/W2153100729","https://openalex.org/W2094788990","https://openalex.org/W4302423001","https://openalex.org/W4236039393","https://openalex.org/W1732806635","https://openalex.org/W2581448187","https://openalex.org/W3134809298","https://openalex.org/W56552447","https://openalex.org/W2185102111","https://openalex.org/W2112502633"],"abstract_inverted_index":{"Execution-driven":[0],"data":[1,17,71,88,179],"dependence":[2,18,22,44,72,103,122,137,150,180],"profiling":[3,23,45,114,126,157,198],"has":[4],"gained":[5],"significant":[6],"interest":[7],"as":[8],"a":[9,120],"tool":[10],"to":[11,67,146,212],"compensate":[12],"the":[13,87,91,108,156,177,183,192,197],"weakness":[14],"of":[15,203],"static":[16],"analysis.":[19],"Although":[20],"such":[21,94],"is":[24,127],"valid":[25],"for":[26,38,102,129,205],"specific":[27],"inputs":[28],"only,":[29],"its":[30,56],"result":[31],"can":[32,46,98,139,164,221],"be":[33,99,140,165,223],"used":[34],"in":[35,90,112,167],"many":[36],"ways":[37],"program":[39,93],"parallelization.":[40,134],"Unfortunately,":[41],"traditional":[42],"hash-based":[43],"take":[47],"tremendous":[48],"memory":[49,84,96,193],"and":[50,78,133,195],"machine":[51],"time,":[52],"which":[53,171],"severely":[54],"limits":[55],"practical":[57],"use.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,117],"propose":[63],"new":[64],"compiler-based":[65],"techniques":[66,189],"perform":[68],"fast":[69],"loop-level":[70,130],"profiling.":[73],"Firstly,":[74],"using":[75],"type":[76],"consistency":[77],"alias":[79],"information,":[80],"our":[81,153],"compiler":[82,154],"embeds":[83],"tags":[85],"into":[86,159,176],"structures":[89],"original":[92],"that":[95,119,187],"addresses":[97],"efficiently":[100],"compared":[101],"testing.":[104],"This":[105],"approach":[106],"avoids":[107],"bytewise":[109],"hashing":[110],"overhead":[111],"conventional":[113],"methods.":[115],"Secondly,":[116],"prove":[118],"partial":[121,136],"graph":[123,138,181],"obtained":[124,141],"from":[125],"sufficient":[128],"reordering":[131],"transformations":[132],"Such":[135,162],"very":[142],"fast,":[143],"without":[144],"having":[145],"exhaustively":[147],"enumerate":[148],"all":[149,215],"edges.":[151],"Thirdly,":[152],"partitions":[155],"task":[158],"independent":[160],"slices.":[161],"slices":[163],"profiled":[166,224],"parallel,":[168],"producing":[169],"subgraphs":[170],"are":[172],"eventually":[173],"combined":[174],"automatically":[175],"complete":[178],"by":[182,218],"compiler.":[184],"Experiments":[185],"show":[186],"these":[188],"significantly":[190],"reduce":[191],"use":[194],"shorten":[196],"time":[199],"(by":[200],"an":[201],"order":[202],"magnitude":[204],"several":[206,227],"SPEC2006":[207],"benchmarks).":[208],"Benchmarks":[209],"too":[210],"big":[211],"profile":[213],"at":[214],"loop":[216],"levels":[217],"previous":[219],"methods":[220],"now":[222],"fully":[225],"within":[226],"hours.":[228]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}