{"id":"https://openalex.org/W3086803347","doi":"https://doi.org/10.1109/hpcs48598.2019.9188161","title":"Combining static and dynamic analysis to guide PGO for HPC applications: a case study on real-world applications","display_name":"Combining static and dynamic analysis to guide PGO for HPC applications: a case study on real-world applications","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W3086803347","doi":"https://doi.org/10.1109/hpcs48598.2019.9188161","mag":"3086803347"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs48598.2019.9188161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","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/A5041407202","display_name":"Youenn Lebras","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Youenn Lebras","raw_affiliation_strings":["University of Versailles, Versailles, France"],"affiliations":[{"raw_affiliation_string":"University of Versailles, Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072068080","display_name":"Andres Charif Rubial","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andres S. Charif-Rubial","raw_affiliation_strings":["PeXL, Versailles, France"],"affiliations":[{"raw_affiliation_string":"PeXL, Versailles, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048989161","display_name":"William Jalby","orcid":"https://orcid.org/0000-0002-4975-5469"},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"William Jalby","raw_affiliation_strings":["University of Versailles, Versailles, France"],"affiliations":[{"raw_affiliation_string":"University of Versailles, Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041407202"],"corresponding_institution_ids":["https://openalex.org/I4210165330"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25893556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"513","last_page":"520"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9894000291824341,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8746618032455444},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8694205284118652},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6953493356704712},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.6329207420349121},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6165061593055725},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5052562355995178},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4815242886543274},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4698682725429535},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4448421895503998},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4235770106315613},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.420261949300766},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.353908896446228},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33866897225379944},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2876451015472412},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14801174402236938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8746618032455444},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8694205284118652},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6953493356704712},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.6329207420349121},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6165061593055725},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5052562355995178},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4815242886543274},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4698682725429535},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4448421895503998},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4235770106315613},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.420261949300766},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.353908896446228},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33866897225379944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2876451015472412},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14801174402236938},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcs48598.2019.9188161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1500210458","https://openalex.org/W1510687364","https://openalex.org/W1517652255","https://openalex.org/W1557475516","https://openalex.org/W1987304299","https://openalex.org/W1996852726","https://openalex.org/W2060823499","https://openalex.org/W2068810256","https://openalex.org/W2107089133","https://openalex.org/W2121546953","https://openalex.org/W2125872407","https://openalex.org/W2153185479","https://openalex.org/W2161385493","https://openalex.org/W2164003586","https://openalex.org/W2294681552","https://openalex.org/W2548615750","https://openalex.org/W2885207652","https://openalex.org/W4246066726","https://openalex.org/W4246166885","https://openalex.org/W4252857370","https://openalex.org/W6629907520","https://openalex.org/W6633306651"],"related_works":["https://openalex.org/W3006937969","https://openalex.org/W2950655732","https://openalex.org/W2152397470","https://openalex.org/W4246264663","https://openalex.org/W1988661923","https://openalex.org/W2577630842","https://openalex.org/W1814870153","https://openalex.org/W2001356339","https://openalex.org/W2113798250","https://openalex.org/W1996886894"],"abstract_inverted_index":{"Modern":[0],"high":[1,21],"performance":[2,6,46,53,209,240,258],"processor":[3],"architectures":[4],"/tackle":[5],"issues":[7],"by":[8,208,220,228],"heavily":[9],"relying":[10],"on":[11,214],"increased":[12],"vector":[13],"lengths":[14],"and":[15,31,55,129,141,155,184,203,224,227,248],"advanced":[16],"memory":[17],"hierarchies":[18],"to":[19,42,83,91,95,124,160,168,177,251],"deliver":[20],"performance.":[22,132],"This":[23,150],"stresses":[24],"the":[25,35,65,103,122,152,157,179,186,257],"importance":[26],"of":[27,34,71,105,188,201],"data":[28,107,148,206],"access":[29],"optimization":[30,70,127],"efficient":[32],"usage":[33],"underlying":[36],"hardware.":[37],"Developers":[38],"usually":[39],"trust":[40],"compilers":[41,50,93,170],"automatically":[43],"address":[44],"these":[45],"issues,":[47],"but":[48,79],"unfortunately,":[49],"deploy":[51],"static":[52,202,223],"models":[54],"heuristics":[56],"which,":[57],"sometimes,":[58],"remain":[59],"conservative":[60],"or":[61],"even":[62],"fail":[63],"in":[64,175,236],"worst":[66],"case.":[67],"Moreover,":[68],"manual":[69],"production":[72],"HPC":[73],"codes":[74],"is":[75,94,142,167],"not":[76,136],"only":[77],"impractical,":[78],"impossible":[80],"when":[81],"having":[82],"manage":[84],"multiple":[85],"architecture":[86],"dependent":[87],"transformations.":[88],"One":[89],"way":[90],"assist":[92],"use":[96,104],"Profile":[97],"Guided":[98],"Optimization":[99],"(PGO).":[100],"It":[101],"allows":[102,250],"feedback":[106],"from":[108],"dynamic":[109,204,225],"profiling":[110,205],"using":[111],"a":[112,117,195,253],"representative":[113],"training":[114],"dataset,":[115],"for":[116],"given":[118],"target":[119],"application,":[120],"enabling":[121],"compiler":[123],"refine":[125],"its":[126],"choices":[128],"enhance":[130,185],"application":[131],"But,":[133],"PGO":[134,249],"does":[135],"always":[137],"consider":[138],"certain":[139],"metrics":[140],"rarely":[143],"aggressive":[144],"enough":[145],"regarding":[146],"metric":[147],"collection.":[149],"bounds":[151],"transformation":[153,180],"space":[154,181],"limits":[156],"compiler's":[158],"ability":[159],"perform":[161],"further":[162],"optimizations.":[163],"An":[164],"additional":[165],"option":[166],"provide":[169],"with":[171],"user":[172],"guided":[173],"assistance":[174],"order":[176],"enlarge":[178],"(i.e.":[182],"specialization)":[183],"quality":[187],"optimizations.In":[189],"this":[190],"paper,":[191],"we":[192],"introduce":[193],"ASSIST,":[194],"semi-automatic":[196],"source-to-source":[197],"manipulation":[198],"taking":[199],"advantage":[200],"produced":[207],"analysis":[210],"tools.":[211],"We":[212],"demonstrate":[213],"real":[215],"industrial":[216],"class":[217],"applications":[218],"that":[219],"combining":[221,246],"both":[222],"analyses":[226],"deploying":[229],"simple":[230],"transformations,":[231],"ASSIST":[232,247],"generates":[233],"similar":[234],"(and":[235],"some":[237],"cases":[238],"higher)":[239],"speedups":[241],"than":[242],"Intel":[243],"PGO.":[244],"Furthermore,":[245],"go":[252],"step":[254],"further,":[255],"increasing":[256],"substantially.":[259]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}