{"id":"https://openalex.org/W2971602575","doi":"https://doi.org/10.1145/3355378.3355381","title":"Profiling Halide DSL with CPU Performance Events for Schedule Optimization","display_name":"Profiling Halide DSL with CPU Performance Events for Schedule Optimization","publication_year":2019,"publication_date":"2019-09-05","ids":{"openalex":"https://openalex.org/W2971602575","doi":"https://doi.org/10.1145/3355378.3355381","mag":"2971602575"},"language":"en","primary_location":{"id":"doi:10.1145/3355378.3355381","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3355378.3355381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XXIII Brazilian Symposium on Programming Languages","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/A5010619377","display_name":"Rafael Ravedutti Lucio Machado","orcid":"https://orcid.org/0000-0002-5157-3429"},"institutions":[{"id":"https://openalex.org/I52418104","display_name":"Universidade Federal do Paran\u00e1","ror":"https://ror.org/05syd6y78","country_code":"BR","type":"education","lineage":["https://openalex.org/I52418104"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Rafael Ravedutti L. Machado","raw_affiliation_strings":["Universidade Federal do Paran\u00e1 Curitiba, Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Paran\u00e1 Curitiba, Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I52418104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003796569","display_name":"Andr\u00e9 Murbach Maidl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Murbach Maidl","raw_affiliation_strings":["Elastic Curitiba, Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Elastic Curitiba, Paran\u00e1, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015233908","display_name":"Daniel Weingaertner","orcid":null},"institutions":[{"id":"https://openalex.org/I52418104","display_name":"Universidade Federal do Paran\u00e1","ror":"https://ror.org/05syd6y78","country_code":"BR","type":"education","lineage":["https://openalex.org/I52418104"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel Weingaertner","raw_affiliation_strings":["Universidade Federal do Paran\u00e1 Curitiba, Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Paran\u00e1 Curitiba, Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I52418104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010619377"],"corresponding_institution_ids":["https://openalex.org/I52418104"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49308636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"45"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9886999726295471,"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":0.988099992275238,"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":0.850589394569397},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8105610609054565},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.7441462874412537},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5957484245300293},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5837739706039429},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.5551210641860962},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5457928776741028},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4881220757961273},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.4303862750530243},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.42129582166671753},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3671136200428009},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2489253580570221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850589394569397},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8105610609054565},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.7441462874412537},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5957484245300293},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5837739706039429},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.5551210641860962},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5457928776741028},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4881220757961273},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.4303862750530243},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.42129582166671753},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3671136200428009},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2489253580570221},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3355378.3355381","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3355378.3355381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XXIII Brazilian Symposium on Programming Languages","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1656664476","https://openalex.org/W1961751213","https://openalex.org/W1965351873","https://openalex.org/W1986989509","https://openalex.org/W1989988531","https://openalex.org/W2055312318","https://openalex.org/W2063099138","https://openalex.org/W2084917734","https://openalex.org/W2260757707","https://openalex.org/W2344642201","https://openalex.org/W2471164860","https://openalex.org/W3103104567","https://openalex.org/W4254778071"],"related_works":["https://openalex.org/W2140324148","https://openalex.org/W2121199344","https://openalex.org/W2285914869","https://openalex.org/W3117515082","https://openalex.org/W2113441357","https://openalex.org/W3022537591","https://openalex.org/W2167639078","https://openalex.org/W2379283503","https://openalex.org/W2141676084","https://openalex.org/W2462146500"],"abstract_inverted_index":{"Halide":[0,49,55],"is":[1],"a":[2,11,59,99,121],"domain-specific":[3],"language":[4],"(DSL)":[5],"for":[6,26,170],"image":[7,172],"processing":[8,173],"that":[9,62],"enforces":[10],"separation":[12],"of":[13,23,37,47,85,106,140],"the":[14,17,21,33,38,45,54,64,73,77,86,103,107,126,157],"algorithm":[15],"and":[16,90,93,144,154],"execution":[18,34],"schedule,":[19,35],"allowing":[20],"generation":[22],"specialized":[24],"code":[25],"distinct":[27],"computer":[28],"architectures":[29],"by":[30,57,72,115],"rewriting":[31],"only":[32],"instead":[36],"whole":[39],"algorithm.":[40],"In":[41],"order":[42,130],"to":[43,68,98,131,163],"support":[44],"creation":[46],"good":[48],"schedules,":[50],"our":[51],"work":[52],"extends":[53],"DSL":[56],"adding":[58],"profiling":[60,84,100,114],"API":[61],"uses":[63],"CPU":[65],"Performance":[66],"Events":[67],"measure":[69],"events":[70,133],"supported":[71],"target":[74],"processor":[75],"during":[76],"application":[78,87],"runtime.":[79],"The":[80],"proposed":[81],"extension":[82],"offers":[83],"loop":[88,104],"levels":[89],"functions'":[91],"producer":[92],"consumer":[94],"relations,":[95],"embedding":[96],"calls":[97],"library":[101,128],"in":[102,129],"nests":[105],"generated":[108],"code.":[109],"It":[110],"also":[111],"supports":[112],"individualized":[113],"threads":[116],"on":[117,148],"parallel":[118],"regions.":[119],"As":[120],"case":[122],"study":[123],"we":[124],"use":[125],"PAPI":[127],"count":[132],"such":[134],"as":[135],"L1":[136],"cache":[137],"misses,":[138],"number":[139],"float":[141],"operations":[142],"(FLOP)":[143],"L3":[145],"data":[146],"volume":[147],"an":[149,171],"Intel":[150],"Core":[151],"i5-7500":[152],"CPU,":[153],"discuss":[155],"how":[156],"reported":[158],"results":[159],"can":[160],"be":[161],"used":[162],"manually":[164],"or":[165],"automatically":[166],"generate":[167],"better":[168],"schedules":[169],"pipeline.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
