{"id":"https://openalex.org/W4221128531","doi":"https://doi.org/10.1145/3497776.3517780","title":"Performant portable OpenMP","display_name":"Performant portable OpenMP","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4221128531","doi":"https://doi.org/10.1145/3497776.3517780"},"language":"en","primary_location":{"id":"doi:10.1145/3497776.3517780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3497776.3517780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012101201","display_name":"G\u00fcray \u00d6zen","orcid":"https://orcid.org/0000-0001-8237-0141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guray Ozen","raw_affiliation_strings":["NVIDIA, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8237-0141","affiliations":[{"raw_affiliation_string":"NVIDIA, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034027625","display_name":"Michael Wolfe","orcid":"https://orcid.org/0000-0002-6481-6792"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wolfe","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8806799650192261},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8150451183319092},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8113110065460205},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7460925579071045},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.730088472366333},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6766330003738403},{"id":"https://openalex.org/keywords/directive","display_name":"Directive","score":0.5911992192268372},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5311148762702942},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5214037895202637},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5192530155181885},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.5066145658493042},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2711595296859741},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1347743570804596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8806799650192261},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8150451183319092},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8113110065460205},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7460925579071045},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.730088472366333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6766330003738403},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.5911992192268372},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5311148762702942},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5214037895202637},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5192530155181885},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.5066145658493042},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2711595296859741},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1347743570804596},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3497776.3517780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3497776.3517780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W143948075","https://openalex.org/W1554398046","https://openalex.org/W1596133819","https://openalex.org/W2019143817","https://openalex.org/W2029940394","https://openalex.org/W2098426571","https://openalex.org/W2170634604","https://openalex.org/W2171262795","https://openalex.org/W2180288011","https://openalex.org/W2211541975","https://openalex.org/W2242505559","https://openalex.org/W2750212803","https://openalex.org/W2786644468","https://openalex.org/W2888279336","https://openalex.org/W2898149606","https://openalex.org/W2912825911","https://openalex.org/W2913957157","https://openalex.org/W2969535219","https://openalex.org/W3037205796","https://openalex.org/W3081656884","https://openalex.org/W3137486602","https://openalex.org/W3157590335","https://openalex.org/W3208923685","https://openalex.org/W4234180294"],"related_works":["https://openalex.org/W2003935582","https://openalex.org/W1991844655","https://openalex.org/W2950520577","https://openalex.org/W1229628","https://openalex.org/W2567390125","https://openalex.org/W2526302199","https://openalex.org/W2009213655","https://openalex.org/W74409296","https://openalex.org/W2593878938","https://openalex.org/W2468095077"],"abstract_inverted_index":{"Accelerated":[0],"computing":[1],"has":[2,41],"increased":[3],"the":[4,15,65,78,86,113,126,156,161],"need":[5],"to":[6,145,155],"specialize":[7],"how":[8],"a":[9,19,25,37,42,57,90,101],"program":[10],"is":[11],"parallelized":[12],"depending":[13],"on":[14,160,164],"target.":[16],"Fully":[17],"exploiting":[18],"highly":[20],"parallel":[21],"accelerator,":[22],"such":[23],"as":[24],"GPU,":[26],"demands":[27],"more":[28,32],"parallelism":[29,35,177],"and":[30,105,119,148,166],"sometimes":[31],"levels":[33],"of":[34,47,82,89,112,135,151],"than":[36],"multicore":[38],"CPU.":[39],"OpenMP":[40,67],"directive":[43,69,92],"for":[44,52,93],"each":[45,53],"level":[46],"parallelism,":[48],"but":[49],"choosing":[50],"directives":[51],"target":[54],"can":[55,76],"incur":[56],"significant":[58],"productivity":[59,87],"cost.":[60],"We":[61,131],"argue":[62],"that":[63],"using":[64,125],"new":[66],"loop":[68,114],"with":[70,85,109],"an":[71,110,133,149],"appropriate":[72],"compiler":[73],"decision":[74],"process":[75],"achieve":[77],"same":[79],"performance":[80,158],"benefits":[81,108],"target-specific":[83],"parallelization":[84],"advantage":[88],"single":[91],"all":[94],"targets.":[95],"In":[96,170],"this":[97],"paper,":[98],"we":[99],"introduce":[100],"fully":[102],"descriptive":[103],"model":[104],"demonstrate":[106],"its":[107],"implementation":[111,134],"directive,":[115],"comparing":[116],"performance,":[117],"productivity,":[118],"portability":[120],"against":[121],"other":[122],"production":[123],"compilers":[124],"SPEC":[127],"ACCEL":[128],"benchmark":[129],"suite.":[130],"provide":[132],"our":[136,172],"proposal":[137,173],"in":[138],"NVIDIA's":[139],"HPC":[140],"compiler.":[141],"It":[142],"yields":[143],"up":[144],"56X":[146],"speedup":[147,153],"average":[150],"1.91x-1.79x":[152],"compared":[154],"baseline":[157],"(depending":[159],"host":[162],"system)":[163],"GPUs,":[165],"preserves":[167],"CPU":[168],"performance.":[169],"addition,":[171],"requires":[174],"60%":[175],"fewer":[176],"directives.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}