{"id":"https://openalex.org/W3037205796","doi":"https://doi.org/10.1147/jrd.2019.2962428","title":"OpenMP 4.5 compiler optimization for GPU offloading","display_name":"OpenMP 4.5 compiler optimization for GPU offloading","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3037205796","doi":"https://doi.org/10.1147/jrd.2019.2962428","mag":"3037205796"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2019.2962428","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2962428","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-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/A5085106119","display_name":"Ettore Tiotto","orcid":"https://orcid.org/0000-0001-5235-8248"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"E. Tiotto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012183381","display_name":"Bardia Mahjour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B. Mahjour","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074766900","display_name":"Wenlong Tsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Tsang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101898791","display_name":"Xiaoping Xue","orcid":"https://orcid.org/0000-0003-0066-8329"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"X. Xue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067278813","display_name":"Tarikul Islam","orcid":"https://orcid.org/0000-0002-1901-239X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Islam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055644612","display_name":"William Chen","orcid":"https://orcid.org/0000-0001-8924-5853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085106119"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3127,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89019437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"64","issue":"3/4","first_page":"14:1","last_page":"14:11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8730574250221252},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.812049388885498},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.715600848197937},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.6011577844619751},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.5961978435516357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5661895275115967},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4928191006183624},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4290202856063843},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39193493127822876},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.353763222694397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8730574250221252},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.812049388885498},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.715600848197937},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.6011577844619751},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.5961978435516357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5661895275115967},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4928191006183624},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4290202856063843},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39193493127822876},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.353763222694397},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2019.2962428","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2962428","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3608418543","display_name":null,"funder_award_id":"B604142","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2019143817","https://openalex.org/W2916922955","https://openalex.org/W6759929088"],"related_works":["https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035","https://openalex.org/W1597127505","https://openalex.org/W3146558274"],"abstract_inverted_index":{"Ability":[0],"to":[1,6,65,79,105,112,124,138,160,177,184],"efficiently":[2],"offload":[3],"computational":[4],"workloads":[5],"graphic":[7],"processing":[8],"units":[9],"(GPUs)":[10],"is":[11,30],"critical":[12],"for":[13,129],"the":[14,22,37,49,53,75,84,93,107,119,145,152,173],"success":[15],"of":[16,39,48,83,96,109,142,147],"hybrid":[17],"CPU\u2013GPU":[18],"architectures,":[19],"such":[20],"as":[21],"Summit":[23],"and":[24,41,57,100],"Sierra":[25],"supercomputing":[26],"systems.":[27],"OpenMP":[28,50,60,85,181],"4.5":[29],"a":[31,97],"high-level":[32],"programming":[33],"model":[34],"that":[35,62],"enables":[36],"development":[38],"architecture-":[40],"accelerator-independent":[42],"applications.":[43],"This":[44,69],"article":[45,164],"describes":[46],"aspects":[47],"implementation":[51],"in":[52,144,151,172,179],"IBM":[54],"XL":[55,58,76,174],"C/C++":[56],"Fortran":[59,175],"compilers":[61],"aid":[63,178],"programmers":[64],"achieve":[66],"performance":[67,161],"objectives.":[68],"includes":[70],"an":[71,113,139,167],"interprocedural":[72],"static":[73],"analysis":[74],"optimizer":[77],"uses":[78],"specialize":[80],"code":[81],"generation":[82],"<italic":[86],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">distribute":[88],"parallel":[89],"do</i>":[90],"loop":[91],"within":[92],"dynamic":[94],"context":[95],"target":[98,115,131,149],"region,":[99],"other":[101],"compiler":[102,176],"optimizations":[103],"designed":[104],"reduce":[106],"overhead":[108],"data":[110],"transferred":[111],"offloaded":[114,130,183],"region.":[116],"We":[117],"introduce":[118],"heuristic":[120],"used":[121],"at":[122],"runtime":[123,146],"select":[125],"optimal":[126],"grid":[127],"sizes":[128],"team":[132],"constructs.":[133],"These":[134],"tuned":[135],"heuristics":[136],"lead":[137],"average":[140],"improvement":[141],"2\u00d7":[143],"several":[148],"regions":[150],"SPEC":[153],"ACCEL":[154],"V1.2":[155],"benchmark":[156],"suite.":[157],"In":[158],"addition":[159],"enhancement,":[162],"this":[163],"also":[165],"presents":[166],"advanced":[168],"diagnostic":[169],"feature":[170],"implemented":[171],"debugging":[180],"applications":[182],"accelerators.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
