{"id":"https://openalex.org/W4386709678","doi":"https://doi.org/10.1145/3605573.3605640","title":"Implementing OpenMP\u2019s SIMD Directive in LLVM\u2019s GPU Runtime","display_name":"Implementing OpenMP\u2019s SIMD Directive in LLVM\u2019s GPU Runtime","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709678","doi":"https://doi.org/10.1145/3605573.3605640"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605573.3605640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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/A5005506476","display_name":"Eric Wright","orcid":"https://orcid.org/0000-0002-1982-9092"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Wright","raw_affiliation_strings":["University of Delaware, United States"],"raw_orcid":"https://orcid.org/0000-0002-1982-9092","affiliations":[{"raw_affiliation_string":"University of Delaware, United States","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032645176","display_name":"Johannes Doerfert","orcid":"https://orcid.org/0000-0001-7870-8963"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes Doerfert","raw_affiliation_strings":["Lawrence Livermore National Laboratory, United States"],"raw_orcid":"https://orcid.org/0000-0001-7870-8963","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, United States","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083617935","display_name":"Shilei Tian","orcid":"https://orcid.org/0000-0001-6468-6839"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shilei Tian","raw_affiliation_strings":["Stony Brook University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6468-6839","affiliations":[{"raw_affiliation_string":"Stony Brook University, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Stony Brook University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8449-8579","affiliations":[{"raw_affiliation_string":"Stony Brook University, United States of America","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009614578","display_name":"Sunita Chandrasekaran","orcid":"https://orcid.org/0000-0002-3560-9428"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunita Chandrasekaran","raw_affiliation_strings":["University of Delaware, United States"],"raw_orcid":"https://orcid.org/0000-0002-3560-9428","affiliations":[{"raw_affiliation_string":"University of Delaware, United States","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.996399998664856,"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":0.996399998664856,"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":0.9904000163078308,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/simd","display_name":"SIMD","score":0.8302809596061707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8092969655990601},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6929184198379517},{"id":"https://openalex.org/keywords/directive","display_name":"Directive","score":0.6697717905044556},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3702227473258972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23364198207855225}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8302809596061707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092969655990601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6929184198379517},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.6697717905044556},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3702227473258972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23364198207855225}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605573.3605640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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":18,"referenced_works":["https://openalex.org/W1584265037","https://openalex.org/W1845641575","https://openalex.org/W2019143817","https://openalex.org/W2180288011","https://openalex.org/W2281558607","https://openalex.org/W2519929754","https://openalex.org/W2521614036","https://openalex.org/W2786644468","https://openalex.org/W2905488570","https://openalex.org/W3037205796","https://openalex.org/W3081656884","https://openalex.org/W3101695443","https://openalex.org/W3167401864","https://openalex.org/W3194993684","https://openalex.org/W4213291706","https://openalex.org/W4250713484","https://openalex.org/W4285504014","https://openalex.org/W6884652701"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2162726111","https://openalex.org/W2022397046","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W2117755361","https://openalex.org/W2286348849","https://openalex.org/W2018511057","https://openalex.org/W2478126787","https://openalex.org/W1587248296"],"abstract_inverted_index":{"GPUs":[0],"support":[1,47],"three":[2,28,65,146],"levels":[3],"of":[4,26,29,68,78,90,149,159],"parallelism:":[5],"thread":[6,54],"blocks,":[7],"warps":[8],"(or":[9],"wavefronts)":[10],"within":[11,16,59],"a":[12,17,60,115,120],"block,":[13],"and":[14,40,49,56,74,88,104,114],"threads":[15,58],"warp.":[18],"Some":[19],"GPU":[20,98,160],"programming":[21],"models":[22],"allow":[23],"the":[24,37,79,91,130,132,156],"use":[25],"all":[27,57],"these":[30],"levels,":[31,53],"such":[32,136],"as":[33],"OpenMP":[34,92,97],"offloading":[35],"with":[36,64,145],"teams,":[38],"parallel,":[39],"simd":[41,48,93],"directives.":[42],"However":[43],"LLVM/OpenMP":[44],"does":[45],"not":[46],"only":[50],"uses":[51],"two":[52],"blocks":[55],"block.":[61],"For":[62],"codes":[63],"explicit":[66,147],"layers":[67,148],"parallelism":[69,150],"this":[70,82,140],"can":[71],"decrease":[72],"performance":[73,121],"potentially":[75],"require":[76],"restructuring":[77],"application.":[80],"In":[81],"work":[83,141],"we":[84],"present":[85],"our":[86,110],"design":[87],"implementation":[89],"directive":[94],"in":[95],"LLVM\u2019s":[96],"runtime,":[99],"which":[100],"includes":[101],"both":[102],"CPU-centric":[103],"GPU-centric":[105],"execution":[106],"models.":[107],"We":[108],"evaluate":[109],"prototype":[111],"using":[112],"kernels":[113,133],"few":[116],"proxy":[117],"applications":[118,144],"showing":[119],"improvement":[122],"ranging":[123],"from":[124,135],"1.3x":[125],"to":[126,151,153],"3.5x":[127],"depending":[128],"on":[129],"benefit":[131],"receives":[134],"an":[137],"optimization.":[138],"Thus,":[139],"enables":[142],"real-world":[143],"expose":[152],"better":[154],"exploit":[155],"full":[157],"benefits":[158],"architecture.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}