{"id":"https://openalex.org/W4394006036","doi":"https://doi.org/10.1145/3648115.3648117","title":"AdaptiveCpp Stdpar: C++ Standard Parallelism Integrated Into a SYCL Compiler","display_name":"AdaptiveCpp Stdpar: C++ Standard Parallelism Integrated Into a SYCL Compiler","publication_year":2024,"publication_date":"2024-04-05","ids":{"openalex":"https://openalex.org/W4394006036","doi":"https://doi.org/10.1145/3648115.3648117"},"language":"en","primary_location":{"id":"doi:10.1145/3648115.3648117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648115.3648117","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3648115.3648117","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017192992","display_name":"Aksel Alpay","orcid":"https://orcid.org/0000-0003-1976-6375"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Aksel Alpay","raw_affiliation_strings":["Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058920681","display_name":"Vincent Heuveline","orcid":"https://orcid.org/0000-0002-2217-7558"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vincent Heuveline","raw_affiliation_strings":["Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017192992"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":4.2552,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95193435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.8808201551437378},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.817575991153717},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7161798477172852},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4317566156387329},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4275496006011963},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.339835524559021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3082599639892578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808201551437378},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.817575991153717},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7161798477172852},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4317566156387329},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4275496006011963},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.339835524559021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3082599639892578},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3648115.3648117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648115.3648117","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3648115.3648117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648115.3648117","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5783490283","display_name":null,"funder_award_id":"EP/P020224/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2399715892","https://openalex.org/W2521708680","https://openalex.org/W2528745529","https://openalex.org/W2759968233","https://openalex.org/W3017538311","https://openalex.org/W3152529237","https://openalex.org/W3187530291","https://openalex.org/W4225263328","https://openalex.org/W4246166885","https://openalex.org/W4318602934","https://openalex.org/W4318603243","https://openalex.org/W4362675404"],"related_works":["https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W650988184","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2162410319","https://openalex.org/W2137356287","https://openalex.org/W4321184925","https://openalex.org/W2255990315","https://openalex.org/W60915090"],"abstract_inverted_index":{"Expressing":[0],"data":[1],"parallel":[2],"programs":[3],"using":[4,111],"C++":[5,112],"standard":[6,46,113],"parallelism":[7],"is":[8,49,79,88,124],"attractive":[9],"not":[10],"only":[11],"due":[12,21,178],"to":[13,22,32,45,94,107,119,150,173,179,204],"the":[14,17,65,82,89,140],"simplicity":[15],"of":[16,81,142,153],"model,":[18,29],"but":[19],"also":[20,36],"its":[23],"highly":[24],"idiomatic":[25],"nature.":[26],"This":[27],"programming":[28,41],"commonly":[30],"referred":[31],"as":[33,55,121],"stdpar,":[34,73],"can":[35],"be":[37],"used":[38],"for":[39,166],"accelerator":[40],"by":[42,51,148,171,189],"offloading":[43,213],"calls":[44],"algorithms,":[47,114],"and":[48,62,102,104,115,197,211],"supported":[50],"multiple":[52],"vendors,":[53],"such":[54],"NVIDIA":[56,101,176],"with":[57,60,64,195],"nvc++,":[58],"AMD":[59],"roc-stdpar,":[61],"Intel":[63],"new":[66],"ICPX":[67],"-fsycl-pstl-offload":[68],"flag.":[69],"We":[70,126],"present":[71],"AdaptiveCpp":[72,83,86,159],"a":[74,163,192],"novel":[75,180],"stdpar":[76,87,92,134,183],"implementation":[77,93,184],"that":[78,128],"part":[80],"SYCL":[84,120],"implementation.":[85],"very":[90],"first":[91],"demonstrate":[95],"performance":[96],"across":[97],"GPUs":[98,138],"from":[99,186],"Intel,":[100],"AMD,":[103],"allows":[105],"users":[106],"start":[108],"developing":[109],"applications":[110],"then":[116],"progressively":[117],"move":[118],"more":[122],"control":[123],"needed.":[125],"find":[127],"our":[129],"solution":[130],"outperforms":[131,160],"all":[132,167],"vendor":[133],"compilers":[135],"on":[136,175,191],"HPC":[137],"in":[139,145,162],"majority":[141],"tested":[143,168],"applications,":[144],"some":[146],"configurations":[147],"up":[149,172],"an":[151,212],"order":[152],"magnitude.":[154],"Furthermore,":[155],"we":[156],"show":[157],"how":[158],"nvc++":[161],"latency-bound":[164],"code":[165],"problem":[169],"sizes":[170],"80%":[174],"A100":[177],"optimizations.":[181],"Our":[182],"deviates":[185],"existing":[187],"implementations":[188],"relying":[190],"tighter":[193],"integration":[194],"compiler":[196],"runtime,":[198],"including":[199],"e.g.":[200],"dedicated":[201],"optimization":[202],"passes":[203],"elide":[205],"synchronization,":[206],"automatically":[207],"prefetching":[208],"required":[209],"allocations,":[210],"heuristic.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}