{"id":"https://openalex.org/W4225278845","doi":"https://doi.org/10.1145/3529538.3530216","title":"Compiler-aided nd-range parallel-for implementations on CPU in hipSYCL","display_name":"Compiler-aided nd-range parallel-for implementations on CPU in hipSYCL","publication_year":2022,"publication_date":"2022-05-02","ids":{"openalex":"https://openalex.org/W4225278845","doi":"https://doi.org/10.1145/3529538.3530216"},"language":"en","primary_location":{"id":"doi:10.1145/3529538.3530216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529538.3530216","pdf_url":null,"source":{"id":"https://openalex.org/S4306420323","display_name":"International Workshop on OpenCL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","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/A5000242668","display_name":"Joachim Meyer","orcid":"https://orcid.org/0000-0003-2656-9863"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Joachim Meyer","raw_affiliation_strings":["Compiler Design Lab, Saarland Informatics Campus, Saarland University, Germany"],"affiliations":[{"raw_affiliation_string":"Compiler Design Lab, Saarland Informatics Campus, Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","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":false,"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":"middle","author":{"id":"https://openalex.org/A5014251134","display_name":"Holger Fr\u00f6ning","orcid":"https://orcid.org/0000-0001-9562-0680"},"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":"Holger Fr\u00f6ning","raw_affiliation_strings":["Computing Systems Group, Institute of Computer Engineering, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Computing Systems Group, Institute of Computer Engineering, 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":4,"corresponding_author_ids":["https://openalex.org/A5000242668"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":1.071,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71284125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9921000003814697,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9861000180244446,"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":0.8838421106338501},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7699815630912781},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7450202703475952},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.723097562789917},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5786063075065613},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4843767583370209},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.43087053298950195},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4235122799873352},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4192933440208435},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.41595423221588135},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41086500883102417},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23449307680130005},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.19145196676254272},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12985065579414368},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.07000845670700073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8838421106338501},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7699815630912781},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7450202703475952},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.723097562789917},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5786063075065613},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4843767583370209},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.43087053298950195},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4235122799873352},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4192933440208435},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.41595423221588135},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41086500883102417},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23449307680130005},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.19145196676254272},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12985065579414368},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.07000845670700073},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3529538.3530216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529538.3530216","pdf_url":null,"source":{"id":"https://openalex.org/S4306420323","display_name":"International Workshop on OpenCL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1991592471","https://openalex.org/W2146411490","https://openalex.org/W2489197585","https://openalex.org/W2528745529","https://openalex.org/W3017538311","https://openalex.org/W3018019719","https://openalex.org/W3116487210","https://openalex.org/W3158823657"],"related_works":["https://openalex.org/W3020739840","https://openalex.org/W2128640905","https://openalex.org/W2011460173","https://openalex.org/W4386875822","https://openalex.org/W3177128669","https://openalex.org/W2122078011","https://openalex.org/W4385574943","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408"],"abstract_inverted_index":{"With":[0],"heterogeneous":[1],"programming":[2],"continuously":[3],"on":[4,45,96,132],"the":[5,16,47,52,63,75,79,82,117,121],"rise,":[6],"performance":[7,80],"portability":[8],"is":[9,120],"still":[10],"to":[11,32,41,91,107,125],"be":[12],"improved.":[13],"SYCL":[14,60,123],"provides":[15],"nd-range":[17,64,83,130],"parallel-for":[18,65,84,131],"paradigm":[19],"for":[20,28,87],"writing":[21],"data-parallel":[22],"kernels.":[23,36],"This":[24],"model":[25,42],"allows":[26],"barriers":[27],"group-local":[29],"synchronization,":[30],"similar":[31],"CUDA":[33],"and":[34,111],"OpenCL":[35,138],"GPUs":[37],"provide":[38,126],"efficient":[39],"means":[40],"this,":[43,74],"but":[44],"CPUs":[46,88],"necessary":[48],"forward-progress":[49],"guarantees":[50],"require":[51],"use":[53],"of":[54,81,94,116],"many":[55],"(lightweight)":[56],"threads":[57],"in":[58,85],"library-only":[59],"implementations,":[61],"rendering":[62],"unacceptably":[66],"inefficient.":[67],"By":[68,113],"adopting":[69],"two":[70,101],"compiler-based":[71],"approaches":[72],"solving":[73],"present":[76],"work":[77],"improves":[78],"hipSYCL":[86,119],"by":[89],"up":[90],"multiple":[92],"orders":[93],"magnitude":[95],"various":[97],"CPU":[98],"architectures.":[99],"The":[100],"alternatives":[102],"are":[103],"compared":[104],"with":[105],"regard":[106],"their":[108],"functional":[109],"correctness":[110],"performance.":[112],"upstreaming":[114],"one":[115],"variants,":[118],"first":[122],"implementation":[124],"a":[127],"well":[128],"performing":[129],"CPU,":[133],"without":[134],"requiring":[135],"an":[136],"available":[137],"runtime.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}