{"id":"https://openalex.org/W7167680582","doi":"https://doi.org/10.1145/3811257.3811262","title":"AdaptiveCpp Portable CUDA: A SYCL-Compatible CUDA Compiler for CPUs and GPUs from Multiple Vendors","display_name":"AdaptiveCpp Portable CUDA: A SYCL-Compatible CUDA Compiler for CPUs and GPUs from Multiple Vendors","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7167680582","doi":"https://doi.org/10.1145/3811257.3811262"},"language":null,"primary_location":{"id":"doi:10.1145/3811257.3811262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811257.3811262","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 International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3811257.3811262","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"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["DE","RU"],"is_corresponding":false,"raw_author_name":"Aksel Alpay","raw_affiliation_strings":["Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1976-6375","affiliations":[{"raw_affiliation_string":"Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210143490"]}]},{"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"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["DE","RU"],"is_corresponding":false,"raw_author_name":"Vincent Heuveline","raw_affiliation_strings":["Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2217-7558","affiliations":[{"raw_affiliation_string":"Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210143490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89525959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9857000112533569,"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":0.9857000112533569,"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/T10126","display_name":"Logic, programming, and type systems","score":0.0038999998942017555,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8712999820709229},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.78329998254776},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5974000096321106},{"id":"https://openalex.org/keywords/interprocedural-optimization","display_name":"Interprocedural optimization","score":0.4453999996185303},{"id":"https://openalex.org/keywords/compiler-correctness","display_name":"Compiler correctness","score":0.41290000081062317},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.3483000099658966},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8712999820709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633999824523926},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.78329998254776},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.692799985408783},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5974000096321106},{"id":"https://openalex.org/C111564260","wikidata":"https://www.wikidata.org/wiki/Q4288856","display_name":"Interprocedural optimization","level":5,"score":0.4453999996185303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C68366613","wikidata":"https://www.wikidata.org/wiki/Q5156378","display_name":"Compiler correctness","level":3,"score":0.41290000081062317},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3811257.3811262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811257.3811262","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 International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3811257.3811262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811257.3811262","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 International Workshop on OpenCL and SYCL","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2888171975","display_name":"Scaling extreme analYtics with Cross-architecture acceLeration based on OPen Standards\u200b","funder_award_id":"101092877","funder_id":"https://openalex.org/F4320338444","funder_display_name":"HORIZON EUROPE Digital, Industry and Space"}],"funders":[{"id":"https://openalex.org/F4320338444","display_name":"HORIZON EUROPE Digital, Industry and Space","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W583100948","https://openalex.org/W2292282166","https://openalex.org/W2399715892","https://openalex.org/W2613143750","https://openalex.org/W2996849306","https://openalex.org/W3011794212","https://openalex.org/W3020739840","https://openalex.org/W3152529237","https://openalex.org/W4225269858","https://openalex.org/W4289522463","https://openalex.org/W4362675350","https://openalex.org/W4362675393","https://openalex.org/W4362675404","https://openalex.org/W4367665029","https://openalex.org/W4381894488","https://openalex.org/W4393970692","https://openalex.org/W4393970761","https://openalex.org/W4393970819","https://openalex.org/W4394006036","https://openalex.org/W4407848494","https://openalex.org/W4413458368","https://openalex.org/W7128246394"],"related_works":[],"abstract_inverted_index":{"We":[0,97,123,155,235],"present":[1],"AdaptiveCpp":[2,35,56,64],"portable":[3],"CUDA":[4,93,159],"(PCUDA),":[5],"a":[6,132,250],"new":[7],"compiler":[8,36,70,117],"and":[9,14,25,38,48,104,127,151,228,233,265],"runtime":[10,49],"which":[11],"enables":[12],"compilation":[13],"execution":[15],"of":[16,33,92,134,161,171,208,255],"HIP/CUDA":[17,69,105],"code":[18],"on":[19,45,136,231],"CPUs,":[20],"NVIDIA":[21,149],"GPUs,":[22],"AMD":[23,138,152],"GPUs":[24],"Intel":[26,146],"GPUs.":[27,154],"PCUDA":[28,65,209,239,266],"is":[29,39,66,210],"implemented":[30],"as":[31,143,145],"part":[32],"the":[34,46,67,114,158,172,184,190,217,241,256],"project,":[37],"designed":[40],"to":[41,95,181,200,212],"be":[42,84,109,119,179,213],"fully":[43],"interoperable":[44],"source":[47],"level":[50],"with":[51,75,166],"other":[52],"programming":[53,106],"models":[54,107],"that":[55,71,100,157,189,238,272],"supports,":[57],"in":[58,183,216,270],"particular":[59],"SYCL.":[60,96],"To":[61],"our":[62],"knowledge,":[63],"first":[68],"has":[72],"full":[73],"interoperability":[74],"SYCL,":[76,248],"while":[77],"also":[78,98,236],"inheriting":[79],"SYCL\u2019s":[80],"portability.":[81],"This":[82,187],"can":[83,108,118,178],"beneficial":[85],"e.g.":[86],"for":[87,121],"iterative":[88],"or":[89],"partial":[90],"porting":[91],"projects":[94],"argue":[99],"using":[101,131],"PCUDA,":[102,167],"SYCL":[103,174,191,257,264,271],"compared":[110,199],"more":[111],"accurately,":[112],"because":[113],"exact":[115],"same":[116],"used":[120],"comparisons.":[122],"describe":[124],"PCUDA\u2019s":[125],"design,":[126],"demonstrate":[128],"its":[129],"capabilities":[130],"set":[133],"benchmarks":[135,221],"an":[137],"Ryzen":[139],"9":[140],"9950X":[141],"CPU,":[142],"well":[144],"Arc":[147],"B580,":[148],"A100":[150],"MI300X":[153],"find":[156],"versions":[160],"these":[162],"benchmarks,":[163],"when":[164],"compiled":[165],"closely":[168],"match":[169],"performance":[170,197,207],"AdaptiveCpp-compiled":[173],"versions.":[175],"Larger":[176],"deviations":[177],"attributed":[180],"differences":[182],"input":[185],"code.":[186],"indicates":[188],"abstractions":[192],"do":[193],"not":[194],"inherently":[195],"introduce":[196],"penalties":[198],"HIP/CUDA\u2019s":[201],"lower":[202],"abstraction":[203],"level.":[204],"The":[205],"overall":[206],"found":[211],"highly":[214],"competitive,":[215],"geometric":[218],"mean":[219],"across":[220],"outperforming":[222],"vendor":[223],"GPU":[224],"compilers":[225],"between":[226,263],"7%":[227],"31%,":[229],"depending":[230],"platform":[232],"configuration.":[234],"show":[237],"compiles":[240],"CloverLeaf":[242],"application":[243],"roughly":[244],"10x":[245],"faster":[246],"than":[247],"indicating":[249],"severe":[251],"compile":[252],"time":[253],"disadvantage":[254],"model.":[258],"Comparing":[259],"kernel":[260],"submission":[261,268],"throughput":[262],"reveals":[267],"overheads":[269],"are":[273],"primarily":[274],"caused":[275],"by":[276],"unnecessary":[277],"event":[278],"creation.":[279]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-09T00:00:00"}