{"id":"https://openalex.org/W4400224498","doi":"https://doi.org/10.1145/3649153.3652997","title":"A Portable Tool to Compare Performance Profiles from GPU Offloading Programming Models","display_name":"A Portable Tool to Compare Performance Profiles from GPU Offloading Programming Models","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4400224498","doi":"https://doi.org/10.1145/3649153.3652997"},"language":"en","primary_location":{"id":"doi:10.1145/3649153.3652997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3652997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","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/A5099870933","display_name":"Jakob Sch\u00e4ffeler","orcid":"https://orcid.org/0009-0006-6818-4813"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jakob Sch\u00e4ffeler","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":"https://orcid.org/0009-0006-6818-4813","affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086176033","display_name":"Bengisu Elis","orcid":"https://orcid.org/0000-0002-0781-8206"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bengisu Elis","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":"https://orcid.org/0000-0002-0781-8206","affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005482380","display_name":"Amir Raoofy","orcid":"https://orcid.org/0000-0001-9664-8298"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amir Raoofy","raw_affiliation_strings":["Leibniz Supercomputing Centre"],"raw_orcid":"https://orcid.org/0000-0001-9664-8298","affiliations":[{"raw_affiliation_string":"Leibniz Supercomputing Centre","institution_ids":["https://openalex.org/I4210163716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073800722","display_name":"Josef Weidendorfer","orcid":"https://orcid.org/0000-0001-7159-1432"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef Weidendorfer","raw_affiliation_strings":["Leibniz Supercomputing Centre"],"raw_orcid":"https://orcid.org/0000-0001-7159-1432","affiliations":[{"raw_affiliation_string":"Leibniz Supercomputing Centre","institution_ids":["https://openalex.org/I4210163716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":"https://orcid.org/0000-0001-9013-435X","affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099870933"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.4744,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58469197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9966999888420105,"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":0.8282605409622192},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5109838247299194},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.392544686794281},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.338126003742218},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3175370693206787},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.15206846594810486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282605409622192},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5109838247299194},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.392544686794281},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.338126003742218},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3175370693206787},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.15206846594810486}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649153.3652997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3652997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.47999998927116394,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2990714382","https://openalex.org/W3125884253"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2505380084","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2086739451","https://openalex.org/W1980160788"],"abstract_inverted_index":{"GPUs":[0],"are":[1,80],"growingly":[2],"dominating":[3],"the":[4,10,69,95,110,114,130,135,147,157],"High-Performance":[5],"Computing":[6],"ecosystem,":[7],"and":[8,20,27,31,40,58,66,77,105,163],"therefore,":[9],"ease":[11,127],"of":[12,97,128,137,166],"their":[13],"programming":[14],"is":[15],"getting":[16],"increasingly":[17],"important.":[18],"Standard":[19],"high-level":[21],"offloading":[22,26,33,75,103,162],"methods,":[23],"like":[24],"OpenMP":[25,161],"OpenACC,":[28],"facilitate":[29],"portable":[30,91],"efficient":[32],"across":[34],"different":[35,45,118],"GPU":[36,106],"platforms.":[37,107],"However,":[38],"pinpointing":[39],"troubleshooting":[41],"performance":[42,70,98,123],"variations":[43],"among":[44],"models,":[46],"implementations,":[47],"or":[48],"architectures":[49],"poses":[50],"a":[51,90],"challenge":[52],"due":[53],"to":[54,62,67,73,93,120],"varying":[55],"abstraction":[56],"levels":[57],"profilers":[59,119],"employed.":[60],"Therefore,":[61],"tackle":[63],"this":[64,86],"problem":[65],"unwind":[68],"issues":[71,153],"related":[72],"various":[74,102],"abstractions":[76],"models":[78,104],"that":[79],"entangled":[81],"together":[82],"in":[83,85],"practice,":[84],"work,":[87],"we":[88,145],"introduce":[89],"tool":[92,111,131,158],"enable":[94],"comparison":[96],"profiles":[99,116],"acquired":[100],"from":[101],"For":[108,126],"this,":[109],"first":[112],"processes":[113],"collected":[115],"by":[117,150,155],"extract":[121],"key":[122],"indicatory":[124],"metrics.":[125],"comparison,":[129],"utilizes":[132],"plots":[133],"depicting":[134],"metrics":[136],"all":[138],"target":[139],"variants":[140],"for":[141],"relative":[142],"comparison.":[143],"Moreover,":[144],"demonstrate":[146],"tool's":[148],"capabilities":[149],"discussing":[151],"specific":[152],"discovered":[154],"using":[156],"when":[159],"comparing":[160],"CUDA":[164],"implementations":[165],"Babelstream.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
