{"id":"https://openalex.org/W4393970798","doi":"https://doi.org/10.1145/3648115.3648123","title":"Accelerating Machine Learning Inference on GPUs with SYCL","display_name":"Accelerating Machine Learning Inference on GPUs with SYCL","publication_year":2024,"publication_date":"2024-04-05","ids":{"openalex":"https://openalex.org/W4393970798","doi":"https://doi.org/10.1145/3648115.3648123"},"language":"en","primary_location":{"id":"doi:10.1145/3648115.3648123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648115.3648123","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5014340646","display_name":"Ioanna-Maria Panagou","orcid":"https://orcid.org/0009-0000-4205-7281"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioanna-Maria Panagou","raw_affiliation_strings":["University of Thessaly, Greece"],"raw_orcid":"https://orcid.org/0009-0000-4205-7281","affiliations":[{"raw_affiliation_string":"University of Thessaly, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062849403","display_name":"Nikolaos Bellas","orcid":"https://orcid.org/0000-0002-9522-9136"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Bellas","raw_affiliation_strings":["University of Thessaly, Greece"],"raw_orcid":"https://orcid.org/0000-0002-9522-9136","affiliations":[{"raw_affiliation_string":"University of Thessaly, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025129711","display_name":"L. Moneta","orcid":"https://orcid.org/0000-0002-0935-0862"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lorenzo Moneta","raw_affiliation_strings":["CERN, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0935-0862","affiliations":[{"raw_affiliation_string":"CERN, Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049827266","display_name":"Sanjiban Sengupta","orcid":"https://orcid.org/0009-0005-1281-505X"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sanjiban Sengupta","raw_affiliation_strings":["CERN, Switzerland"],"raw_orcid":"https://orcid.org/0009-0005-1281-505X","affiliations":[{"raw_affiliation_string":"CERN, Switzerland","institution_ids":["https://openalex.org/I67311998"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.992900013923645,"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":0.9861000180244446,"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/inference","display_name":"Inference","score":0.7842159271240234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7533900737762451},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5920605063438416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563986599445343},{"id":"https://openalex.org/keywords/large-hadron-collider","display_name":"Large Hadron Collider","score":0.48607638478279114},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4820159673690796},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4658167362213135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.451923131942749},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.446138858795166},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2541857361793518},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1669503152370453},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.09970659017562866}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7842159271240234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533900737762451},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5920605063438416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563986599445343},{"id":"https://openalex.org/C87668248","wikidata":"https://www.wikidata.org/wiki/Q40605","display_name":"Large Hadron Collider","level":2,"score":0.48607638478279114},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4820159673690796},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4658167362213135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.451923131942749},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.446138858795166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2541857361793518},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1669503152370453},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.09970659017562866},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3648115.3648123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648115.3648123","pdf_url":null,"source":null,"license":null,"license_id":null,"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"},{"id":"pmh:oai:cds.cern.ch:2940309","is_oa":false,"landing_page_url":"http://cds.cern.ch/record/2940309","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2551989492","https://openalex.org/W3093756531","https://openalex.org/W3190695173","https://openalex.org/W4256598393"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372"],"abstract_inverted_index":{"Recently,":[0],"machine":[1,31,102,132],"learning":[2,32,103,133],"has":[3,115],"established":[4],"itself":[5],"as":[6,24,35],"a":[7,79],"valuable":[8],"tool":[9],"for":[10,42,71,73,131],"researchers":[11],"to":[12,127],"analyze":[13],"their":[14,48,59],"data":[15],"and":[16,37,51,114,143,151],"draw":[17],"conclusions":[18],"in":[19,97],"various":[20,140],"scientific":[21],"fields,":[22],"such":[23,34],"High":[25],"Energy":[26],"Physics":[27],"(HEP).":[28],"Commonly":[29],"used":[30],"libraries,":[33],"Keras":[36],"PyTorch,":[38],"might":[39],"provide":[40],"functionality":[41,124],"inference,":[43],"but":[44],"they":[45],"only":[46,145],"support":[47],"own":[49],"models":[50],"are":[52],"constrained":[53],"by":[54],"heavy":[55],"dependencies,":[56],"which":[57,69],"render":[58],"deployment":[60],"on":[61,139,147],"embedded":[62],"or":[63],"bare-metal":[64],"environments":[65],"infeasible.":[66],"SOFIE":[67,126],"[3],":[68],"stands":[70],"System":[72],"Optimized":[74],"Fast":[75],"Inference":[76],"code":[77,92,106,130],"Emit,":[78],"part":[80],"of":[81,99,125],"the":[82,100,123],"ROOT":[83],"project":[84],"developed":[85],"at":[86],"CERN,":[87],"creates":[88],"standalone":[89],"C++":[90,112],"inference":[91,135],"from":[93,110],"an":[94],"input":[95],"model":[96,134],"one":[98],"popular":[101],"formats.":[104],"This":[105],"is":[107,144],"directly":[108],"invokable":[109],"other":[111],"projects":[113],"minimal":[116],"dependencies.":[117],"In":[118],"this":[119],"work,":[120],"we":[121],"extend":[122],"generate":[128],"SYCL":[129],"that":[136],"can":[137],"run":[138],"GPU":[141],"platforms":[142],"dependent":[146],"Intel":[148],"MKL":[149],"BLAS":[150],"portBLAS":[152],"libraries.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
