{"id":"https://openalex.org/W3159481477","doi":"https://doi.org/10.1145/3456669.3456698","title":"Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs","display_name":"Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3159481477","doi":"https://doi.org/10.1145/3456669.3456698","mag":"3159481477"},"language":"en","primary_location":{"id":"doi:10.1145/3456669.3456698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3456669.3456698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3456669.3456698","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3456669.3456698","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066426380","display_name":"Tobias Baumann","orcid":"https://orcid.org/0000-0001-7480-7809"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tobias Baumann","raw_affiliation_strings":["Zuse Institute Berlin (ZIB), DE"],"affiliations":[{"raw_affiliation_string":"Zuse Institute Berlin (ZIB), DE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090060060","display_name":"Matthias Noack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Noack","raw_affiliation_strings":["Zuse Institute Berlin (ZIB), DE"],"affiliations":[{"raw_affiliation_string":"Zuse Institute Berlin (ZIB), DE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090438638","display_name":"Thomas Steinke","orcid":"https://orcid.org/0000-0002-0338-8042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Steinke","raw_affiliation_strings":["Zuse Institute Berlin (ZIB), DE"],"affiliations":[{"raw_affiliation_string":"Zuse Institute Berlin (ZIB), DE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066426380"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3138,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.35747664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.994700014591217,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.991599977016449,"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":0.8207343816757202},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.6780295372009277},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6472183465957642},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45685580372810364},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4302067458629608},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3349209427833557},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.20408833026885986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207343816757202},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6780295372009277},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6472183465957642},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45685580372810364},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4302067458629608},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3349209427833557},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.20408833026885986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3456669.3456698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3456669.3456698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3456669.3456698","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":{"id":"doi:10.1145/3456669.3456698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3456669.3456698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3456669.3456698","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"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G285373376","display_name":null,"funder_award_id":"MODAL, project number 05M20ZBM","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4192406653","display_name":null,"funder_award_id":"05M20ZBM","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7225624288","display_name":null,"funder_award_id":"This work was","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3159481477.pdf","grobid_xml":"https://content.openalex.org/works/W3159481477.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W38257615","https://openalex.org/W1677252112","https://openalex.org/W1933929749","https://openalex.org/W1991592471","https://openalex.org/W2399715892","https://openalex.org/W2527815437","https://openalex.org/W2611626712","https://openalex.org/W2736325406","https://openalex.org/W2766807579","https://openalex.org/W2791531244","https://openalex.org/W2886022695","https://openalex.org/W2897298870","https://openalex.org/W2944262483","https://openalex.org/W2995010870","https://openalex.org/W3012497848","https://openalex.org/W3024375933","https://openalex.org/W3103903655","https://openalex.org/W3104343495","https://openalex.org/W4247111930","https://openalex.org/W4247856748"],"related_works":["https://openalex.org/W2386275106","https://openalex.org/W1997145140","https://openalex.org/W2034384303","https://openalex.org/W2063994682","https://openalex.org/W2370834747","https://openalex.org/W2386620328","https://openalex.org/W2060613067","https://openalex.org/W2351721127","https://openalex.org/W2347627348","https://openalex.org/W2213483932"],"abstract_inverted_index":{"The":[0],"Portable":[1],"Computing":[2],"Language":[3],"(PoCL)":[4],"is":[5,101],"a":[6,16,22,51,64,72,115,128],"vendor":[7],"independent":[8],"open-source":[9],"OpenCL":[10,30,109],"implementation":[11,31],"that":[12],"aims":[13],"to":[14,88,103,107,119],"support":[15],"variety":[17],"of":[18,36,46,53,117],"compute":[19],"devices":[20],"in":[21,61,94,122],"single":[23],"platform.":[24],"Evaluating":[25],"PoCL":[26,37,62],"versus":[27],"the":[28,47,97,105],"Intel":[29,39,78,108],"reveals":[32],"significant":[33],"performance":[34,59],"drawbacks":[35],"on":[38,66,77],"CPUs":[40],"\u2013":[41],"which":[42],"run":[43],"92":[44],"%":[45],"TOP500":[48],"list.":[49],"Using":[50,96],"selection":[52],"benchmarks,":[54],"we":[55],"identify":[56],"and":[57,68,83,110],"analyse":[58],"issues":[60],"with":[63,86,127],"focus":[65],"scheduling":[67],"vectorisation.":[69],"We":[70],"propose":[71],"new":[73],"CPU":[74],"device-driver":[75],"based":[76],"Threading":[79],"Building":[80],"Blocks":[81],"(TBB),":[82],"evaluate":[84],"LLVM":[85],"respect":[87],"automatic":[89],"compiler":[90],"vectorisation":[91,130],"across":[92],"work-items":[93],"PoCL.":[95],"TBB":[98],"driver,":[99],"it":[100,113],"possible":[102],"narrow":[104],"gap":[106],"even":[111],"outperform":[112],"by":[114],"factor":[116],"up":[118],"1.3":[120],"\u00d7":[121],"our":[123],"proxy":[124],"application":[125],"benchmark":[126],"manual":[129],"strategy.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
