{"id":"https://openalex.org/W4362675393","doi":"https://doi.org/10.1145/3585341.3585342","title":"Implementation Techniques for SPMD Kernels on CPUs","display_name":"Implementation Techniques for SPMD Kernels on CPUs","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362675393","doi":"https://doi.org/10.1145/3585341.3585342"},"language":"en","primary_location":{"id":"doi:10.1145/3585341.3585342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3585341.3585342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3585341.3585342","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3585341.3585342","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 Computin, Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computin, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018809145","display_name":"Sebastian Hack","orcid":"https://orcid.org/0000-0002-3387-2134"},"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":false,"raw_author_name":"Sebastian Hack","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/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":5,"corresponding_author_ids":["https://openalex.org/A5000242668"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":2.1736,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85915493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"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":1.0,"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":1.0,"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":0.9988999962806702,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983999729156494,"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/spmd","display_name":"SPMD","score":0.9598528146743774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393845558166504},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6528695225715637},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.63680100440979},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.5179101824760437},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.46480312943458557},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.43526989221572876},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34700876474380493},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21964532136917114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18985489010810852},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.05630195140838623},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05427682399749756}],"concepts":[{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.9598528146743774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393845558166504},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6528695225715637},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.63680100440979},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5179101824760437},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.46480312943458557},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43526989221572876},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34700876474380493},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21964532136917114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18985489010810852},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.05630195140838623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05427682399749756},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3585341.3585342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3585341.3585342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3585341.3585342","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3585341.3585342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3585341.3585342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3585341.3585342","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4405971636","display_name":"GW4 Tier-2 HPC Centre for Advanced Architectures","funder_award_id":"EP/T022078/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320331","display_name":"Met Office","ror":"https://ror.org/01ch2yn61"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362675393.pdf","grobid_xml":"https://content.openalex.org/works/W4362675393.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1991592471","https://openalex.org/W2146411490","https://openalex.org/W2149234156","https://openalex.org/W2153185479","https://openalex.org/W2489197585","https://openalex.org/W3016205154","https://openalex.org/W3017538311","https://openalex.org/W3018019719","https://openalex.org/W3116487210","https://openalex.org/W3144168681","https://openalex.org/W3158823657","https://openalex.org/W3204255478","https://openalex.org/W4224256145","https://openalex.org/W4225278845","https://openalex.org/W4283820265","https://openalex.org/W4289522463","https://openalex.org/W4321446270","https://openalex.org/W4362675185","https://openalex.org/W6606521517"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"More":[0],"and":[1,4],"more":[2],"frameworks":[3],"simulations":[5],"are":[6],"developed":[7],"using":[8],"heterogeneous":[9],"programming":[10],"models":[11,25],"such":[12,38],"as":[13],"OpenCL,":[14],"SYCL,":[15],"CUDA,":[16],"or":[17],"HIP.":[18],"A":[19],"significant":[20],"hurdle":[21],"to":[22,26],"mapping":[23],"these":[24],"CPUs":[27],"in":[28],"a":[29],"performance-portable":[30],"manner":[31],"is":[32],"that":[33,45],"implementing":[34],"work-group":[35],"barriers":[36],"for":[37],"kernels":[39],"requires":[40],"providing":[41],"forward-progress":[42],"guarantees":[43],"so":[44],"all":[46],"work-items":[47],"can":[48],"reach":[49],"the":[50],"barrier.":[51]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}