{"id":"https://openalex.org/W4388581111","doi":"https://doi.org/10.1145/3624062.3624177","title":"Performance Portability Evaluation of Blocked Stencil Computations on GPUs","display_name":"Performance Portability Evaluation of Blocked Stencil Computations on GPUs","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581111","doi":"https://doi.org/10.1145/3624062.3624177"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624177","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035719658","display_name":"Oscar Antepara","orcid":"https://orcid.org/0000-0002-4596-0289"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Antepara","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4596-0289","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8327-5717","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082013692","display_name":"Hans Johansen","orcid":"https://orcid.org/0000-0002-9644-9982"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Johansen","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9644-9982","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033875105","display_name":"Tuowen Zhao","orcid":"https://orcid.org/0000-0002-6347-7135"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuowen Zhao","raw_affiliation_strings":["University of Utah, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6347-7135","affiliations":[{"raw_affiliation_string":"University of Utah, United States of America","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046632473","display_name":"Samantha Hirsch","orcid":"https://orcid.org/0009-0009-5237-637X"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samantha Hirsch","raw_affiliation_strings":["University of Utah, United States of America"],"raw_orcid":"https://orcid.org/0009-0009-5237-637X","affiliations":[{"raw_affiliation_string":"University of Utah, United States of America","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035445731","display_name":"Priya Goyal","orcid":"https://orcid.org/0009-0009-3125-9123"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priya Goyal","raw_affiliation_strings":["University of Utah, United States of America"],"raw_orcid":"https://orcid.org/0009-0009-3125-9123","affiliations":[{"raw_affiliation_string":"University of Utah, United States of America","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3058-7573","affiliations":[{"raw_affiliation_string":"University of Utah, United States of America","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5055,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94590846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1007","last_page":"1018"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.9986000061035156,"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/software-portability","display_name":"Software portability","score":0.9010351896286011},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8897075653076172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8793348073959351},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7427315711975098},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.74271559715271},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.697867751121521},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.47624921798706055},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4666210412979126},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4650111794471741},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4552539587020874},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4407818913459778},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4122188687324524},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36544719338417053},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.25654542446136475},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.25523704290390015},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.22755134105682373},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19900894165039062},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.16835254430770874},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1637459397315979}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.9010351896286011},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8897075653076172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8793348073959351},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7427315711975098},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.74271559715271},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.697867751121521},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.47624921798706055},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4666210412979126},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4650111794471741},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4552539587020874},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4407818913459778},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4122188687324524},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36544719338417053},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.25654542446136475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25523704290390015},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.22755134105682373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19900894165039062},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.16835254430770874},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1637459397315979},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3624062.3624177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624177","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt3d66m06t","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3d66m06t","pdf_url":"https://escholarship.org/content/qt3d66m06t/qt3d66m06t.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:ark:/13030/qt3d66m06t","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3624062.3624177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624177","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1071216263","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2366088775","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G2638771445","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G2900453181","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3944918260","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4327825534","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5723425519","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7368046788","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581111.pdf","grobid_xml":"https://content.openalex.org/works/W4388581111.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1492882524","https://openalex.org/W1774469134","https://openalex.org/W1979457157","https://openalex.org/W1997147891","https://openalex.org/W1997375049","https://openalex.org/W2002555321","https://openalex.org/W2003798513","https://openalex.org/W2016618963","https://openalex.org/W2035430533","https://openalex.org/W2039378765","https://openalex.org/W2076028817","https://openalex.org/W2104512032","https://openalex.org/W2113190809","https://openalex.org/W2128746953","https://openalex.org/W2150319905","https://openalex.org/W2152914333","https://openalex.org/W2160106616","https://openalex.org/W2486796129","https://openalex.org/W2599011453","https://openalex.org/W2607112060","https://openalex.org/W2613618711","https://openalex.org/W2743401659","https://openalex.org/W2903775786","https://openalex.org/W2918924644","https://openalex.org/W2984920043","https://openalex.org/W2994151208","https://openalex.org/W3020936970","https://openalex.org/W3147517636","https://openalex.org/W3152199537","https://openalex.org/W3153525491","https://openalex.org/W4200140025","https://openalex.org/W4200626107","https://openalex.org/W4229701516","https://openalex.org/W4230033531","https://openalex.org/W4232301837","https://openalex.org/W4249968602","https://openalex.org/W4318603305","https://openalex.org/W6931846337","https://openalex.org/W7134224534"],"related_works":["https://openalex.org/W3100998497","https://openalex.org/W1999524790","https://openalex.org/W2130241392","https://openalex.org/W3106055984","https://openalex.org/W2996929894","https://openalex.org/W4223480868","https://openalex.org/W2111914791","https://openalex.org/W2244508497","https://openalex.org/W4251625807","https://openalex.org/W2246512960"],"abstract_inverted_index":{"In":[0,52],"this":[1,53],"new":[2,30,132],"era":[3],"where":[4,35],"multiple":[5,14],"GPU":[6],"vendors":[7],"are":[8,17,38],"leading":[9],"the":[10,21,43,60,77],"supercomputing":[11],"landscape,":[12],"and":[13,46,64,92,94,101,137],"programming":[15,97,123,138],"models":[16,98,129,139],"available":[18],"to":[19,23,40,75],"users,":[20],"drive":[22],"achieve":[24],"performance":[25,57,118],"portability":[26,58],"across":[27],"platforms":[28],"faces":[29],"challenges.":[31],"Consider":[32],"stencil":[33,109],"algorithms,":[34],"architecture-specific":[36],"solutions":[37],"required":[39],"optimize":[41],"for":[42,68,134],"parallelism":[44],"hierarchy":[45,48],"memory":[47],"of":[49,59,80,108,120],"emerging":[50],"systems.":[51],"work,":[54],"we":[55,111,126],"analyze":[56],"BrickLib":[61,70,115],"domain-specific":[62],"library":[63],"vector":[65],"code":[66],"generator":[67],"stencils.":[69,85],"employs":[71],"fine-grain":[72],"data":[73,81],"blocking":[74],"reduce":[76],"large":[78],"amount":[79],"movement":[82],"associated":[83,96],"with":[84],"We":[86],"compare":[87],"different":[88],"GPUs":[89],"(NVIDIA,":[90],"AMD":[91],"Intel)":[93],"their":[95],"(CUDA,":[99],"HIP":[100],"SYCL).":[102],"By":[103],"testing":[104],"a":[105,131],"wide":[106],"range":[107],"configurations,":[110],"show":[112],"that":[113],"overall,":[114],"achieves":[116],"good":[117],"independent":[119],"machine":[121],"or":[122],"model.":[124],"Moreover,":[125],"introduce":[127],"correlation":[128],"as":[130],"tool":[133],"comparing":[135],"architectures":[136],"from":[140],"Roofline":[141],"model":[142],"data.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}
