{"id":"https://openalex.org/W4205652951","doi":"https://doi.org/10.1145/3503470.3503476","title":"Performance tuning of the Helmholtz matrix-vector product kernel in the computational fluid dynamics solver Nek5000/RS for the A64FX processor","display_name":"Performance tuning of the Helmholtz matrix-vector product kernel in the computational fluid dynamics solver Nek5000/RS for the A64FX processor","publication_year":2022,"publication_date":"2022-01-11","ids":{"openalex":"https://openalex.org/W4205652951","doi":"https://doi.org/10.1145/3503470.3503476"},"language":"en","primary_location":{"id":"doi:10.1145/3503470.3503476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503470.3503476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on High Performance Computing in Asia-Pacific Region Workshops","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/A5079973660","display_name":"Miwako Tsuji","orcid":"https://orcid.org/0000-0003-4709-1969"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miwako Tsuji","raw_affiliation_strings":["RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN, Japan","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029616613","display_name":"Misun Min","orcid":"https://orcid.org/0000-0002-5646-5689"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Misun Min","raw_affiliation_strings":["Argonne National Laboratory, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080842672","display_name":"Stefan Kerkemeier","orcid":"https://orcid.org/0009-0002-3715-2641"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Kerkemeier","raw_affiliation_strings":["Argonne National Laboratory, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081088881","display_name":"Paul Fischer","orcid":"https://orcid.org/0000-0002-6506-4502"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Fischer","raw_affiliation_strings":["University of Illinois, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, United States","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046254414","display_name":"Elia Merzari","orcid":"https://orcid.org/0000-0003-0174-7424"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elia Merzari","raw_affiliation_strings":["Penn State University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040254066","display_name":"Mitsuhisa Sato","orcid":"https://orcid.org/0000-0003-0543-7116"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mitsuhisa Sato","raw_affiliation_strings":["RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN, Japan","institution_ids":["https://openalex.org/I4210110652"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2318,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3109666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11694","display_name":"Fluid Dynamics Simulations and Interactions","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7908759117126465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.742885410785675},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6772860288619995},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5519673824310303},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5118059515953064},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4502895176410675},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42981988191604614},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4178202450275421},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37683385610580444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1825253963470459},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06978872418403625}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7908759117126465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742885410785675},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6772860288619995},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5519673824310303},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5118059515953064},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4502895176410675},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42981988191604614},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4178202450275421},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37683385610580444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1825253963470459},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06978872418403625},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503470.3503476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503470.3503476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on High Performance Computing in Asia-Pacific Region Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3155036733","https://openalex.org/W4287815141","https://openalex.org/W6775510394"],"related_works":["https://openalex.org/W1604758548","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W1549048322","https://openalex.org/W2804126825","https://openalex.org/W2011940952","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2144429051","https://openalex.org/W2981935664"],"abstract_inverted_index":{"Nek5000/RS":[0,22],"is":[1,23],"an":[2],"open":[3],"source":[4],"computational":[5],"fluid":[6],"dynamics":[7],"solver":[8],"based":[9],"on":[10,41],"the":[11,17,21,28,38,42,46,58,61,84,90,93,99,103],"spectral":[12],"element":[13],"method.":[14],"One":[15],"of":[16,20,49,92],"important":[18],"kernel":[19,40,59],"called":[24],"\u201caxhelm\u201d,":[25],"which":[26],"computes":[27],"Helmholtz":[29],"matrix-vector":[30],"product.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"have":[36,56],"evaluated":[37],"axhelm":[39],"A64FX":[43,62,100],"processor":[44,63,101],"for":[45,60],"simplest":[47],"case":[48],"polynomial":[50],"degree":[51],"N":[52],"=":[53],"7.":[54],"We":[55,81],"optimized":[57],"by":[64],"using":[65],"well":[66],"known":[67],"optimization":[68,94],"techniques":[69,95],"such":[70],"as":[71],"SIMDization,":[72],"software":[73,79],"pipelining,":[74],"continuous":[75],"access":[76],"enhancing,":[77],"and":[78,102],"prefetch.":[80],"also":[82],"provide":[83],"performance":[85],"analysis":[86],"data":[87],"to":[88,96],"investigate":[89],"effects":[91],"help":[97],"understanding":[98],"Fujitsu":[104],"compiler.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
