{"id":"https://openalex.org/W4319067145","doi":"https://doi.org/10.1145/3581576.3581609","title":"Optimization of NumPy Transcendental Functions for Arm SVE","display_name":"Optimization of NumPy Transcendental Functions for Arm SVE","publication_year":2023,"publication_date":"2023-02-03","ids":{"openalex":"https://openalex.org/W4319067145","doi":"https://doi.org/10.1145/3581576.3581609"},"language":"en","primary_location":{"id":"doi:10.1145/3581576.3581609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581576.3581609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the HPC Asia 2023 Workshops","raw_type":"proceedings-article"},"type":"article","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/A5002035728","display_name":"Fuyuka Yamada","orcid":"https://orcid.org/0000-0003-4867-0903"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Fuyuka Yamada","raw_affiliation_strings":["Fujitsu Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Ltd., Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041721902","display_name":"Kentaro Kawakami","orcid":"https://orcid.org/0000-0002-3248-1190"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Kawakami","raw_affiliation_strings":["Fujitsu Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Ltd., Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105459197","display_name":"Kouji Kurihara","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouji Kurihara","raw_affiliation_strings":["Fujitsu Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Ltd., Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077631093","display_name":"Kazuhito Matsuda","orcid":"https://orcid.org/0000-0001-6495-0636"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhito Matsuda","raw_affiliation_strings":["Fujitsu Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Ltd., Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034919372","display_name":"Tsuguchika Tabaru","orcid":"https://orcid.org/0000-0001-6568-1968"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuguchika Tabaru","raw_affiliation_strings":["Fujitsu Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Ltd., Japan","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002035728"],"corresponding_institution_ids":["https://openalex.org/I2252096349"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50967063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.949999988079071,"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/T13126","display_name":"Scientific Research and Discoveries","score":0.9236999750137329,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.9031314849853516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759329080581665},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6428503394126892},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.627721905708313},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6109678745269775},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.5604568123817444},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4055386185646057},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32804155349731445},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25176626443862915},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.12123620510101318}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.9031314849853516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759329080581665},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6428503394126892},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.627721905708313},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6109678745269775},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.5604568123817444},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4055386185646057},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32804155349731445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25176626443862915},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.12123620510101318}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581576.3581609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581576.3581609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the HPC Asia 2023 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":2,"referenced_works":["https://openalex.org/W2613264175","https://openalex.org/W3123542955"],"related_works":["https://openalex.org/W2148967747","https://openalex.org/W4256534760","https://openalex.org/W3008658471","https://openalex.org/W2133860611","https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W1582436825","https://openalex.org/W1486009489","https://openalex.org/W1996803181","https://openalex.org/W2979588510"],"abstract_inverted_index":{"The":[0],"high-performance":[1],"computing":[2,32],"instruction":[3],"set":[4],"for":[5,58,120],"the":[6,19,28,86],"Arm":[7],"processors,":[8],"Scalable":[9],"Vector":[10],"Extension":[11],"(SVE),":[12],"is":[13,50,55,68,75],"adopted":[14],"in":[15,23,47],"\"Fujitsu":[16],"A64FX\"":[17],"of":[18,25,116],"Fugaku":[20],"supercomputer,":[21],"and":[22,41,90,105],"\"Graviton3\"":[24],"AWS.":[26],"NumPy,":[27],"primary":[29],"Python":[30,59],"numerical":[31,60],"package,":[33],"does":[34],"not":[35],"support":[36],"SVE.":[37,80],"Large-scale":[38],"machine":[39],"learning":[40],"other":[42],"applications":[43],"are":[44],"often":[45,56],"implemented":[46],"Python,":[48],"which":[49],"easy":[51],"to":[52,77],"implement.":[53],"NumPy":[54,87],"used":[57],"operations.":[61],"Therefore,":[62],"even":[63],"if":[64],"such":[65],"an":[66,71],"application":[67],"executed":[69],"on":[70,94],"SVE-capable":[72],"processor,":[73],"it":[74],"unable":[76],"benefit":[78],"from":[79],"For":[81],"this":[82],"study,":[83],"we":[84,109],"assessed":[85],"performance":[88],"before":[89],"after":[91],"implementing":[92],"SVE":[93],"A64FX.":[95],"Results":[96],"show":[97],"that,":[98],"by":[99],"Single":[100],"Instruction":[101],"Multiple":[102],"Data,":[103],"inlining,":[104],"loop-unrolling":[106],"number":[107],"optimization,":[108],"achieved":[110],"about":[111],"six":[112],"times":[113],"speeding":[114],"up":[115],"transcendental":[117],"function":[118],"processing":[119],"array":[121],"data.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}