{"id":"https://openalex.org/W4409591486","doi":"https://doi.org/10.1145/3703001.3724385","title":"Performance Evaluation of Loop Body Splitting for Fast Modal Filtering in SCALE-DG on A64FX","display_name":"Performance Evaluation of Loop Body Splitting for Fast Modal Filtering in SCALE-DG on A64FX","publication_year":2025,"publication_date":"2025-02-19","ids":{"openalex":"https://openalex.org/W4409591486","doi":"https://doi.org/10.1145/3703001.3724385"},"language":"en","primary_location":{"id":"doi:10.1145/3703001.3724385","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703001.3724385","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703001.3724385","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 2025 International Conference on High Performance Computing in Asia-Pacific Region Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3703001.3724385","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060197632","display_name":"Xuanzhengbo Ren","orcid":"https://orcid.org/0009-0001-2784-4540"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xuanzhengbo Ren","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0001-2784-4540","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091611103","display_name":"Yuta Kawai","orcid":"https://orcid.org/0000-0002-9964-955X"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Kawai","raw_affiliation_strings":["RIKEN R-CCS, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9964-955X","affiliations":[{"raw_affiliation_string":"RIKEN R-CCS, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012330250","display_name":"Hirofumi Tomita","orcid":"https://orcid.org/0000-0002-7154-8060"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Tomita","raw_affiliation_strings":["RIKEN R-CCS, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7154-8060","affiliations":[{"raw_affiliation_string":"RIKEN R-CCS, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038510654","display_name":"Seiya Nishizawa","orcid":"https://orcid.org/0000-0001-9457-7457"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiya Nishizawa","raw_affiliation_strings":["RIKEN R-CCS, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9457-7457","affiliations":[{"raw_affiliation_string":"RIKEN R-CCS, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078063020","display_name":"Takahiro Katagiri","orcid":"https://orcid.org/0000-0001-7193-9304"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Katagiri","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7193-9304","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101918467","display_name":"Tetsuya Hoshino","orcid":"https://orcid.org/0009-0004-5349-6852"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Hoshino","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0004-5349-6852","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035972892","display_name":"Daichi Mukunoki","orcid":"https://orcid.org/0000-0002-0051-6811"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Mukunoki","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0051-6811","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009492561","display_name":"Masatoshi Kawai","orcid":"https://orcid.org/0009-0003-1454-202X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Kawai","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0003-1454-202X","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106037488","display_name":"Toru Nagai","orcid":"https://orcid.org/0000-0002-5827-1220"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nagai","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5827-1220","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7378,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79888155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9747999906539917,"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":0.9747999906539917,"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/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.9585999846458435,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9368000030517578,"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/modal","display_name":"Modal","score":0.6722779273986816},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.6114755272865295},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5877612829208374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5838682651519775},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37497398257255554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2001446783542633},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15275460481643677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12898600101470947},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09330210089683533},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.0768451988697052}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6722779273986816},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.6114755272865295},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5877612829208374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5838682651519775},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37497398257255554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2001446783542633},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15275460481643677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12898600101470947},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09330210089683533},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0768451988697052},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703001.3724385","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703001.3724385","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703001.3724385","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 2025 International Conference on High Performance Computing in Asia-Pacific Region Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3703001.3724385","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703001.3724385","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703001.3724385","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 2025 International Conference on High Performance Computing in Asia-Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4073843068","display_name":null,"funder_award_id":"JPMJSP2125","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409591486.pdf","grobid_xml":"https://content.openalex.org/works/W4409591486.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2758250355","https://openalex.org/W3190673640","https://openalex.org/W4324053857","https://openalex.org/W4404099709"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W24774503","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Modern":[0],"general-purpose":[1],"central":[2],"processing":[3],"units":[4],"(CPUs)":[5],"benefit":[6],"from":[7,101],"the":[8,31,45,47,60,80,102,115,124,131,135,140,150,155,170,205],"integration":[9],"of":[10,22,50,63,134,152,157,172],"Single":[11],"Instruction,":[12],"Multiple":[13],"Data":[14],"(SIMD)":[15],"architectures.Scalable":[16],"Vector":[17],"Extensions":[18],"(SVE)":[19],"is":[20,30,73],"one":[21],"Arm's":[23],"SIMD":[24,51],"architectures":[25],"designed":[26],"for":[27],"HPC.Fujitsu's":[28],"A64FX":[29],"first":[32],"Armbased":[33],"processor":[34],"to":[35,107,174,201],"incorporate":[36],"hardware-implemented":[37],"SVE":[38],"alongside":[39],"High-Bandwidth":[40],"Memory":[41],"2":[42],"(HBM2).However,":[43],"in":[44,68,89,114,144,169,189],"A64FX,":[46],"high":[48],"latencies":[49],"instructions,":[52],"such":[53],"as":[54],"fused":[55],"multiply-add":[56],"(FMA),":[57],"combined":[58],"with":[59,110,139,176,192],"limited":[61],"capacity":[62],"reservation":[64],"stations,":[65],"can":[66,119],"result":[67],"inefficient":[69],"Out-of-Order":[70],"(OoO)":[71],"execution.SCALE-DG":[72],"an":[74,86,92,165],"atmospheric":[75],"dynamical":[76],"core":[77],"that":[78,184],"uses":[79],"discontinuous":[81],"Galerkin":[82],"Method":[83],"(DGM).Modal":[84],"filtering,":[85,98],"essential":[87],"procedure":[88],"SCALE-DG,":[90,145],"has":[91],"optimized":[93],"version":[94],"called":[95],"fast":[96,158],"modal":[97,159],"which":[99],"suffers":[100],"OoO":[103],"execution":[104],"issue":[105,118],"due":[106],"dot":[108,136],"products":[109],"long":[111],"vector":[112,132],"lengths":[113],"loop":[116,125,206],"body.This":[117],"be":[120],"alleviated":[121],"by":[122],"splitting":[123,178,204,210],"body":[126],"into":[127],"multiple":[128],"parts.However,":[129],"since":[130],"length":[133],"product":[137],"varies":[138],"polynomial":[141],"order":[142],"()":[143],"it":[146],"remains":[147],"unclear":[148],"how":[149],"number":[151],"splits":[153],"affects":[154],"performance":[156,187],"filtering.In":[160],"this":[161],"paper,":[162],"we":[163],"present":[164],"evaluation":[166],"across":[167],"values":[168],"range":[171],"3":[173],"11":[175],"different":[177],"numbers":[179],"and":[180],"combinations.The":[181],"results":[182],"indicate":[183],"when":[185],"7,":[186],"degraded":[188],"most":[190],"cases,":[191],"only":[193],"a":[194,212],"few":[195],"cases":[196],"achieving":[197],"positive":[198],"speedups":[199],"(1.01x":[200],"1.02x)":[202],"after":[203],"body.For":[207],"8":[208],"11,":[209],"had":[211],"consistently":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
