{"id":"https://openalex.org/W7139127243","doi":"https://doi.org/10.1109/access.2026.3675604","title":"Learning-Augmented Performance Model for Tensor Product Factorization in High-Order FEM","display_name":"Learning-Augmented Performance Model for Tensor Product Factorization in High-Order FEM","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139127243","doi":"https://doi.org/10.1109/access.2026.3675604"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3675604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3675604","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3675604","any_repository_has_fulltext":true},"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":["Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"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":null,"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/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":["Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Climate Science Research Team, RIKEN Center for Computational Science (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":null,"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":null,"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/A5122925842","display_name":"Seiya Nishizawa","orcid":null},"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":["Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39366337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"43679","last_page":"43693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7261000275611877,"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":0.7261000275611877,"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/T12303","display_name":"Tensor decomposition and applications","score":0.1331000030040741,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.032499998807907104,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/tensor-product","display_name":"Tensor product","score":0.6123999953269958},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5674999952316284},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.4821000099182129},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.45329999923706055},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4528000056743622},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.448199987411499},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44449999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.6123999953269958},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C77926391","wikidata":"https://www.wikidata.org/wiki/Q603880","display_name":"Finite field","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C180623205","wikidata":"https://www.wikidata.org/wiki/Q1268589","display_name":"Outer product","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25859999656677246}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2026.3675604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3675604","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2601.06886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06886","pdf_url":"https://arxiv.org/pdf/2601.06886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:d49dfd85fff44b3e82ed6f1800812c42","is_oa":true,"landing_page_url":"https://doaj.org/article/d49dfd85fff44b3e82ed6f1800812c42","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 43679-43693 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3675604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3675604","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1436303213","display_name":"Development of performance parameter optimization tools for automatic tuning","funder_award_id":"23K11126","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3660632507","display_name":null,"funder_award_id":"JPMJSP2125","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"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"},{"id":"https://openalex.org/G8547178248","display_name":"\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30a8\u30f3\u30b8\u30f3\u3068\u306e\u9023\u643a\u306b\u57fa\u3065\u304f\u81e8\u6a5f\u5fdc\u5909\u306a\u30b8\u30e7\u30d6\u30b9\u30b1\u30b8\u30e5\u30fc\u30ea\u30f3\u30b0\u306e\u5b9f\u73fe","funder_award_id":"24K02945","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"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"performance":[1,17,79],"prediction":[2],"is":[3,27,35,83,109],"essential":[4],"for":[5,29,37,55,96,184],"optimizing":[6],"scientific":[7],"applications":[8],"on":[9,21],"modern":[10],"high-performance":[11],"computing":[12],"(HPC)":[13],"architectures.":[14],"Widely":[15],"used":[16,159],"models":[18,91,199,239],"primarily":[19],"focus":[20],"cache":[22],"and":[23,101,162,182,197,204,228,237,244],"memory":[24],"bandwidth,":[25],"which":[26,50],"suitable":[28],"many":[30],"memory-bound":[31],"workloads.":[32],"However,":[33],"it":[34],"unsuitable":[36],"highly":[38],"arithmetic":[39],"intensive":[40],"cases":[41],"such":[42,73],"as":[43,74],"the":[44,75,78,129,142,153,157,167,171,194,208,214,234],"sum-factorization":[45],"with":[46,63],"tensorn-mode":[47,130],"product":[48,131],"kernels,":[49],"are":[51,92,146],"an":[52],"optimization":[53],"technique":[54],"high-order":[56],"finite":[57],"element":[58],"methods":[59],"(FEM).":[60],"On":[61,166,207],"processors":[62],"relatively":[64],"high":[65],"single":[66],"instruction":[67,71,126],"multiple":[68],"data":[69],"(SIMD)":[70],"latency,":[72],"Fujitsu":[76,168],"A64FX,":[77],"of":[80,202,242],"these":[81,98],"kernels":[82],"strongly":[84],"influenced":[85],"by":[86],"loop-body":[87],"splitting":[88,99],"strategies.":[89],"Memory-bandwidth-oriented":[90],"therefore":[93],"not":[94],"appropriate":[95],"evaluating":[97],"configurations,":[100],"a":[102,117],"model":[103,144,149,155,173,216],"that":[104,121,145],"directly":[105],"reflects":[106],"instruction-level":[107],"efficiency":[108],"required.":[110],"To":[111],"address":[112],"this":[113],"need,":[114],"we":[115],"develop":[116],"dependency-chain\u2013based":[118],"analytical":[119,143],"formulation":[120],"links":[122],"loop-splitting":[123],"configurations":[124],"to":[125,137,148,190,222],"dependencies":[127],"in":[128,141],"kernel.":[132],"We":[133],"further":[134],"use":[135],"XGBoost":[136],"estimate":[138],"key":[139],"parameters":[140],"difficult":[147],"explicitly.":[150],"Evaluations":[151],"showthat":[152],"learning-augmented":[154,172,215],"outperforms":[156],"widely":[158],"standard":[160,195,235],"Roofline":[161,196,236],"Execution-Cache-Memory":[163],"(ECM)":[164],"models.":[165],"A64FX":[169],"processor,":[170,213],"achieves":[174,217],"mean":[175],"absolute":[176],"percentage":[177],"errors":[178,201,241],"(MAPE)":[179],"between":[180],"1%":[181,221],"24%":[183,229],"polynomial":[185],"orders":[186],"(P)":[187],"from":[188,220],"1":[189,225,247],"15.":[191,231],"In":[192,232],"comparison,":[193],"ECM":[198,238],"yield":[200],"42%\u2013256%":[203],"5%\u2013117%,":[205],"respectively.":[206,250],"Intel":[209],"Xeon":[210],"Gold":[211],"6230":[212],"MAPE":[218],"values":[219],"13%":[223],"forP=":[224,246],"toP=":[226,248],"14,":[227],"atP=":[230],"contrast,":[233],"produce":[240],"1%\u201373%":[243],"8%\u2013112%":[245],"15,":[249]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2026-03-20T00:00:00"}