{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:13:28Z","timestamp":1774473208148,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Japan Science and Technology Agency (JST) Support for Pioneering Research Initiated by the Next Generation","award":["JPMJSP2125"],"award-info":[{"award-number":["JPMJSP2125"]}]},{"name":"Joint Usage\/Research Center for Interdisciplinary Large-Scale Information Infrastructures (JHPCN) and the High-Performance Computing Infrastructure","award":["jh250015"],"award-info":[{"award-number":["jh250015"]}]},{"name":"Joint Usage\/Research Center for Interdisciplinary Large-Scale Information Infrastructures (JHPCN) and the High-Performance Computing Infrastructure","award":["jh250018"],"award-info":[{"award-number":["jh250018"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP23K11126"],"award-info":[{"award-number":["JP23K11126"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP24K02945"],"award-info":[{"award-number":["JP24K02945"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3675604","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:08:18Z","timestamp":1773950898000},"page":"43679-43693","source":"Crossref","is-referenced-by-count":0,"title":["Learning-Augmented Performance Model for Tensor Product Factorization in High-Order FEM"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2784-4540","authenticated-orcid":false,"given":"Xuanzhengbo","family":"Ren","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}]},{"given":"Yuta","family":"Kawai","sequence":"additional","affiliation":[{"name":"Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"}]},{"given":"Tetsuya","family":"Hoshino","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}]},{"given":"Hirofumi","family":"Tomita","sequence":"additional","affiliation":[{"name":"Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"}]},{"given":"Takahiro","family":"Katagiri","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}]},{"given":"Daichi","family":"Mukunoki","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}]},{"given":"Seiya","family":"Nishizawa","sequence":"additional","affiliation":[{"name":"Computational Climate Science Research Team, RIKEN Center for Computational Science (R-CCS), Kobe, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref2","article-title":"Execution-cache-memory performance model: Introduction and validation","author":"Hofmann","year":"2015","journal-title":"arXiv:1509.03118"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.cma.2019.04.031","article-title":"Sum factorization techniques in isogeometric analysis","volume":"352","author":"Bressan","year":"2019","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1016\/j.finel.2020.103385","article-title":"Sum factorization for fast integration of DPG matrices on prismatic elements","volume":"172","author":"Badger","year":"2020","journal-title":"Finite Elements Anal. Design"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3703001.3724385"},{"key":"ref6","first-page":"615","article-title":"SwDNN: A library for accelerating deep learning applications on sunway TaihuLight","volume-title":"Proc. IEEE Int. Parallel Distrib. Process. Symp. (IPDPS)","author":"Fang"},{"key":"ref7","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Conf. Operating Syst. Design Implement.","author":"Chen"},{"key":"ref8","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/1094342018816368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"issue":"6","key":"ref11","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1175\/MWR-D-22-0245.1","article-title":"Numerical accuracy necessary for large-eddy simulation of planetary boundary layer turbulence using the discontinuous Galerkin method","volume":"151","author":"Kawai","year":"2023","journal-title":"Monthly Weather Rev."},{"issue":"3","key":"ref12","doi-asserted-by":"crossref","first-page":"725","DOI":"10.5194\/gmd-18-725-2025","article-title":"Development of a high-order global dynamical core using the discontinuous Galerkin method for an atmospheric large-eddy simulation (LES) and proposal of test cases: SCALE-DG v0.8.0","volume":"18","author":"Kawai","year":"2025","journal-title":"Geoscientific Model Develop."},{"key":"ref13","first-page":"150","article-title":"Implementing fast modal filtering of SCALE-DG","volume-title":"Proc. IEEE Int. Conf. Cluster Comput. Workshops (CLUSTER Workshops)","author":"Ren"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250712"},{"key":"ref15","volume-title":"RRZE-HPC\/OSACA","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/a:1026431920605"},{"key":"ref17","volume-title":"A64FX Microarchitecture Manual V1.8.1","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304062"},{"key":"ref19","first-page":"52","article-title":"Theoretical modeling of superscalar processor performance","volume-title":"Proc. 27th Annu. Int. Symp. Microarchitecture","author":"Noonburg"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101805"},{"key":"ref21","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241303884"},{"key":"ref23","volume-title":"LLVM-MCA-LLVM Machine Code Analyzer-LLVM 22.0.0git Documentation","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1534909.1534910"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063454"},{"issue":"12","key":"ref26","first-page":"3537","article-title":"Analytical processor performance and power modeling using micro-architecture independent characteristics","volume":"65","author":"Van den Steen","year":"2016","journal-title":"IEEE Trans. Comput."},{"issue":"1","key":"ref27","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/L-CA.2013.6","article-title":"Cache-aware roofline model: Upgrading the loft","volume":"13","author":"Ilic","year":"2014","journal-title":"IEEE Comput. Archit. Lett."},{"key":"ref28","first-page":"222","article-title":"Extending the roofline model: Bottleneck analysis with microarchitectural constraints","volume-title":"Proc. IEEE Int. Symp. Workload Characterization (IISWC)","author":"Cabezas"},{"key":"ref29","first-page":"121","article-title":"Automated instruction stream throughput prediction for Intel and AMD microarchitectures","volume-title":"Proc. IEEE\/ACM Perform. Model., Benchmarking Simul. High Perform. Comput. Syst. (PMBS)","author":"Laukemann"},{"key":"ref30","first-page":"1","article-title":"Automatic throughput and critical path analysis of x86 and ARM assembly kernels","volume-title":"Proc. IEEE\/ACM Perform. Model., Benchmarking Simul. High Perform. Comput. Syst. (PMBS)","author":"Laukemann"},{"key":"ref31","first-page":"87","article-title":"Facile: Fast, accurate, and interpretable basic-block throughput prediction","volume-title":"Proc. IEEE Int. Symp. Workload Characterization (IISWC)","author":"Abel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3505285"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6591"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-99857-7_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3424144"},{"key":"ref36","first-page":"387","article-title":"A learned performance model for tensor processing units","volume-title":"Proc. Mach. Learn. Syst.","author":"Kaufman"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575737"},{"key":"ref38","article-title":"COGNATE: Acceleration of sparse tensor programs on emerging hardware using transfer learning","author":"Sudusinghe","year":"2025","journal-title":"arXiv:2506.00424"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6512"},{"key":"ref40","volume-title":"RRZE-HPC\/ECM-Model: Knowledge Base How To Setup the ECM Model Inputs","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11443259.pdf?arnumber=11443259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:57:46Z","timestamp":1774468666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3675604","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}