{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T02:39:32Z","timestamp":1789871972694,"version":"4.0.1"},"reference-count":27,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2025,4,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Modern accelerators use hierarchical parallel programming models that enable massive multithreading within a processing element (PE), with multiple PEs per device driven by traditional processes. Batching is a technique for exposing PE-level parallelism in algorithms that have traditionally run on MPI processes or multiple threads within a single process. Opportunities for batching arise in, for example, kinetic discretizations of magnetized plasmas where collisions are advanced in velocity space at each spatial point independently. This paper builds on previous work on a high-performance, fully nonlinear, Landau collision operator by batching the linear solver, as well as batching the spatial point problems and adding new support for multiple grids for multiscale, multispecies problems. An anisotropic relaxation verification test that agrees well with previously published results and analytical models is presented. The performance results from NVIDIA A100 and AMD MI250X nodes are presented with hardware utilization analysis for each architecture. The entire implicit Landau operator time advance is implemented in Kokkos for performance portability, running entirely on the device and is available in the PETSc numerical library.<\/jats:p>\n                  <jats:p>Reproducibility of computational results. This paper has been awarded the \u201cSIAM Reproducibility Badge: Code and data available\u201d as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https:\/\/gitlab.com\/markadams4\/batch_paper_data and in the supplementary materials ( batch_paper_data-main.zip [9.15MB]). [Formula: see text]<\/jats:p>","DOI":"10.1137\/24m1640252","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T04:04:31Z","timestamp":1741665871000},"page":"B360-B381","source":"Crossref","is-referenced-by-count":5,"title":["A Performance Portable, Fully Implicit Landau Collision Operator with Batched Linear Solvers"],"prefix":"10.1137","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-2047","authenticated-orcid":true,"given":"Mark F.","family":"Adams","sequence":"first","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA 94720 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, CA 95050 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"Merson","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY 12180 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Huck","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR 97403 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2292-0735","authenticated-orcid":true,"given":"Matthew G.","family":"Knepley","sequence":"additional","affiliation":[{"name":"University of Buffalo, Buffalo, NY 14260 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"M. F. Adams, D. P. Brennan, M. G. Knepley, and P. Wang, Landau collision operator in the CUDA programming model applied to thermal quench plasmas, in Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2022, pp. 115\u2013123, https:\/\/doi.org\/10.1109\/IPDPS53621.2022.00020.","DOI":"10.1109\/IPDPS53621.2022.00020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/17M1118828"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"I. Aggarwal, A. Kashi, P. Nayak, C. J. Balos, C. S. Woodward, and H. Anzt, Batched sparse iterative solvers for computational chemistry simulations on GPUs, in Proceedings of the 12th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA), 2021, pp. 35\u201343, https:\/\/doi.org\/10.1109\/ScalA54577.2021.00010.","DOI":"10.1109\/ScalA54577.2021.00010"},{"key":"ref4","first-page":"218","volume":"1","author":"Beliaev S. T.","year":"1956","journal-title":"Soviet Physics Doklady"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.09.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.59.1817"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1063\/1.873738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1063\/1.2751603"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2016.03.064"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6587\/abe884"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1063\/1.4979122"},{"key":"ref13","volume-title":"NRL PLASMA FORMULARY Supported by The Office of Naval Research","author":"Huba J. D.","year":"2013"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"A. Kashi, P. Nayak, D. Kulkarni, A. Scheinberg, P. Lin, and H. Anzt, Batched sparse iterative solvers on gpu for the collision operator for fusion plasma simulations, in Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2022, pp. 157\u2013167, https:\/\/doi.org\/10.1109\/IPDPS53621.2022.00024.","DOI":"10.1109\/IPDPS53621.2022.00024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1063\/1.4998610"},{"key":"ref16","first-page":"154","volume":"10","author":"Landau L. D.","year":"1936","journal-title":"Phys. Z. Sowjetunion"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113188"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3249110"},{"key":"ref19","unstructured":"J. Merson and M. S. Shephard, Using Hierarchical Parallelism to Accelerate the Solution of Many Small Partial Differential Equations, preprint, https:\/\/arxiv.org\/abs\/2305.07030, 2023."},{"key":"ref20","unstructured":"R. T. Mills, M. Adams, S. Balay, J. Brown, J. Faibussowitsch, T. Isaac, M. Knepley, T. Munson, H. Suh, S. Zampini, H. Zhang, and J. Zhang, PETSc\/TAO Developments for Early Exascale Systems, preprint, https:\/\/arxiv.org\/abs\/2406.08646, 2024."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/21M1454079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.99.053309"},{"key":"ref24","unstructured":"Simulation modeling suite, 2023, http:\/\/www.simmetrix.com\/index.php\/simulation-modeling-suite (accessed 2023-05-05)."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1063\/1.3519513"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1070\/PU1968v010n06ABEH003709"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"F. Zonta, J. V. Pusztay, and E. Hirvijoki, Multispecies structure-preserving particle discretization of the Landau collision operator, Phys. Plasmas, 29 (2022), 123906, https:\/\/doi.org\/10.1063\/5.0105182.","DOI":"10.1063\/5.0105182"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/24M1640252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T17:58:17Z","timestamp":1787335097000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1640252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4,30]]}},"alternative-id":["10.1137\/24M1640252"],"URL":"https:\/\/doi.org\/10.1137\/24m1640252","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]}}}