{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:33:35Z","timestamp":1759941215563,"version":"3.40.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"DOI":"10.1109\/hpec62836.2024.10938453","type":"proceedings-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:07:19Z","timestamp":1743707239000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["JACC.shared: Leveraging HPC Metaprogramming and Performance Portability for Computations That Use Shared Memory GPUs"],"prefix":"10.1109","author":[{"given":"Pedro","family":"Valero-Lara","sequence":"first","affiliation":[{"name":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William F.","family":"Godoy","sequence":"additional","affiliation":[{"name":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[{"name":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[{"name":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bridging HPC Communities through the Julia Programming Language","author":"Churavy","year":"2022","journal-title":"submitted for review"},{"issue":"1","key":"ref2","first-page":"68","article-title":"MPI.jl: Julia bindings for the Message Passing Interface","volume-title":"Proceedings of the JuliaCon Conferences","volume":"1","author":"Byrne"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3302577"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/mcse.2021.3098509"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2021.3097283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"issue":"8","key":"ref7","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.3390\/rs12081257","article-title":"A new GPU implementation of support vector machines for fast hyperspectral image classification","volume":"12","author":"Paoletti","year":"2020","journal-title":"Remote. Sens."},{"issue":"3","key":"ref8","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1007\/s11227-011-0597-1","article-title":"A gpubased implementation of the MRF algorithm in ITK package","volume":"58","author":"Valero-Lara","year":"2011","journal-title":"J. Supercomput."},{"key":"ref9","first-page":"149","article-title":"MRF satellite image classification on GPU","volume-title":"41st International Conference on Parallel Processing Workshops, ICPPW 2012, Pittsburgh, PA, USA, September 10\u201313, 2012","author":"Valero-Lara"},{"issue":"11","key":"ref10","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1109\/JPROC.2016.2598228","article-title":"Big data for remote sensing: Challenges and opportunities","volume":"104","author":"Chi","year":"2016","journal-title":"Proc. IEEE"},{"key":"ref11","first-page":"373","article-title":"Evaluating performance and portability of high-level programming models: Julia, python\/numba, and kokkos on exascale nodes","volume-title":"IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023 - Workshops, St. Petersburg, FL, USA, May 15\u201319, 2023","author":"Godoy"},{"key":"ref12","first-page":"149","article-title":"MRF satellite image classification on GPU","volume-title":"41st International Conference on Parallel Processing Workshops, ICPPW 2012, Pittsburgh, PA, USA, September 10\u201313, 2012","author":"Valero-Lara"},{"issue":"2","key":"ref13","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/s11227-014-1262-2","article-title":"Accelerating solid-fluid interaction based on the immersed boundary method on multicore and GPU architectures","volume":"70","author":"Valero-Lara","year":"2014","journal-title":"J. Supercomput."},{"key":"ref14","first-page":"102","article-title":"hlcs. A hybrid GPGPU approach for solving multiple short and unbalanced LCS problems","volume-title":"Computational Science and Its Applications - ICCSA 2014\u201314th International Conference, Guimar\u00e3es, Portugal, June 30 - July 3, 2014, Proceedings, Part VI, ser. Lecture Notes in Computer Science","volume":"8584","author":"Valero-Lara"},{"key":"ref15","first-page":"656","article-title":"Similarity search implementations for multi-core and many-core processors","volume-title":"2011 International Conference on High Performance Computing & Simulation, HPCS 2012, Istanbul, Turkey, July 4\u20138, 2011","author":"Paredes"},{"issue":"2","key":"ref16","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/s11227-014-1262-2","article-title":"Accelerating solid-fluid interaction based on the immersed boundary method on multicore and GPU architectures","volume":"70","author":"Valero-Lara","year":"2014","journal-title":"J. Supercomput."},{"issue":"3","key":"ref17","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1109\/TPDS.2021.3098456","article-title":"Propagation pattern for moment representation of the lattice boltzmann method","volume":"33","author":"Gounley","year":"2022","journal-title":"IEEE Trans. Parallel Distributed Syst."},{"key":"ref18","first-page":"1697","article-title":"Moment representation of regularized lattice boltzmann methods on NVIDIA and AMD gpus","volume-title":"Proceedings of the SC \u201923 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, Denver, CO, USA, November 12\u201317, 2023","author":"Valero-Lara"},{"issue":"4","key":"ref19","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1016\/j.cpc.2013.12.026","article-title":"Fast finite difference poisson solvers on heterogeneous architectures","volume":"185","author":"Valero-Lara","year":"2014","journal-title":"Comput. Phys. Co\u0442\u0442\u0438\u043f."},{"key":"ref20","doi-asserted-by":"crossref","first-page":"63","DOI":"10.2516\/ogst\/2018061","article-title":"Simulating the behavior of the human brain on gpus","volume":"73","author":"Valero-Lara","year":"2018","journal-title":"Oil Gas Sci. Technol. - Rev. IFP Energies nouvelles"},{"key":"ref21","first-page":"495","article-title":"The design and performance of batched BLAS on modern high-performance computing systems","volume-title":"International Conference on Computational Science, ICCS 2017, 12\u201314 June 2017, Zurich, Switzerland, ser. Procedia Computer Science","volume":"108","author":"Dongarra"},{"key":"ref22","first-page":"256","article-title":"IRIS-BLAS: towards a performance portable and heterogeneous BLAS library","volume-title":"29th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2022, Bengaluru, India, December 18\u201321, 2022","author":"Miniskar"},{"issue":"2","key":"ref23","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1007\/s10586-021-03494-y","article-title":"cuconv: CUDA implementation of convolution for CNN inference","volume":"25","author":"Jord\u00e0","year":"2022","journal-title":"Clust. Comput."},{"key":"ref24","first-page":"3242","article-title":"Kokkacc: Enhancing kokkos with openacc","author":"Valero-Lara","year":"2022","journal-title":"9th Workshop on Accelerator Programming Using Directives, WACCPD@SC 2022, Dallas, TX, USA, November 13\u201318"}],"event":{"name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2024,9,23]]},"location":"Wakefield, MA, USA","end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10938401\/10938415\/10938453.pdf?arnumber=10938453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T08:11:53Z","timestamp":1743754313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/hpec62836.2024.10938453","relation":{},"subject":[],"published":{"date-parts":[[2024,9,23]]}}}