{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:22:53Z","timestamp":1774120973089,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624164","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"876-883","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["OpenMP Kernel Language Extensions for Performance Portable GPU Codes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6468-6839","authenticated-orcid":false,"given":"Shilei","family":"Tian","sequence":"first","affiliation":[{"name":"Stony Brook University, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7234-5743","authenticated-orcid":false,"given":"Tom","family":"Scogland","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8449-8579","authenticated-orcid":false,"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[{"name":"Stony Brook University, United States of America and Hewlett Packard Enterprise, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7870-8963","authenticated-orcid":false,"given":"Johannes","family":"Doerfert","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"AMD. 2023. HIP Documentation. https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/latest\/"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"e_1_3_2_2_3_1","volume-title":"MILC Code Performance on High End CPU and GPU Supercomputer Clusters. arXiv 175 (11","author":"DeTar Carleton","year":"2017","unstructured":"Carleton DeTar, Steven Gottlieb, Ruizi Li, and Doug Toussaint. 2017. MILC Code Performance on High End CPU and GPU Supercomputer Clusters. arXiv 175 (11 2017), 1\u20138. arxiv:1712.00143"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569687"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00055"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577504"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554736"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741290"},{"key":"e_1_3_2_2_10_1","unstructured":"International Organization for Standardization. 2017. Programming languages \u2014 C++. https:\/\/www.iso.org\/standard\/68564.html"},{"key":"e_1_3_2_2_11_1","unstructured":"Zheming Jin. 2023. HeCBench. https:\/\/github.com\/zjin-lcf\/HeCBench"},{"key":"e_1_3_2_2_12_1","unstructured":"Khronos OpenCL Working Group. 2023. The OpenCL Specification. https:\/\/registry.khronos.org\/OpenCL\/specs\/3.0-unified\/pdf\/OpenCL_API.pdf"},{"key":"e_1_3_2_2_13_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR). arXiv","author":"P.","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR). arXiv, San Diego, CA, USA, 1\u201315. http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15922-0_2"},{"key":"e_1_3_2_2_15_1","volume-title":"Improving GPU-accelerated Adaptive IDW Interpolation Algorithm Using Fast kNN Search. CoRR abs\/1601.05904","author":"Mei Gang","year":"2016","unstructured":"Gang Mei, Nengxiong Xu, and Liangliang Xu. 2016. Improving GPU-accelerated Adaptive IDW Interpolation Algorithm Using Fast kNN Search. CoRR abs\/1601.05904 (2016), 1\u201312. arXiv:1601.05904http:\/\/arxiv.org\/abs\/1601.05904"},{"key":"e_1_3_2_2_16_1","unstructured":"NVIDIA. 2023. cuBLAS. https:\/\/docs.nvidia.com\/cuda\/pdf\/CUBLAS_Library.pdf"},{"key":"e_1_3_2_2_17_1","unstructured":"OpenMP ARB. 2021. OpenMP Application Programming Interface. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-5-2.pdf"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-07312-0_16"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.anucene.2012.06.040"},{"key":"e_1_3_2_2_20_1","unstructured":"Mark Segal and Kurt Akeley. 2022. The OpenGL Graphics System: A Specification. https:\/\/registry.khronos.org\/OpenGL\/specs\/gl\/glspec46.core.pdf"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","unstructured":"Baodi Shan Mauricio Araya-Polo Abid\u00a0M. Malik and Barbara\u00a0M. Chapman. 2023. MPI-based Remote OpenMP Offloading: A More Efficient and Easy-to-use Implementation. In International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM). ACM Montreal QC Canada 50\u201359. https:\/\/doi.org\/10.1145\/3582514.3582519","DOI":"10.1145\/3582514.3582519"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89740-8_2"},{"key":"e_1_3_2_2_23_1","volume-title":"SYCL 2020 Specification. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/pdf\/sycl-2020","author":"The Khronos SYCL Working Group","year":"2020","unstructured":"The Khronos SYCL Working Group. 2020. SYCL 2020 Specification. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/pdf\/sycl-2020.pdf"},{"key":"e_1_3_2_2_24_1","unstructured":"The Khronos Vulkan Working Group. 2022. Vulkan - A Specification. https:\/\/registry.khronos.org\/vulkan\/specs\/1.3-extensions\/pdf\/vkspec.pdf"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85262-7_11"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95953-1_4"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15976-8_3"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.11484\/jaea-conf-2014-003"}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624164","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:02:48Z","timestamp":1755745368000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":28,"alternative-id":["10.1145\/3624062.3624164","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624164","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}