{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:23Z","timestamp":1755825023222,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"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"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624604","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"1906-1917","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparing a Naive and a Tree-Based N-Body Algorithm using Different Standard SYCL Implementations on Various Hardware"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1762-8429","authenticated-orcid":false,"given":"Tim","family":"Th\u00fcring","sequence":"first","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3574-0650","authenticated-orcid":false,"given":"Marcel","family":"Breyer","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-0212","authenticated-orcid":false,"given":"Dirk","family":"Pfl\u00fcger","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"volume-title":"Teralens - A parallel (quasar) microlensing code for multi-teraflop devices","author":"Alpay Aksel","key":"e_1_3_2_2_1_1","unstructured":"Aksel Alpay. 2019. Teralens - A parallel (quasar) microlensing code for multi-teraflop devices. University of Heidelberg. https:\/\/github.com\/illuhad\/teralens"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388658"},{"volume-title":"SpatialCL - a high performance library for the spatial processing of particles on GPUs","author":"Alpay Aksel","key":"e_1_3_2_2_3_1","unstructured":"Aksel Alpay. 2019. SpatialCL - a high performance library for the spatial processing of particles on GPUs. University of Heidelberg. https:\/\/github.com\/illuhad\/SpatialCL"},{"key":"e_1_3_2_2_4_1","unstructured":"AMD. 2020. \"Vega\" 7nm Instruction Set Architecture Reference Guide. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/radeon-tech-docs\/instruction-set-architectures\/vega-7nm-shader-instruction-set-architecture.pdf"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.71"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/324446a0"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"Martin Burtscher and Keshav Pingali. 2011. Chapter 6 - An Efficient CUDA Implementation of the Tree-Based Barnes Hut n-Body Algorithm. In GPU computing Gems Emerald edition. Elsevier. https:\/\/doi.org\/10.1016\/B978-0-12-384988-5.00006-1","DOI":"10.1016\/B978-0-12-384988-5.00006-1"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","unstructured":"R. Capuzzo-Dolcetta and M. Spera. 2013. A performance comparison of different graphics processing units running direct N-body simulations. Computer Physics Communications 184 11 (2013). https:\/\/doi.org\/10.1016\/j.cpc.2013.07.005","DOI":"10.1016\/j.cpc.2013.07.005"},{"volume-title":"cuda-to-sycl-nbody","author":"Ltd Codeplay Software","key":"e_1_3_2_2_9_1","unstructured":"Codeplay Software Ltd. 2023. cuda-to-sycl-nbody. Codeplay Software Ltd. https:\/\/github.com\/codeplaysoftware\/cuda-to-sycl-nbody"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fl.18.010186.001331"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPS.2010.2055165"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(87)90140-9"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492902000144"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC51967.2020.00010"},{"key":"e_1_3_2_2_15_1","unstructured":"Khronos-Group. 2023. SYCL - C++ Single-source Heterogeneous Programming for Acceleration Offload. Khronos Group. https:\/\/www.khronos.org\/sycl\/"},{"key":"e_1_3_2_2_16_1","unstructured":"Khronos\u00ae-SYCL\u2122-Working-Group. 2020. SYCL\u2122 Specification. Khronos Group. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-1.2.1.pdf"},{"key":"e_1_3_2_2_17_1","unstructured":"Khronos\u00ae-SYCL\u2122-Working-Group. 2023. SYCL\u2122 2020 Specification (revision 7). Khronos Group. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/html\/sycl-2020.html"},{"key":"e_1_3_2_2_18_1","unstructured":"NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_2_19_1","unstructured":"NVIDIA. 2023. CUDA C++ Best Practices Guide. NVIDIA. https:\/\/docs.nvidia.com\/cuda\/cuda-c-best-practices-guide\/index.html"},{"key":"e_1_3_2_2_20_1","unstructured":"NVIDIA 2023. CUDA C++ Programming Guide Release 12.2. NVIDIA. https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf"},{"key":"e_1_3_2_2_21_1","unstructured":"NVIDIA. 2021. NVIDIA AMPERE GA102 GPU ARCHITECTURE. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf"},{"key":"e_1_3_2_2_22_1","unstructured":"Lars Nyland Mark Harris and Jan Prins. 2007. GPU Gems 3. 62\u201366 pages. https:\/\/developer.nvidia.com\/gpugems\/gpugems3\/part-v-physics-simulation\/chapter-31-fast-n-body-simulation-cuda"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434209400800205"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10051656"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04115"},{"volume-title":"Comparison of different n-body algorithms on various hardware platforms using SYCL. Bachelor Thesis","author":"Th\u00fcring Tim","key":"e_1_3_2_2_26_1","unstructured":"Tim Th\u00fcring. 2023. Comparison of different n-body algorithms on various hardware platforms using SYCL. Bachelor Thesis. University of Stuttgart."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","unstructured":"Tim Th\u00fcring and Marcel Breyer. 2023. TimThuering\/N-Body-Simulation: Version 1.1. https:\/\/doi.org\/10.5281\/zenodo.8382540","DOI":"10.5281\/zenodo.8382540"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/169627.169640"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","unstructured":"Rio Yokota and Lorena\u00a0A. Barba. 2011. Chapter 9 - Treecode and Fast Multipole Method for N-Body Simulation with CUDA. In GPU Computing Gems Emerald Edition Wen mei W.\u00a0Hwu (Ed.). Morgan Kaufmann Boston 113\u2013132. https:\/\/doi.org\/10.1016\/B978-0-12-384988-5.00009-7","DOI":"10.1016\/B978-0-12-384988-5.00009-7"}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","acronym":"SC-W 2023","location":"Denver CO USA"},"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\/3624062.3624604","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:03:04Z","timestamp":1755745384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":30,"alternative-id":["10.1145\/3624062.3624604","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624604","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"}}]}}