{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:29:02Z","timestamp":1765268942190,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Austrian Research Promotion Agency","award":["4814683"],"award-info":[{"award-number":["4814683"]}]},{"DOI":"10.13039\/501100006374","name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["2022CC57PY"],"award-info":[{"award-number":["2022CC57PY"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"HORIZON EUROPE Digital, Industry and Space","doi-asserted-by":"publisher","award":["101092877"],"award-info":[{"award-number":["101092877"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["956137"],"award-info":[{"award-number":["956137"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,8]]},"DOI":"10.1145\/3648115.3648120","type":"proceedings-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:25:24Z","timestamp":1712341524000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-1321","authenticated-orcid":false,"given":"Luigi","family":"Crisci","sequence":"first","affiliation":[{"name":"University of Salerno, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2041-7618","authenticated-orcid":false,"given":"Lorenzo","family":"Carpentieri","sequence":"additional","affiliation":[{"name":"University of Salerno, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4028-7451","authenticated-orcid":false,"given":"Peter","family":"Thoman","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-6375","authenticated-orcid":false,"given":"Aksel","family":"Alpay","sequence":"additional","affiliation":[{"name":"University of Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2217-7558","authenticated-orcid":false,"given":"Vincent","family":"Heuveline","sequence":"additional","affiliation":[{"name":"University of Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8869-6705","authenticated-orcid":false,"given":"Biagio","family":"Cosenza","sequence":"additional","affiliation":[{"name":"University of Salerno, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2012. How to optimize data transfers in CUDA. https:\/\/developer.nvidia.com\/blog\/how-optimize-data-transfers-cuda-cc\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. SYCL Specification. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/html\/sycl-2020.html."},{"key":"e_1_3_2_1_3_1","unstructured":"2023. Top500 chart. https:\/\/www.top500.org\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. Cineca official website. https:\/\/www.cineca.it\/."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3529538.3529997"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388658"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585341.3585351"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388653"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3456669.3456696"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585341.3585374"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJCSE.2018.095847"},{"key":"e_1_3_2_1_15_1","volume-title":"SYnergy: Fine-grained Energy-Efficient Heterogeneous Computing for Scalable Energy Saving. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Fan Kaijie","year":"2023","unstructured":"Kaijie Fan, Marco D\u2019Antonio, Lorenzo Carpentieri, Biagio Cosenza, Federico Ficarelli, and Daniele Cesarini. 2023. SYnergy: Fine-grained Energy-Efficient Heterogeneous Computing for Scalable Energy Saving. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC)."},{"key":"e_1_3_2_1_16_1","volume-title":"The 2020 International Conference on High Performance Computing and Simulation. IEEE.","author":"Gozillon Andrew","year":"2020","unstructured":"Andrew Gozillon, Ronan Keryell, Lin-Ya Yu, Gauthier Harnisch, and Paul Keir. 2020. triSYCL for Xilinx FPGA. In The 2020 International Conference on High Performance Computing and Simulation. IEEE."},{"key":"e_1_3_2_1_17_1","volume-title":"Optimizing parallel reduction in CUDA. NVIDIA developer technology 2, 4","author":"Mark Harris","year":"2007","unstructured":"Mark Harris 2007. Optimizing parallel reduction in CUDA. NVIDIA developer technology 2, 4 (2007), 1\u201339."},{"key":"e_1_3_2_1_18_1","unstructured":"Zheming Jin. 2020. The rodinia benchmark suite in SYCL. Technical Report. Argonne National Lab.(ANL) Argonne IL (United States). Argonne Leadership\u00a0\u2026."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995222"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00041"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC51967.2020.00010"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2438\/1\/012018"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432261.3432268"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919639"},{"volume-title":"Euro-Par 2020: Parallel Processing","author":"Lal Sohan","key":"e_1_3_2_1_25_1","unstructured":"Sohan Lal, Aksel Alpay, Philip Salzmann, Biagio Cosenza, Alexander Hirsch, Nicolai Stawinoga, Peter Thoman, Thomas Fahringer, and Vincent Heuveline. 2020. SYCL-Bench: A Versatile Cross-Platform Benchmark Suite for Heterogeneous Computing. In Euro-Par 2020: Parallel Processing, Maciej Malawski and Krzysztof Rzadca (Eds.). Springer International Publishing, Cham, 629\u2013644."},{"key":"e_1_3_2_1_26_1","volume-title":"Fast Algorithms for Convolutional Neural Networks. CoRR abs\/1509.09308","author":"Lavin Andrew","year":"2015","unstructured":"Andrew Lavin. 2015. Fast Algorithms for Convolutional Neural Networks. CoRR abs\/1509.09308 (2015). arXiv:1509.09308http:\/\/arxiv.org\/abs\/1509.09308"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3456669.3456701"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO57284.2023.10159832"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188506"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622813"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624180"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00018"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.9"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3456669.3456683"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3529538.3529548"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.2172\/1473756"}],"event":{"name":"IWOCL '24: International Workshop on OpenCL and SYCL","acronym":"IWOCL '24","location":"Chicago IL USA"},"container-title":["Proceedings of the 12th International Workshop on OpenCL and SYCL"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648115.3648120","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3648115.3648120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:26:38Z","timestamp":1755915998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648115.3648120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,8]]},"references-count":36,"alternative-id":["10.1145\/3648115.3648120","10.1145\/3648115"],"URL":"https:\/\/doi.org\/10.1145\/3648115.3648120","relation":{},"subject":[],"published":{"date-parts":[[2024,4,8]]},"assertion":[{"value":"2024-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}