{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:31:39Z","timestamp":1792787499504,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["JP24K14967"],"award-info":[{"award-number":["JP24K14967"]}]},{"name":"NSF I\/UCRC Center for Space, High-Performance, and Resilient Computing (SHREC)","award":["CNS-1822080"],"award-info":[{"award-number":["CNS-1822080"]}]},{"name":"U.S. Department of Energy, Office of Science","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"https:\/\/ror.org\/01bj3aw27","id-type":"ROR","asserted-by":"crossref"}]},{"name":"U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research Program","award":["DE-FOA-0003264"],"award-info":[{"award-number":["DE-FOA-0003264"]}],"id":[{"id":"https:\/\/ror.org\/0012c7r22","id-type":"ROR","asserted-by":"crossref"}]},{"name":"U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research Program","award":["DE-SC0025645"],"award-info":[{"award-number":["DE-SC0025645"]}],"id":[{"id":"https:\/\/ror.org\/0012c7r22","id-type":"ROR","asserted-by":"crossref"}]},{"name":"U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research Program","award":["FWP ERKJ452"],"award-info":[{"award-number":["FWP ERKJ452"]}],"id":[{"id":"https:\/\/ror.org\/0012c7r22","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"DOI":"10.1145\/3832810.3832914","type":"proceedings-article","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:19:06Z","timestamp":1789258746000},"page":"166-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A SYCLic Investigation of SYCL Ecosystems: UniSYCL for Heterogeneous Scaling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1093-9760","authenticated-orcid":false,"given":"Nabayan","family":"Chaudhury","sequence":"first","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5386-7623","authenticated-orcid":false,"given":"Norihisa","family":"Fujita","sequence":"additional","affiliation":[{"name":"Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5426-1415","authenticated-orcid":false,"given":"Beau","family":"Johnston","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8730-2228","authenticated-orcid":false,"given":"Taisuke","family":"Boku","sequence":"additional","affiliation":[{"name":"Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan and Advanced HPC-AI Research and Development Support Center, RIST, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6015-0727","authenticated-orcid":false,"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Advanced Micro Devices Inc.2026. ROCm HIP Programming Guide. https:\/\/rocm.docs.amd.com\/en\/develop\/how-to\/programming_guide.html. Online documentation."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388658"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3585341.3585351"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"C\u00e9dric Augonnet Samuel Thibault Raymond Namyst and Pierre-Andr\u00e9 Wacrenier. 2011. StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurrency and Computation: Practice and Experience 23 2 (2011) 187\u2013198. arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.163110.1002\/cpe.1631","DOI":"10.1002\/cpe.1631"},{"key":"e_1_3_3_1_6_2","series-title":"(SC \u201912)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Bauer Michael","year":"2012","unstructured":"Michael Bauer, Sean Treichler, Elliott Slaughter, and Alex Aiken. 2012. Legion: expressing locality and independence with logical regions. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Salt Lake City, Utah) (SC \u201912). IEEE Computer Society Press, Washington, DC, USA, Article 66, 11\u00a0pages."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.281"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"H. Carter\u00a0Edwards Christian\u00a0R. Trott and Daniel Sunderland. 2014. Kokkos. J. Parallel Distrib. Comput. 74 12 (Dec. 2014) 3202\u20133216. 10.1016\/j.jpdc.2014.07.003","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_3_1_10_2","unstructured":"Codeplay Software Ltd.2023. oneAPI for NVIDIA GPUs and oneAPI for AMD GPUs. https:\/\/developer.codeplay.com\/. SYCL plug-ins for CUDA and HIP backends."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Tom Deakin James Price Matt Martineau and Simon McIntosh-Smith. 2018. Evaluating attainable memory bandwidth of parallel programming models via BabelStream. International Journal of Computational Science and Engineering 17 3 (Oct. 2018) 247\u2013262. 10.1504\/IJCSE.2017.10011352","DOI":"10.1504\/IJCSE.2017.10011352"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Youssef Faqir-Rhazoui and Carlos Garcia. 2022. Exploring the Performance and Portability of the k-means Algorithm on SYCL Across CPU and GPU Architectures. 10.21203\/rs.3.rs-2402689\/v1","DOI":"10.21203\/rs.3.rs-2402689\/v1"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14313-2_51"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624244"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science62913.2024.10678717"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.2172\/1441285"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00041"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00067"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622873"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Elias Konstantinidis and Yiannis Cotronis. 2017. A quantitative roofline model for GPU kernel performance estimation using micro-benchmarks and hardware metric profiling. J. Parallel and Distrib. Comput. 107 (2017) 37\u201356. 10.1016\/j.jpdc.2017.04.002","DOI":"10.1016\/j.jpdc.2017.04.002"},{"key":"e_1_3_3_1_21_2","unstructured":"NVIDIA Corporation. 2026. CUDA C++ Programming Guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/. Online documentation."},{"key":"e_1_3_3_1_22_2","unstructured":"OpenACC-Standard.org. 2022. The OpenACC Application Programming Interface Version 3.3. https:\/\/www.openacc.org\/specification. Version 3.3 specification."},{"key":"e_1_3_3_1_23_2","unstructured":"OpenMP Architecture Review Board. 2021. OpenMP Application Programming Interface Version 5.2. https:\/\/www.openmp.org\/specifications\/. Language specification."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-5574-2"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388649"},{"key":"e_1_3_3_1_26_2","unstructured":"University of Delaware IT Research Cyberinfrastructure. 2022. DARWIN System Information. University of Delaware HPC Documentation. Describes NVIDIA T4 NVIDIA V100 and AMD MI50 GPU resources. https:\/\/www.hpc.udel.edu\/systems\/darwin"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (April 2009) 65\u201376. 10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"}],"event":{"name":"ICPP '26: Proceedings of the 55th International Conference on Parallel Processing","location":"Singapore , Singapore","acronym":"ICPP '26"},"container-title":["Proceedings of the 55th International Conference on Parallel Processing"],"original-title":[],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:05:12Z","timestamp":1789581912000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3832810.3832914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":26,"alternative-id":["10.1145\/3832810.3832914","10.1145\/3832810"],"URL":"https:\/\/doi.org\/10.1145\/3832810.3832914","relation":{},"subject":[],"published":{"date-parts":[[2026,9,27]]},"assertion":[{"value":"2026-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}