{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T02:39:28Z","timestamp":1770691168921,"version":"3.49.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z211100002121001"],"award-info":[{"award-number":["Z211100002121001"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s42514-025-00252-z","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T08:10:30Z","timestamp":1763626230000},"page":"94-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SYCL-MLU: unifying SIMT and SIMD in heterogeneous programming"],"prefix":"10.1007","volume":"8","author":[{"given":"Runyu","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yijin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jiacheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Ziyang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"En","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Ziyan","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Huimin","family":"Cui","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"252_CR1","doi-asserted-by":"publisher","unstructured":"Alekseenko, A., P\u00e1ll, S., Lindahl, E.: GROMACS on AMD GPU-Based HPC platforms: Using SYCL for performance and portability. In: Proceedings of the Cray User Group, pp. 71\u201384. Association for Computing Machinery, New York (2025). https:\/\/doi.org\/10.1145\/3725789.3725797","DOI":"10.1145\/3725789.3725797"},{"key":"252_CR2","doi-asserted-by":"publisher","unstructured":"Alpay, A., Heuveline, V.: One pass to bind them: The first single-pass SYCL compiler with unified code representation across backends. In: Proceedings of the 2023 International Workshop on OpenCL. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3585341.3585351","DOI":"10.1145\/3585341.3585351"},{"key":"252_CR3","doi-asserted-by":"publisher","unstructured":"Alpay, A., Soproni, B., W\u00fcns\u00adche, H., Heuveline, V.: Exploring the possibility of a hipSYCL-based implementation of oneAPI. In: Proceedings of the 10th International Workshop on OpenCL. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3529538.3530005","DOI":"10.1145\/3529538.3530005"},{"issue":"1\u20133","key":"252_CR4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/0010-4655(95)00042-E","volume":"91","author":"HJC Berendsen","year":"1995","unstructured":"Berendsen, H.J.C., van der Spoel, D., van Drunen, R.: GROMACS: A message-passing parallel molecular dynamics implementation. Computer Physics Communications 91, 43\u201356 (1995).","journal-title":"Computer Physics Communications"},{"key":"252_CR5","doi-asserted-by":"publisher","unstructured":"Bi, R., Xu, T., Xu, M., Chen, E.: PaddlePaddle: A production-oriented deep learning platform facilitating the competency of enterprises. In: 2022 IEEE 24th Int Conf on High Performance Computing Communications; 8th Int Conf on Data Science Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud Big Data Systems Application (HPCC\/DSS\/SmartCity\/DependSys), pp. 92\u201399 (2022). https:\/\/doi.org\/10.1109\/HPCC-DSS-SmartCity-DependSys57074.2022.00046","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys57074.2022.00046"},{"key":"252_CR6","unstructured":"CINN Team: CINN: Compiler Infrastructure for Neural Networks (2021). https:\/\/github.com\/PaddlePaddle\/Paddle\/tree\/develop\/paddle\/cinn"},{"key":"252_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"252_CR8","unstructured":"Gerganov., G.: llama.cpp: LLM inference in C\/C++ (2023). https:\/\/github.com\/ggml-org\/llama.cpp"},{"key":"252_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"252_CR10","unstructured":"Hikida, S.: Intel\u00ae Compiler Achieves SYCL 2020 Conformance (2024). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/compiler-first-full-sycl2020-conformance.html"},{"key":"252_CR11","unstructured":"Intel Corporation: Compile Cross-Architecture: Intel\u00ae oneAPI DPC++\/C++ Compiler (2023a). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compiler.html"},{"key":"252_CR12","unstructured":"Intel Corporation: Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects (2019). https:\/\/github.com\/intel\/llvm"},{"key":"252_CR13","unstructured":"Intel Corporation: Migrate CUDA* to DPC++ Code: Intel\u00ae DPC++ Compatibility Tool (2023c). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compatibility-tool.html"},{"key":"252_CR14","unstructured":"Intel Corporation: oneAPI: A New Era of Heterogeneous Computing (2023b). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/overview.html"},{"key":"252_CR15","doi-asserted-by":"publisher","unstructured":"Ke, Y., Agung, M., Takizawa, H.: neoSYCL: a SYCL implementation for SX-Aurora TSUBASA. In: The International Conference on High Performance Computing in Asia-Pacific Region, pp. 50\u201357. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3432261.3432268","DOI":"10.1145\/3432261.3432268"},{"key":"252_CR16","unstructured":"Liu, Y., Chu, L., Chen, G., Wu, Z., Chen, Z., Lai, B., Hao, Y.: PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation (2021). https:\/\/arxiv.org\/abs\/2101.06175"},{"issue":"1","key":"252_CR17","doi-asserted-by":"publisher","first-page":"105","DOI":"10.11871\/jfdc.issn.2096.742X.2019.01.011","volume":"1","author":"Y Ma","year":"2019","unstructured":"Ma, Y., Yu, D., Wu, T., Wang, H.: PaddlePaddle: An open-source deep learning platform from industrial practice. Frontiers of Data and Computing 1, 105\u2013115 (2019). https:\/\/doi.org\/10.11871\/jfdc.issn.2096.742X.2019.01.011","journal-title":"Front Data Domputing"},{"key":"252_CR18","unstructured":"PaddleNLP Contributors: PaddleNLP: An Easy-to-use and High Performance NLP Library (2021). https:\/\/github.com\/PaddlePaddle\/PaddleNLP"},{"key":"252_CR19","unstructured":"PaddlePaddle Authors: PaddleDetection, Object detection and instance segmentation toolkit based on PaddlePaddle (2019a). https:\/\/github.com\/PaddlePaddle\/PaddleDetection"},{"key":"252_CR20","unstructured":"PaddlePaddle Authors: PaddlePaddle custom device implementaion (2024). https:\/\/github.com\/PaddlePaddle\/PaddleCustomDevice"},{"key":"252_CR21","unstructured":"PaddlePaddle Authors: Paddle: PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (2016). https:\/\/github.com\/PaddlePaddle\/Paddle"},{"key":"252_CR22","unstructured":"PaddlePaddle Authors: PaddleSeg, End-to-end image segmentation kit based on PaddlePaddle (2019b). https:\/\/github.com\/PaddlePaddle\/PaddleSeg"},{"key":"252_CR23","unstructured":"Peng, J., Liu, Y., Tang, S., Hao, Y., Chu, L., Chen, G., Wu, Z., Chen, Z., Yu, Z., Du, Y., Dang, Q., Lai, B., Liu, Q., Hu, X., Yu, D., Ma, Y.: PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model (2022). https:\/\/arxiv.org\/abs\/2204.02681"},{"key":"252_CR24","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An Incremental Improvement (2018). https:\/\/arxiv.org\/abs\/1804.02767"},{"key":"252_CR25","doi-asserted-by":"publisher","unstructured":"Reyes, R., Brown, G., Burns, R., Wong, M.: SYCL 2020: More than meets the eye. In: Proceedings of the International Workshop on OpenCL. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3388333.3388649","DOI":"10.1145\/3388333.3388649"},{"key":"252_CR26","doi-asserted-by":"publisher","unstructured":"Reyes, R., Lom\u00fcller, V.: SYCL: Single-source C++ accelerator programming. In: Parallel Computing: On the Road to Exascale, pp. 673\u2013682. IOS Press, Amsterdam, the Netherlands (2016). https:\/\/doi.org\/10.3233\/978-1-61499-621-7-673","DOI":"10.3233\/978-1-61499-621-7-673"},{"key":"252_CR27","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetV2: Inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00252-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00252-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00252-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T08:55:44Z","timestamp":1770627344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00252-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["252"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00252-z","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"assertion":[{"value":"18 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}