{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:21Z","timestamp":1750219941258,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T00:00:00Z","timestamp":1677283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,25]]},"DOI":"10.1145\/3589236.3589238","type":"proceedings-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:32:47Z","timestamp":1687307567000},"page":"14-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding Portability of Automotive Workload: A Case Study with the Points-to-Image Kernel in SYCL on Heterogeneous Computing Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7197-780X","authenticated-orcid":false,"given":"Zheming","family":"Jin","sequence":"first","affiliation":[{"name":"ORNL, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey","family":"Vetter","sequence":"additional","affiliation":[{"name":"ORNL, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Sommer L. Stock F. Solis-Vasquez L. and Koch A. 2019 October. Work-in-Progress: DAPHNE-An Auto-motive Benchmark Suite for Parallel Programming Models on Embedded Heterogeneous Platforms. In 2019 International Conference on Embedded Software (EMSOFT) (pp. 1-2). IEEE.","DOI":"10.1145\/3349568.3351547"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.133"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Kuon I. Tessier R. and Rose J. 2008. FPGA architecture: Survey and challenges. Foundations and Trends\u00ae in Electronic Design Automation 2(2) pp.135-253.","DOI":"10.1561\/1000000005"},{"key":"e_1_3_2_1_5_1","unstructured":"Chandra R. Dagum L. Kohr D. Menon R. Maydan D. and McDonald J. 2001. Parallel programming in OpenMP. Morgan Kaufmann."},{"key":"e_1_3_2_1_6_1","unstructured":"Munshi A. Gaster B. Mattson T.G. and Ginsburg D. 2011. OpenCL programming guide. Pearson Education."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.57"},{"key":"e_1_3_2_1_8_1","unstructured":"SYCL 2020 Specification (revision 5) [online] Available: https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/html\/sycl-2020.html"},{"volume-title":"Proceedings of the International Workshop on OpenCL (pp. 1-1).","author":"Reyes R.","key":"e_1_3_2_1_9_1","unstructured":"Reyes, R., Brown, G. and Burns, R., 2020, April. Bringing performant support for NVIDIA hardware to SYCL. In Proceedings of the International Workshop on OpenCL (pp. 1-1)."},{"key":"e_1_3_2_1_10_1","unstructured":"https:\/\/github.com\/intel\/llvm\/blob\/sycl\/sycl\/doc\/PluginInterface.md"},{"volume-title":"International Workshop on OpenCL (pp. 1-4).","author":"Feng W.","key":"e_1_3_2_1_11_1","unstructured":"Feng, W., Maghareh, R. and Wang, K.T.A., 2021, April. Extending DPC++ with Support for Huawei Ascend AI Chipset. In International Workshop on OpenCL (pp. 1-4)."},{"volume-title":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 1-8).","author":"Jin Z.","key":"e_1_3_2_1_12_1","unstructured":"Jin, Z. and Vetter, J.S., 2022, August. Performance portability study of epistasis detection using SYCL on NVIDIA GPU. In Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 1-8)."},{"volume-title":"International Workshop on OpenCL (pp. 1-5).","author":"Hardy D.J.","key":"e_1_3_2_1_13_1","unstructured":"Hardy, D.J., Choi, J., Jiang, W. and Tajkhorshid, E., 2022, May. Experiences Porting NAMD to the Data Parallel C++ Programming Model. In International Workshop on OpenCL (pp. 1-5)."},{"volume-title":"International Workshop on OpenCL (pp. 1-12)","author":"Breyer M.","key":"e_1_3_2_1_14_1","unstructured":"Breyer, M., Van Craen, A. and Pfl\u00fcger, D., 2022, May. A Comparison of SYCL, OpenCL, CUDA, and OpenMP for Massively Parallel Support Vector Machine Classification on Multi-Vendor Hardware. In International Workshop on OpenCL (pp. 1-12)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.03.017"},{"volume-title":"Intel and NVIDIA GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 45-56)","author":"Kwack J.","key":"e_1_3_2_1_16_1","unstructured":"Kwack, J., Tramm, J., Bertoni, C., Ghadar, Y., Homerding, B., Rangel, E., Knight, C. and Parker, S., 2021, November. Evaluation of Performance Portability of Applications and Mini-Apps across AMD, Intel and NVIDIA GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 45-56). IEEE."},{"key":"e_1_3_2_1_17_1","volume-title":"AMD and Intel GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 57-67)","author":"Dufek A.S.","year":"2021","unstructured":"Dufek, A.S., Gayatri, R., Mehta, N., Doerfler, D., Cook, B., Ghadar, Y. and DeTar, C., 2021, November. Case Study of Using Kokkos and SYCL as Performance-Portable Frameworks for Milc-Dslash Benchmark on NVIDIA, AMD and Intel GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 57-67). IEEE."},{"volume-title":"2021 IEEE High Performance Extreme Computing Conference (HPEC) (pp. 1-7). IEEE.","author":"Kuncham G.K.R.","key":"e_1_3_2_1_18_1","unstructured":"Kuncham, G.K.R., Vaidya, R. and Barve, M., 2021, September. Performance Study of GPU applications using SYCL and CUDA on Tesla V100 GPU. In 2021 IEEE High Performance Extreme Computing Conference (HPEC) (pp. 1-7). IEEE."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Pascuzzi V.R. and Goli M. 2022. Achieving Near-Native Runtime Performance and Cross-Platform Performance Portability for Random Number Generation Through SYCL Interoperability. In International Workshop on Accelerator Programming Using Directives (pp. 22-45). Springer Cham.","DOI":"10.1007\/978-3-030-97759-7_2"},{"volume-title":"2018 IEEE International Symposium on High Performance Computer Architecture (HPCA) (pp. 608-619)","author":"Gutierrez A.","key":"e_1_3_2_1_20_1","unstructured":"Gutierrez, A., Beckmann, B.M., Dutu, A., Gross, J., LeBeane, M., Kalamatianos, J., Kayiran, O., Poremba, M., Potter, B., Puthoor, S. and Sinclair, M.D., 2018, February. Lost in abstraction: Pitfalls of analyzing GPUs at the intermediate language level. In 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA) (pp. 608-619). IEEE."},{"key":"e_1_3_2_1_21_1","unstructured":"ROCm Open Ecosystem 2021. Advanced Micro Devices. https:\/\/www.amd.com\/en\/graphics\/servers-solutions-rocm"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Reinders J. Ashbaugh B. Brodman J. Kinsner M. Pennycook J. and Tian X. 2021. Data Parallel C++: Mastering DPC++ for Programming of Heterogeneous Systems using C++ and SYCL. Springer Nature.","DOI":"10.1007\/978-1-4842-5574-2"},{"volume-title":"International Symposium on Code Generation and Optimization, 2004. CGO 2004. (pp. 75-86)","author":"Lattner C.","key":"e_1_3_2_1_24_1","unstructured":"Lattner, C. and Adve, V., 2004, March. LLVM: A compilation framework for lifelong program analysis & trans-formation. In International Symposium on Code Generation and Optimization, 2004. CGO 2004. (pp. 75-86). IEEE."},{"key":"e_1_3_2_1_26_1","unstructured":"Camera calibration with opensource computer vision (OpenCV) [online] https:\/\/docs.opencv.org\/3.4\/d4\/d94\/tutorial_camera_calibration.html"},{"key":"e_1_3_2_1_27_1","unstructured":"The Darmstadt Automotive Parallel HeterogeNEous (DAPHNE) Benchmark-Suite. [online] https:\/\/github.com\/esa-tu-darmstadt\/daphne-benchmark"},{"volume-title":"SC'16: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 409-420)","author":"Zohouri H.R.","key":"e_1_3_2_1_28_1","unstructured":"Zohouri, H.R., Maruyama, N., Smith, A., Matsuda, M. and Matsuoka, S., 2016, November. Evaluating and optimizing OpenCL kernels for high performance computing with FPGAs. In SC'16: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 409-420). IEEE."},{"key":"e_1_3_2_1_29_1","unstructured":"FPGA Optimization Guide for Intel oneAPI Toolkits [online] https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/oneapi-fpga-optimization-guide"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.02.008"},{"key":"e_1_3_2_1_31_1","unstructured":"Intel FPGA Programmable Acceleration Card D5005 Data Sheet [online] https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/programmable\/683568\/current\/specifications.html"},{"key":"e_1_3_2_1_32_1","unstructured":"The Intel oneAPI DPC++ compiler. [online] https:\/\/github.com\/intel\/llvm"},{"key":"e_1_3_2_1_33_1","unstructured":"CUDA for Tegra. [online] https:\/\/docs.nvidia.com\/cuda\/cuda-for-tegra-appnote\/index.html"},{"key":"e_1_3_2_1_34_1","unstructured":"PTX Machine Model. [online] https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html#ptx-machine-model"},{"volume-title":"Proceedings of the International Workshop on OpenCL (pp. 1-7).","author":"Homerding B.","key":"e_1_3_2_1_35_1","unstructured":"Homerding, B. and Tramm, J., 2020, April. Evaluating the Performance of the hipSYCL Toolchain for HPC Kernels on NVIDIA V100 GPUs. In Proceedings of the International Workshop on OpenCL (pp. 1-7)."},{"volume-title":"2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 68-78)","author":"Haseeb M.","key":"e_1_3_2_1_36_1","unstructured":"Haseeb, M., Ding, N., Deslippe, J. and Awan, M., 2021, November. Evaluating Performance and Portability of a core bioinformatics kernel on multiple vendor GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 68-78). IEEE."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.03.017"},{"key":"e_1_3_2_1_38_1","unstructured":"Migdal M. 2021. From CUDA to SYCL. SYCL summer sessions. https:\/\/sycl.tech\/assets\/files\/Michel_Migdal_Codeplay_Porting_Tips_CDUA_To_SYCL.pdf."},{"volume-title":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (pp. 907-910)","author":"Siefert C.","key":"e_1_3_2_1_39_1","unstructured":"Siefert, C., Olivier, S.L., Voskuilen, G. and Young, J., 2022, May. MultiGrid on FPGA Using Data Parallel C++. In 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (pp. 907-910). IEEE."},{"volume-title":"International Conference on High Performance Computing in Asia-Pacific Region (pp. 84-93)","author":"Kashino R.","key":"e_1_3_2_1_40_1","unstructured":"Kashino, R., Kobayashi, R., Fujita, N. and Boku, T., 2022, January. Multi-hetero Acceleration by GPU and FPGA for Astrophysics Simulation on oneAPI Environment. In International Conference on High Performance Computing in Asia-Pacific Region (pp. 84-93)."},{"volume-title":"International Workshop on OpenCL (pp. 1-11)","author":"Kamalakkannan K.","key":"e_1_3_2_1_41_1","unstructured":"Kamalakkannan, K., Mudalige, G.R., Reguly, I.Z. and Fahmy, S.A., 2022, May. FPGA Acceleration of Structured-Mesh-Based Explicit and Implicit Numerical Solvers using SYCL. In International Workshop on OpenCL (pp. 1-11)."}],"event":{"name":"GPGPU '23: 15th Workshop on General Purpose Processing Using GPU","acronym":"GPGPU '23","location":"Montreal Canada"},"container-title":["Proceedings of the 15th Workshop on General Purpose Processing Using GPU"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589236.3589238","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589236.3589238","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589236.3589238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:53Z","timestamp":1750182533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589236.3589238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,25]]},"references-count":40,"alternative-id":["10.1145\/3589236.3589238","10.1145\/3589236"],"URL":"https:\/\/doi.org\/10.1145\/3589236.3589238","relation":{},"subject":[],"published":{"date-parts":[[2023,2,25]]},"assertion":[{"value":"2023-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}