2026-04-27T07:54:16Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/793762025-12-15T09:23:03Zcom_10324_1165com_10324_931com_10324_894col_10324_1335

On the development of high-performance, multi-GPU applications on heterogeneous systems leveraging SYCL Andújar Muñoz, Francisco José Carratalá Sáez, Rocío Torres de la Sierra, Yuri González Escribano, Arturo Llanos Ferraris, Diego Rafael Informática Computational platforms for high-performance scientific applications are increasingly heterogeneous, incorporating multiple GPU accelerators. However, differences in GPU vendors, architectures, and programming models challenge performance portability and ease of development. SYCL provides a unified programming approach, enabling applications to target NVIDIA and AMD GPUs simultaneously while offering higher-level abstractions for data and task management. This paper evaluates SYCL’s performance and development effort using the Finite Time Lyapunov Exponent (FTLE) calculation as a case study. We compare SYCL’s AdaptiveCpp (Ahead-Of-Time and Just-In-Time) and Intel oneAPI compilers, along with different data management strategies (Unified Shared Memory and buffers), against equivalent CUDA and HIP implementations. Our analysis considers single and multi-GPU execution, including heterogeneous setups with GPUs from different vendors. Results show that, while SYCL introduces additional development effort compared to native CUDA and HIP implementations, it enables multi-vendor portability with minimal performance overhead when using specific design options. Based on our findings, we provide development guidelines to help programmers decide when to use SYCL versus vendor-specific alternatives. 2025-11-06T12:20:08Z 2025-11-06T12:20:08Z 2025-11-06T12:20:08Z 2026 info:eu-repo/semantics/article Journal of Parallel and Distributed Computing Volume 207, January 2026, 105188 0743-7315 https://uvadoc.uva.es/handle/10324/79376 10.1016/j.jpdc.2025.105188 1 207 24 Journal of Parallel and Distributed Computing 207 eng https://www.sciencedirect.com/science/article/pii/S0743731525001558 info:eu-repo/semantics/openAccess Elsevier