RT info:eu-repo/semantics/article
T1 On the development of high-performance, multi-GPU applications on heterogeneous systems leveraging SYCL
A1 Andújar Muñoz, Francisco José
A1 Carratalá-Sáez, Rocío
A1 Torres de la Sierra, Yuri
A1 González Escribano, Arturo
A1 Llanos Ferraris, Diego Rafael
K1 Informática
K1 SYCL; CUDA; HIP; Finite Time Lyapunov Exponent; Performance evaluation; Development effort
K1 1203 Ciencia de Los Ordenadores
K1 3304 Tecnología de Los Ordenadores
AB 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.
PB Elsevier
SN 0743-7315
YR 2026
FD 2026
LK https://uvadoc.uva.es/handle/10324/79376
UL https://uvadoc.uva.es/handle/10324/79376
LA eng
NO Journal of Parallel and Distributed Computing Volume 207, January 2026, 105188
NO Producción Científica
DS UVaDOC
RD 07-nov-2025