On the development of high-performance, multi-GPU applications on heterogeneous systems leveraging SYCL

• We present new baseline implementations of the UVaFTLE application using CUDA and HIP. • We offer a portable UVaFTLE using SYCL, supporting simultaneous multi- vendor GPU use. • We evaluate the different UVaFTLE implementations performance and development effort. • Based on our analysis, we offer development strategy recommendations for using SYCL. • We support open science; all the implementations are open-source and public on GitHub. 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.