SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs
University of Salerno, Italy
International Workshop on OpenCL and SYCL (IWOCL ’24), 2024
@article{crisci2024sycl,
title={SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs},
author={Crisci, Luigi and Carpentieri, Lorenzo and Thoman, Peter and Alpay, Aksel and Heuveline, Vincent and Cosenza, Biagio},
year={2024}
}
Today, the SYCL standard represents the most advanced programming model for heterogeneous computing, delivering both productivity, portability, and performance in pure C++17. SYCL 2020, in particular, represents a major enhancement that pushes the boundaries of heterogeneous programming by introducing a number of new features. As the new features are implemented by existing compilers, it becomes critical to assess the maturity of the implementation through accurate and specific benchmarking. This paper presents SYCL-Bench 2020, an extended benchmark suite specifically designed to evaluate six key features of SYCL 2020: unified shared memory, reduction kernel, specialization constants, group algorithms, in-order queue, and atomics. We experimentally evaluate SYCL-Bench 2020 on GPUs from the three major vendors, i.e., AMD, Intel, and NVIDIA, and on two different SYCL implementations AdaptiveCPP and oneAPI DPC++.
March 10, 2024 by hgpu
