Comparing Performance and Portability Between CUDA and SYCL for Protein Database Search on NVIDIA, AMD, and Intel GPUs

• Manuel Costanzo UNLP https://orcid.org/0000-0002-6937-3943
• Enzo Rucci UNLP https://orcid.org/0000-0001-6736-7358
• Carlos García-Sánchez Universidad Complutense de Madrid https://orcid.org/0000-0002-3470-1097
• Marcelo Naiouf UNLP https://orcid.org/0000-0001-9127-3212
• Manuel Prieto-Matías Universidad Complutense de Madrid https://orcid.org/0000-0003-0687-3737

Resumo

The heterogeneous computing paradigm has led to the need for portable and efficient programming solutions that can leverage the capabilities of various hardware devices, such as NVIDIA, Intel, and AMD GPUs. This study evaluates the portability and performance of the SYCL and CUDA languages for one fundamental bioinformatics application (Smith-Waterman protein database search) across different GPU architectures, considering single and multi-GPU configurations from different vendors. The experimental work showed that, while both CUDA and SYCL versions achieve similar performance on NVIDIA devices, the latter demonstrated remarkable code portability to other GPU architectures, such as AMD and Intel. Furthermore, the architectural efficiency rates achieved on these devices were superior in 3 of the 4 cases tested. This brief study highlights the potential of SYCL as a viable solution for achieving both performance and portability in the heterogeneous computing ecosystem.

Palavras-chave: oneAPI, SYCL, GPU, CUDA, Performance portability