Document Type
Conference Paper
Publication Date
2023
DOI
10.1145/3624062.3624251
Publication Title
Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis
Pages
1705-1712
Conference Name
Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W 2023), November 12-17, 2023, Denver, Colorado
Abstract
We describe our experience porting FUN3D’s CUDA-optimized kernels to Intel oneAPI SYCL.We faced several challenges, including foremost the suboptimal performance of the oneAPI code on Intel’s new data center GPU. Suboptimal performance of the oneAPI code was due primarily to high register spills, memory latency, and poor vectorization. We addressed these issues by implementing the kernels using Intel oneAPI’s Explicit SIMD SYCL extension (ESIMD) API. The ESIMD API enables the writing of explicitly vectorized kernel code, gives more precise control over register usage and prefetching, and better handles thread divergence compared to SYCL. The ESIMD code outperforms the optimized SYCL code by up to a factor of 3.6, depending on the kernel.We also compared the performance of three ESIMD kernels on the Intel Data Center Max 1550 GPU with the CUDA-optimized versions on NVIDIA V100 and A100 GPUs. We found the performance of a single tile of the Intel GPU using ESIMD greater than NVIDIA V100 and similar to NVIDIA A100.
Rights
© 2023 Copyright held by the owner/authors.
This work is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Original Publication Citation
Zubair, M., Walden, A., Nastac, G., Nielsen, E., Bauinger, C., & Zhu, X. (2023). Optimization of ported CFD kernels on Intel Data Center GPU Max 1550 using oneAPI ESIMD. In Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W 2023). Association for Computing Machinery. https://doi.org/10.1145/3624062.3624251
Repository Citation
Zubair, M., Walden, A., Nastac, G., Nielsen, E., Bauinger, C., & Zhu, X. (2023). Optimization of ported CFD kernels on Intel Data Center GPU Max 1550 using oneAPI ESIMD. In Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W 2023). Association for Computing Machinery. https://doi.org/10.1145/3624062.3624251
ORCID
0000-0002-5449-1779 (Zubair)