Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath
Organizations: IPVS, University of Stuttgart Stuttgart, Germany
Abstract
Modern multi-vendor GPU environments force a choice between portable code and native performance. GPRat is an open-source Python library for exact Gaussian process regression built on the HPX asynchronous many-task runtime, tiled algorithms, and CPU/CUDA BLAS backends. We contribute a UXL Foundation oneMath backend with a hybrid HPX/SYCL design, extending GPRat to AMD and Intel GPUs. The new SYCL backend comes within 3% of native CUDA on an NVIDIA A30 at the largest problem size and outperforms the GPflow and GPyTorch libraries by up to 1.75x and 2.17x on the A30 and up to 1.79x and 4.62x on an AMD Instinct MI210. On an Intel Arc B580, a consumer-class card with FP64 throughput below our CPUs, the unmodified SYCL backend trails GPRat's CPU backend. Overall, oneMath's dispatch to vendor-native BLAS lets a single SYCL codebase match CUDA on NVIDIA and outperform established Python GP frameworks on AMD, without vendor-specific code.
Figures & tables
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| CPU | NVIDIA GPU | AMD GPU | Intel GPU | |
|---|---|---|---|---|
| Device | AMD EPYC 9274F | NVIDIA A30 | AMD Instinct MI210 | Intel Arc B580 |
| Cores/CUs | Cores | 56 SMs | 104 CUs | 20 Xe Cores |
| L1 cache | / core | / SM | / CU | / Xe Core |
| L2 cache | / core | |||
| L3 cache | / socket | – | – | – |
| RAM/VRAM | DDR5 | HBM2e | HBM2e | GDDR6 |
GPU Acceleration
GPU acceleration uses parallel processors, specialized kernels, and memory-aware systems to speed computation across AI and scientific workloads.
See all 200 papers