Backend
Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath
arXiv cs.DC0 views
arXiv:2611.17565v1 Announce Type: new 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.
Source:https://arxiv.org/abs/2611.17565PreviousThe Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text TransferNextSuperfluid: Local AI Server for Distributed LLM Inference
Related posts
What Actually Happens When You Make a REST API Request?
0dev.to WebDev

Ping64|How Captchas Tell the Difference Between a Human and a Bot
0dev.to Security
Your coding agent has a shell. What stops it from using it badly?
0dev.to Security
How to Check WordPress Plugins for Known Vulnerabilities With the WPScan API
0dev.to Security
The Tool Continues; the Human Stops
0dev.to Security
Your developer disappeared: a 10-step recovery checklist
0dev.to Security