# AMD and Intel align x86 CPU software work for PyTorch

> AMD and Intel said on 20 October they will combine x86 CPU optimizations for PyTorch in the open-source oneDNN library. The companies aim to give developers a common software path for AI workloads across AMD and Intel processors.

- Canonical URL: https://newsverum.com/en/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026
- Publisher: Newsverum
- Section: Technology
- Country: United States
- Published: 2026-10-21T00:43:59+00:00
- Updated: 2026-10-21T00:43:59+00:00
- Event / data period: 2026-10-20
- Other editions: [Türkçe](https://newsverum.com/tr/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md), [العربية](https://newsverum.com/ar/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md), [Français](https://newsverum.com/fr/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md), [Español](https://newsverum.com/es/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md), [Deutsch](https://newsverum.com/de/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md), [Português](https://newsverum.com/pt/news/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026.md)

AMD is integrating its ZenDNN optimizations into oneDNN and has joined the UXL Foundation as a Steering Member. The companies are also working on future x86 AI Compute Extensions designed to accelerate matrix multiplication.

The announcement says oneDNN is the default open-source library for x86 acceleration within PyTorch. It gives no integration schedule or measured performance gains.

## Data

### AMD and Intel align x86 CPU software work for PyTorch

Methodology: AMD and Intel said on 20 October they will combine x86 CPU optimizations for PyTorch in the open-source oneDNN library. The companies aim to give developers a common software path for AI workloads across AMD and Intel processors.

| date | label | description | status |
|---|---|---|---|
| 2026-10-20 | AMD and Intel align x86 CPU software work for PyTorch | AMD and Intel said on 20 October they will combine x86 CPU optimizations for PyTorch in the open-source oneDNN library. The companies aim to give developers a common software path for AI workloads across AMD and Intel processors. | occurred |

Sources: <https://www.intel.com/content/www/us/en/newsroom/news/data-center/amd-intel-simplify-x86-ai-development-with-pytorch.html> · Download data: [JSON](https://newsverum.com/api/v1/articles/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026/data/amd-announcement?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/amd-intel-x86-pytorch-onednn-ai-software-collaboration-2026/data/amd-announcement?lang=en&format=csv)

## Sources

- [Intel Newsroom](<https://www.intel.com/content/www/us/en/newsroom/news/data-center/amd-intel-simplify-x86-ai-development-with-pytorch.html>) (Source checked: 2026-10-21; Published: 2026-10-20)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)