AMD and Intel partner to optimize PyTorch performance for x86 CPUs
10/21/2026 — 10/21, 21:17·2 sources (all)·2 reports (all)
Key takeaways
- AMD and Intel have announced a partnership to integrate their processor optimizations into oneDNN, making it the default open-source acceler…
Background & analysis
On October 20, 2026, AMD and Intel jointly announced a collaboration to optimize PyTorch performance on x86 CPUs. The companies plan to integrate their respective processor optimizations into the open-source deep learning library oneDNN, establishing it as the default open-source library for x86 acceleration within PyTorch. As part of this initiative, AMD will integrate its ZenDNN optimizations into oneDNN and join the UXL Foundation as a steering committee member, with the partnership facilitated by the x86 Ecosystem Advisory Group to provide a unified software path across both companies' CPUs. Beyond oneDNN, AMD and Intel are also advancing AI Compute Extensions for x86 to prioritize matrix multiplication acceleration, with plans to integrate these extensions into PyTorch through oneDNN in the future.
AI-generated from 1 reports · updated 9 hours ago
Latest turnAMD and Intel are partnering to bring CPU inference optimizations for PyTorch under the unified oneDNN library. This collaboration aims to standardize performance optimization paths for AI inference on x86 CPUs.
- Heat index
- 165
- All sources
- 2
- All reports
- 2
- First seen
- 9 hours ago
Reports on this story headlines open the original
AMD and Intel are partnering to bring CPU inference optimizations for PyTorch under the unified oneDNN library. This collaboration aims to standardize performance optimization paths for AI inference on x86 CPUs.
Tom's HardwareAI score 68AMD and Intel said they will consolidate their respective processor optimizations into oneDNN, the open-source deep learning library positioned as the default x86 acceleration path inside PyTorch. AMD will fold in its ZenDNN work and join the UXL Foundation's steering committee. The two are also developing AI Compute Extensions for x86, focused on matrix multiplication, to be exposed to PyTorch through future oneDNN updates.
IT之家AI score 58
Other stories people are talking about
- Heat index 966RisingDeepSeek open-sources DeepInfer large-scale inference framework16 sources
- Heat index 919SurgeNvidia GTC Berlin: Jensen Huang Unveils DSX POD and Enterprise AI Agent Arc10 sources
- Heat index 904RisingDHS orders federal civilian agencies to purge DeepSeek tech19 sources
- Heat index 814SurgeOpenAI says two agents weakened misalignment monitoring10 sources
- Heat index 627RisingSpaceX earnings call: Musk says 2027 ARR could reach $1 trillion10 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion