Today for AI
HOT RADAR
computeHEAT 10.8°

AI CURATED HOT STORY · 10/21/2026

AMD and Intel Unite to Standardize x86 AI Development Path

1 reports archived1 independent sourcesupdated 10/21/2026, 15:08:31
Synthesis & Latest Updates
1 Sources Cross-Validated

AMD and Intel have announced a rare collaboration to consolidate processor optimizations into the open-source library oneDNN, making it the default backend for x86 acceleration in PyTorch. The companies are also advancing 'AI Compute Extensions' (ACE), a next-generation x86 instruction set architecture aimed at reducing ecosystem fragmentation and improving cross-platform AI development efficiency through a unified software path.

LATEST/AMD and Intel have announced a rare collaboration to consolidate processor optimizations into the open-source library oneDNN, making it the default backend for x86 acceleration in PyTorch. The companies are also advancing 'AI Compute Extensions' (ACE), a next-generation x86 instruction set architecture aimed at reducing ecosystem fragmentation and improving cross-platform AI development efficiency through a unified software path.

HEAT TRENDHourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·72 pts
    • AMD will integrate ZenDNN optimizations into oneDNN and join the Unified Acceleration Foundation (UXL Foundation) as a steering committee member.
    • oneDNN will become the default open-source library for x86 acceleration in PyTorch, enabling support via a single software path.
    • Both companies are advancing the 'AI Compute Extensions' (ACE) instruction set architecture, focusing on accelerating matrix multiplication operations.
AMD and Intel Unite to Standardize x86 AI Development Path | Today for AI