# oneDNN 3.14 Released With ACE Support, Initial AMD Zen Optimizations

DevFeed: [oneDNN 3.14 Released With ACE Support, Initial AMD Zen Optimizations](<https://devfeed.tech/articles/onednn-3-14-released-with-ace-support-initial-amd-zen-optimizations-97718.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/oneDNN-3.14-Released>)

Author: Michael Larabel

Published: 2026-10-23T14:12:33Z

Content type: release

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [PyTorch](<https://devfeed.tech/topics/pytorch.md>)

Tags: [ai-compute](<https://devfeed.tech/tags/ai-compute.md>), [amd](<https://devfeed.tech/tags/amd.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [crescent-island](<https://devfeed.tech/tags/crescent-island.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [intel](<https://devfeed.tech/tags/intel.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>), [performance](<https://devfeed.tech/tags/performance.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [processors](<https://devfeed.tech/tags/processors.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [release](<https://devfeed.tech/tags/release.md>), [software](<https://devfeed.tech/tags/software.md>), [support](<https://devfeed.tech/tags/support.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

## AI overview

oneDNN 3.14 adds opt-in MATMUL and inner-product performance optimizations for AMD Zen CPUs. Enabling them requires building with `ONEDNN_X64_USE_ZEN=ON` and including ZenDNN code, either manually or through `ONEDNN_ZENDNN_FETCH=ON`. The release also introduces initial support for AI Compute Extensions (ACE) intended for future AMD and Intel processors, and reports performance improvements for upcoming Xeon Diamond Rapids and Intel GPU products. The excerpt does not provide benchmark results or further implementation details.

## Source excerpt

The UXL Foundation announced today the release of oneDNN 3.14 as the latest feature update to this library providing optimized deep learning operations for software like PyTorch, TensorFlow, OpenVINO, and others. While oneDNN began as an Intel software project, making this version notable is beginning to see AMD Zen CPU optimizations land in oneDNN proper...