Skip To Main Content
Intel logo - Return to the home page
My Tools

Select Your Region

Asia Pacific

  • Asia Pacific (English)
  • Australia (English)
  • India (English)
  • Indonesia (Bahasa Indonesia)
  • Japan (日本語)
  • Korea (한국어)
  • Mainland China (简体中文)
  • Taiwan (繁體中文)
  • Thailand (ไทย)
  • Vietnam (Tiếng Việt)

Europe

  • France (Français)
  • Germany (Deutsch)
  • Ireland (English)
  • Italy (Italiano)
  • Poland (Polski)
  • Spain (Español)
  • Turkey (Türkçe)
  • United Kingdom (English)

Latin America

  • Argentina (Español)
  • Brazil (Português)
  • Chile (Español)
  • Colombia (Español)
  • Latin America (Español)
  • Mexico (Español)
  • Peru (Español)

Middle East/Africa

  • Israel (עברית)

North America

  • United States (English)
  • Canada (English)
  • Canada (Français)
Sign In to access restricted content

Using Intel.com Search

You can easily search the entire Intel.com site in several ways.

  • Brand Name: Core i9
  • Document Number: 123456
  • Code Name: Alder Lake
  • Special Operators: “Ice Lake”, Ice AND Lake, Ice OR Lake, Ice*

Quick Links

You can also try the quick links below to see results for most popular searches.

  • Product Information
  • Support
  • Drivers & Software

Recent Searches

Sign In to access restricted content

Advanced Search

Only search in

Sign in to access restricted content.

The browser version you are using is not recommended for this site.
Please consider upgrading to the latest version of your browser by clicking one of the following links.

  • Safari
  • Chrome
  • Edge
  • Firefox

Intel® oneAPI Deep Neural Network Library

Increase Deep Learning Framework Performance on CPUs and GPUs

Develop Faster Deep Learning Frameworks and Applications

The Intel® oneAPI Deep Neural Network Library (oneDNN) provides highly optimized implementations of deep learning building blocks. With this open source, cross-platform library, deep learning application and framework developers can use the same API for CPUs, GPUs, or both—it abstracts out instruction sets and other complexities of performance optimization.

Using this library, you can:

  • Improve performance of frameworks you already use, such as OpenVINO™ toolkit, Intel® AI Analytics Toolkit, Intel® Distribution for PyTorch*, and Intel® Distribution for TensorFlow*.
  • Develop faster deep learning applications and frameworks using optimized building blocks.
  • Deploy applications optimized for Intel CPUs and GPUs without writing any target-specific code.
Download as Part of the Toolkit

oneDNN is included as part of the Intel® oneAPI Base Toolkit, which is a core set of tools and libraries for developing high-performance, data-centric applications across diverse architectures.

Get It Now
Intel® oneAPI DL Framework Developer Toolkit
Download the Stand-Alone Version

A stand-alone download of oneDNN is available. You can download binaries from Intel or choose your preferred repository.

Download
Runtime Version
Develop in the Cloud

Build and optimize oneAPI multiarchitecture applications using the latest optimized Intel® oneAPI and AI tools, and test your workloads across Intel® CPUs and GPUs. No hardware installations, software downloads, or configuration necessary. Free for 120 days with extensions possible.

 

Get Access
Help oneDNN Evolve

oneDNN is part of the oneAPI industry standards initiative. We welcome you to participate.

 

Specification

Open Source Version (GitHub*)


Features

Automatic Optimization

  • Use existing deep learning frameworks
  • Develop platform-independent deep learning applications and deploy your instruction set architecture (ISA) with automatic detection of and optimization.
     

Network Optimization

  • Identify performance bottlenecks using Intel® VTune™ Profiler
  • Use automatic memory format selection and propagation based on hardware and convolutional parameters
  • Fuse primitives with operations applied to the primitive’s result, for instance, Conv+ReLU
  • Quantize primitives from FP32 to FP16, bf16, or int8 using Intel® Neural Compressor

Optimized Implementations of Key Building Blocks

  • Convolution
  • Matrix multiplication
  • Pooling
  • Batch normalization
  • Activation functions
  • Recurrent neural network (RNN) cells
  • Long short-term memory (LSTM) cells
     

Abstract Programming Model

  • Primitive: Any low-level operation from which more complex operations are constructed, such as convolution, data format reorder, and memory
  • Memory: Handles to memory allocated on a specific engine, tensor dimensions, data type, and memory format
  • Engine: A hardware processing unit, such as a CPU or GPU
  • Stream: A queue of primitive operations on an engine

Learn More


Benchmarks

Case Studies

Preparing for Aurora: Ensuring the Portability of Deep Learning Software to Explore Fusion Energy

Argonne National Laboratory ported FusionDL, a collection of machine learning models and implementations in multiple frameworks, including TensorFlow and PyTorch optimized by oneDNN, to the Aurora exascale supercomputer.

Read More on HPCwire*

Digital Transformation in Tough Times: Four Innovative Examples Powered by Data, AI, and Flexible Infrastructure

Large datasets and AI are applied securely and reliably to address challenges with the supply chain, utilities, healthcare, and COVID-19 risk management for returning to work while preserving privacy.

Read More on VentureBeat

Demonstrations

Leverage Deep Learning Optimizations from Intel in TensorFlow*

oneDNN optimizations are available in TensorFlow, which enables developers to seamlessly benefit from Intel's optimizations.

Read More on oneAPI.io

Accelerate Bfloat16-based PyTorch*

Engineers from Intel and Facebook* introduce the latest software advancements added to Intel® Extension for PyTorch* on top of PyTorch and oneDNN.

Read More on Medium

News

TensorFlow and oneDNN in Partnership

Google* and Intel have been collaborating closely and optimizing TensorFlow to fully use new hardware features and accelerators.

Watch the Video on oneAPI.io

Software AI Accelerators: AI Performance Boost for Free

Accelerate the deep learning framework you already use, such as TensorFlow, PyTorch, or Apache MXNe*, with oneDNN.

Read More on VentureBeat

Documentation & Code Samples

Documentation

  • Installation Guide (All Operating Systems)
  • Get Started Guide
  • API Reference
  • Developer Guide and Reference
  • Release Notes
  • System Requirements

View All Documentation

Code Samples

Get Started

oneDNN: Get Started

Learn how to configure and compile oneDNN applications using prebuilt oneDNN binaries, and how to run these applications on different Intel architectures.

oneDNN with SYCL* Interoperability

Use this code sample to learn about programming for Intel CPU and GPU with SYCL* extensions API in oneDNN.

Tutorials

A oneDNN Library for Convolutional Neural Network (CNN) Inference (FP32)

Learn how oneDNN helps to build a neural network topology for forward-pass inference that implements topology layers as numbered primitives.

oneDNN Tutorials

Use these guided samples on a Jupyter* Notebook to examine oneDNN functionality for developing deep learning applications and neural networks, optimized for Intel CPUs and GPUs.

View All oneDNN Samples

View All oneAPI Samples
 

How to work with code samples:

  • Use a command-line interface: Windows* | Linux*
  • Use an IDE: Windows | Linux

Training

Understanding oneDNN

  • What Is the oneDNN Library? [3:46]
  • oneDNN Library Programming Model and Samples [4:33]

 

AI Model Performance

  • How to Debug AI Model Performance on Intel CPUs

 

🗐 View All Resources

🗗 Training & Events Calendar

Specifications

Processors:

  • Intel Atom® processors with Intel® Streaming SIMD Extensions
  • Intel® Core™ processors
  • Intel® Xeon® processors
  • Intel Xeon Scalable processors

 

GPUs:

  • Intel® Processor Graphics Gen9 and above
  • Intel® Iris® Xe MAX graphic

 

Host & target operating systems:

  • Linux*
  • Windows*
  • macOS*

Languages:

  • SYCL
    Note Must have Intel oneAPI Base Toolkit installed
  • C and C++

 

Compilers:

  • Intel® oneAPI DPC++/C++ Compiler
  • Intel® C++ Compiler Classic
  • Clang*
  • GNU C++ Compiler*
  • Microsoft Visual Studio*
  • LLVM* for Apple*

 

Threading runtimes:

  • Intel® oneAPI Threading Building Blocks
  • OpenMP*
  • SYCL

For more information, see the system requirements.

Get Help

Your success is our success. Access these resources when you need assistance.

  • Intel oneAPI Deep Neural Network Library

For additional help, see oneAPI Support.

Stay in the Know with All Things CODE

Sign up to receive the latest trends, tutorials, tools, training, and more to
help you write better code optimized for CPUs, GPUs, FPGAs, and other
accelerators—stand-alone or in any combination.

 

Sign Up
  • Features
  • Benchmarks
  • Documentation & Code Samples
  • Training
  • Specifications
  • Help
  • Company Overview
  • Contact Intel
  • Newsroom
  • Investors
  • Careers
  • Corporate Responsibility
  • Diversity & Inclusion
  • Public Policy
  • © Intel Corporation
  • Terms of Use
  • *Trademarks
  • Cookies
  • Privacy
  • Supply Chain Transparency
  • Site Map
  • Do Not Share My Personal Information
  • Recycling

Intel technologies may require enabled hardware, software or service activation. // No product or component can be absolutely secure. // Your costs and results may vary. // Performance varies by use, configuration and other factors. // See our complete legal Notices and Disclaimers. // Intel is committed to respecting human rights and avoiding complicity in human rights abuses. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to a violation of an internationally recognized human right.

Intel Footer Logo