oneAPI Deep Neural Network Library (oneDNN)
===========================================

oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform
performance library of basic building blocks for deep learning applications.
oneDNN is part of oneAPI (https://oneapi.io).
The library is optimized for Intel(R) Architecture Processors and Intel Graphics.

oneDNN is intended for deep learning applications and framework
developers interested in improving application performance on CPUs and GPUs.

This package contains oneDNN v3.3.4 (d0c9a50ec3a6e49f82d23f22d5f8b8dc1d0a0308).

You can find information about the latest version and release notes
at the oneDNN Github (https://github.com/oneapi-src/oneDNN/releases).

Documentation
-------------

* Developer guide (https://oneapi-src.github.io/oneDNN/v3.3)
  explains the programming model, supported functionality, and implementation
  details, and includes annotated examples.
* API reference (https://oneapi-src.github.io/oneDNN/v3.3/modules.html)
provides a comprehensive reference of the library API.

System Requirements
-------------------

oneDNN supports systems based on Intel 64 or AMD64 architectures.

The library is optimized for the following CPUs:
* Intel Atom(R) processor (at least Intel SSE4.1 support is required)
* Intel Core(TM) processor (at least Intel SSE4.1 support is required)
* Intel Xeon(R) processor E3, E5, and E7 family (formerly Sandy Bridge,
  Ivy Bridge, Haswell, and Broadwell)
* Intel Xeon Scalable processor (formerly Skylake, Cascade Lake, Cooper
  Lake, Ice Lake, and Sapphire Rapids)
* Intel Xeon CPU Max Series (formerly Sapphire Rapids HBM)
* future Intel Xeon Scalable processor (code name Granite Rapids)

oneDNN detects the instruction set architecture (ISA) at runtime and uses
just-in-time (JIT) code generation to deploy the code optimized
for the latest supported ISA. Future ISAs may have initial support in the
library disabled by default and require the use of run-time controls to enable
them. See CPU dispatcher control (https://oneapi-src.github.io/oneDNN/dev_guide_cpu_dispatcher_control.html)
for more details.

The library is optimized for the following GPUs:
* Intel Processor Graphics based on Gen9, Gen9.5 and Gen11, and Gen12 architectures
* Intel Iris(R) Xe graphics (formerly DG1)
* Intel Arc(TM) graphics (formerly Alchemist and DG2)
* Intel Data Center GPU Flex Series (formerly Arctic Sound-M)
* Intel Data Center GPU Max Series (formerly Ponte Vecchio)

## Linux

Common dependencies:
* GNU C Library (libc.so) 2.12 or later
* GNU Standard C++ Library v3 (libstdc++.so) compatible with GCC 4.8 or later
* Dynamic Linking Library (libdl.so)
* C Math Library (libm.so)
* POSIX Threads Library (libpthread.so)

Runtime specific dependencies:

| Runtime configuration | Dependency                                         |
| --------------------- | -------------------------------------------------- |
| cpu_gomp              | GNU OpenMP runtime (libgomp.so)                    |
| cpu_iomp              | Intel OpenMP runtime (libiomp5.so)                 |
| cpu_tbb               | Threading Building Blocks (libtbb.so)              |
| cpu_dpcpp_gpu_dpcpp   | Intel oneAPI DPC++ Compiler runtime (libsycl.so)   |
|                       | Threading Building Blocks (libtbb.so)              |
|                       | oneAPI Level Zero loader (libze_loader.so)         |
|                       | OpenCL loader (libOpenCL.so)                       |

## Windows

Common dependencies:
* Microsoft Visual C++ Redistributable 2015 or later (msvcrt.dll)

Runtime specific dependencies:

| Runtime configuration | Dependency                                         |
| --------------------- | -------------------------------------------------- |
| cpu_vcomp             | No additional dependencies                         |
| cpu_iomp              | Intel OpenMP runtime (iomp5.dll)                   |
| cpu_tbb               | Threading Building Blocks (tbb.dll)                |
| cpu_dpcpp_gpu_dpcpp   | Intel oneAPI DPC++ Compiler runtime (sycl.dll)     |
|                       | Threading Building Blocks (tbb.dll)                |
|                       | oneAPI Level Zero loader (ze_loader.dll)           |
|                       | OpenCL loader (OpenCL.dll)                         |

## macOS

Common dependencies:
* System C/C++ runtime (libc++.dylib, libSystem.dylib) compatible with
  macOS 10.13 (High Sierra) or later

Runtime specific dependencies:

| Runtime configuration | Dependency                                |
| --------------------- | ----------------------------------------- |
| cpu_iomp              | Intel OpenMP runtime (libiomp5.dylib)     |
| cpu_tbb               | Threading Building Blocks (libtbb.dylib) |

Support
-------

Please submit your questions, feature requests, and bug reports on the
GitHub issues page (https://github.com/oneapi-src/oneDNN/issues).

You may reach out to project maintainers privately at
dnnl.maintainers@intel.com.

License
-------

oneDNN is licensed under Apache License Version 2.0. Refer to the "LICENSE"
file for the full license text and copyright notice.

This distribution includes third party software governed by separate license
terms.

3-clause BSD license:
* Xbyak (https://github.com/herumi/xbyak)
* Instrumentation and Tracing Technology API (ITT API) (https://github.com/intel/ittapi)
* CMake (https://github.com/Kitware/CMake)

Boost Software License, Version 1.0:
* Boost C++ Libraries (https://www.boost.org/)

MIT License:
* Intel Graphics Compute Runtime for oneAPI Level Zero and OpenCL Driver (https://github.com/intel/compute-runtime)
* Intel Graphics Compiler (https://github.com/intel/intel-graphics-compiler)
* oneAPI Level Zero (https://github.com/oneapi-src/level-zero)
* Intel Metrics Discovery Application Programming Interface (https://github.com/intel/metrics-discovery)

This third party software, even if included with the distribution of
the Intel software, may be governed by separate license terms, including
without limitation, third party license terms, other Intel software license
terms, and open source software license terms. These separate license terms
govern your use of the third party programs as set forth in the
"THIRD-PARTY-PROGRAMS" file.

# Security

See Intel's Security Center (https://www.intel.com/content/www/us/en/security-center/default.html)
for information on how to report a potential security issue or vulnerability.

# Trademark Information

Intel, the Intel logo, Arc, Intel Atom, Intel Core, Iris,
OpenVINO, the OpenVINO logo, Pentium, VTune, and Xeon are trademarks
of Intel Corporation or its subsidiaries.

\* Other names and brands may be claimed as the property of others.

Microsoft, Windows, and the Windows logo are trademarks, or registered
trademarks of Microsoft Corporation in the United States and/or other
countries.

OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission
by Khronos.

(C) Intel Corporation
