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

oneAPI Deep Neural Network Library (oneDNN) is an
open-source performance library for deep learning applications. The library
includes basic building blocks for neural networks optimized
for Intel Architecture Processors, Intel Processor Graphics and 
Xe architecture-based Graphics.

This package contains oneDNN v@PROJECT_VERSION@ (@DNNL_VERSION_HASH@).

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/v@DNNL_VERSION_MAJOR@.@DNNL_VERSION_MINOR@)
  explains the programming model, supported functionality, and implementation
  details, and includes annotated examples.
* API reference (https://oneapi-src.github.io/oneDNN/v@DNNL_VERSION_MAJOR@.@DNNL_VERSION_MINOR@/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 processor with Intel SSE4.1 support
* 4th, 5th, 6th, 7th, and 8th generation Intel(R) Core(TM) processor
* Intel(R) Xeon(R) processor E3, E5, and E7 family (formerly Sandy Bridge,
  Ivy Bridge, Haswell, and Broadwell)
* Intel(R) Xeon Phi(TM) processor (formerly Knights Landing and Knights Mill)
* Intel Xeon Scalable processor (formerly Skylake, Cascade Lake, and Cooper
  Lake)
* future Intel Xeon Scalable processor (code name Sapphire 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 HD Graphics
* Intel UHD Graphics
* Intel Iris Plus Graphics
* Xe architecture-based Graphics (code named DG1 and Tiger Lake)

## 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               | TBB 2017 Update 2 or later (libtbb.so)             |
| cpu_dpcpp_gpu_dpcpp   | Intel oneAPI DPC++ Compiler runtime (libsycl.so.3) |
|                       | TBB 2020.2 or later (libtbb.so.12)                 |
|                       | oneAPI Level Zero loader (libze_loader.so.1)       |
|                       | 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                               |
| cpu_tbb               | TBB 2017 Update 2 or later (tbb.dll)               |
| cpu_dpcpp_gpu_dpcpp   | Intel oneAPI DPC++ Compiler runtime (sycl.dll)     |
|                       | TBB 2020.2 or later (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               | TBB 2017 Update 2 or later (libtbb.dylib) |

Support
-------

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

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

WARNING:
This is pre-production software and functionality may change without prior
notice.

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/IntelSEAPI/tree/master/ittnotify)
* 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)

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.

# Trademark Information

Intel, the Intel logo, Intel Atom, Intel Core, Intel Xeon Phi, 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