Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN) is an open source performance library for Deep Learning (DL) applications intended for acceleration of DL frameworks on Intel(R) architecture. Intel(R) MKL-DNN includes highly vectorized and threaded building blocks for implementation of convolutional neural networks (CNN) with C and C++ interfaces. We created this project to enable the DL community to innovate on Intel(R) processors.
Intel MKL-DNN includes functionality similar to Intel(R) Math Kernel Library (Intel(R) MKL) 2017, but is not API compatible. We are investigating how to unify the APIs in future Intel MKL releases.
This release is a technical preview with functionality necessary to accelerate bleeding edge image recognition topologies, including Cifar*, AlexNet*, VGG*, GoogleNet* and ResNet*. As with any technical preview, APIs may change in future updates.
License
Intel MKL-DNN is licensed under Apache License Version 2.0.
Documentation
The latest Intel MKL-DNN documentation is at GitHub pages.
Support
Please report issues and suggestions via GitHub issues or start a topic on Intel MKL forum.
How to Contribute
We welcome community contributions to Intel MKL-DNN. If you have an idea how to improve the library:
-
Share your proposal via GitHub issues.
-
Ensure you can build the product and run all the examples with your patch
-
In the case of a larger feature, create a test
-
Submit a pull request
We will review your contribution and, if any additional fixes or modifications are necessary, may provide feedback to guide you. When accepted, your pull request will be merged into our internal and GitHub repositories.
System Requirements
Intel MKL-DNN supports Intel(R) 64 architecture processors and is optimized for
- Intel(R) Xeon(R) processor E5-xxxx v3 (codename Haswell)
- Intel(R) Xeon(R) processor E5-xxxx v4 (codename Broadwell)
Processors without Intel(R) Advanced Vector Extensions 2 (Intel(R) AVX2) are not supported in this release.
The software dependencies are:
The software was validated on RedHat* Enterprise Linux 7 with
- GNU* Compiler Collection 4.8
- GNU* Compiler Collection 6.1
- Clang* 3.8.0
- Intel(R) C/C++ Compiler 16.0 or later
The implementation uses OpenMP* 4.0 SIMD extensions. We recommend using Intel(R) compiler for the best performance results.
Installation
Download Intel MKL-DNN source code or clone the repository to your system
git clone https://github.com/01org/mkl-dnn.git
Satisfy all hardware and software dependencies and ensure that the versions are correct before installing. Intel MKL-DNN uses the optimized matrix-matrix multiplication (GEMM) function from Intel MKL. The dynamic library with this functionality is included win the repository. Before building the project, download the library using the script provided:
cd scripts && ./prepare_mkl.sh && cd ..
or download manually and unpack it to the external
directory in the repository root.
Intel MKL-DNN uses a CMake-based build system
mkdir -p build && cd build && cmake .. && make
Intel MKL-DNN includes unit tests implemented using the googletest framework. To validate your build, run:
make test
Documentation is provided inline and can be generated in HTML format with Doxygen:
make doc
Documentation will reside in build/reference/html
folder.
Finally,
make install
will place the header files, libraries and documentation in /usr/local
. To change
the installation path, use the option -DCMAKE_INSTALL_PREFIX=<prefix>
when invoking CMake.