Skip to content

Latest commit

 

History

History
73 lines (63 loc) · 4.53 KB

README.md

File metadata and controls

73 lines (63 loc) · 4.53 KB

Build on Linux* Systems

The software was validated on:

Software Requirements

  • CMake* 3.9 or higher
  • GCC* 4.8 or higher to build the Inference Engine

Build Steps

  1. Clone submodules: 
    git submodule init
git submodule update --recursive
  2. Install build dependencies using the install_dependencies.sh script in the project root folder.
  3. Create a build folder:
  mkdir build
  1. Inference Engine uses a CMake-based build system. In the created build directory, run cmake to fetch project dependencies and create Unix makefiles, then run make to build the project:
  cmake -DCMAKE_BUILD_TYPE=Release ..
  make -j16

You can use the following additional build options:

  • Internal JIT GEMM implementation is used by default.
  • To switch to OpenBLAS* implementation, use GEMM=OPENBLAS option and BLAS_INCLUDE_DIRS and BLAS_LIBRARIES cmake options to specify path to OpenBLAS headers and library, for example use the following options on CentOS*: -DGEMM=OPENBLAS -DBLAS_INCLUDE_DIRS=/usr/include/openblas -DBLAS_LIBRARIES=/usr/lib64/libopenblas.so.0
  • To switch to optimized MKL-ML* GEMM implementation, use GEMM=MKL and MKLROOT cmake options to specify path to unpacked MKL-ML with include and lib folders, for example use the following options: -DGEMM=MKL -DMKLROOT=<path_to_MKL>. MKL-ML* package can be downloaded here
  • To switch on/off the CPU and GPU plugins, use cmake options -DENABLE_MKL_DNN=ON/OFF and -DENABLE_CLDNN=ON/OFF.

Build on Windows* Systems:

The software was validated on:

Software Requirements

Build Steps

  1. Clone submodules: 
    git submodule init
git submodule update --recursive
  2. Download and install Intel® C++ Compiler 18.0
  3. Install OpenBLAS:
    1. Download OpenBLAS*
    2. Unzip the downloaded package to a directory on your machine. In this document, this directory is referred to as <OPENBLAS_DIR>.
  4. Create build directory: 
    mkdir build
  5. In the build directory, run cmake to fetch project dependencies and generate a Visual Studio solution:
cd build
cmake -G "Visual Studio 15 2017 Win64" -T "Intel C++ Compiler 18.0" -DOS_FOLDER=ON ^
    -DCMAKE_BUILD_TYPE=Release ^
    -DICCLIB="C:\Program Files (x86)\IntelSWTools\compilers_and_libraries_2018\windows\compiler\lib" ..
  • To switch to OpenBLAS GEMM implementation, use -DGEMM=OPENBLAS cmake option and specify path to OpenBLAS using -DBLAS_INCLUDE_DIRS=<OPENBLAS_DIR>\include and -DBLAS_LIBRARIES=<OPENBLAS_DIR>\lib\libopenblas.dll.a options. Prebuilt OpenBLAS* package can be downloaded here, mingw64* runtime dependencies here
  • To switch to optimized MKL-ML GEMM implementation, use GEMM=MKL and MKLROOT cmake options to specify path to unpacked MKL-ML with include and lib folders, for example use the following options: -DGEMM=MKL -DMKLROOT=<path_to_MKL>. MKL-ML* package can be downloaded here
  1. Build generated solution in Visual Studio 2017 or run cmake --build . --config Release to build from the command line.

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