Skip to content

Latest commit

 

History

History
291 lines (215 loc) · 13.7 KB

MKLDNN_README.md

File metadata and controls

291 lines (215 loc) · 13.7 KB
Raw

Build/Install MXNet with MKL-DNN

A better training and inference performance is expected to be achieved on Intel-Architecture CPUs with MXNet built with Intel MKL-DNN on multiple operating system, including Linux, Windows and MacOS. In the following sections, you will find build instructions for MXNet with Intel MKL-DNN on Linux, MacOS and Windows.

Please find MKL-DNN optimized operators and other features in the MKL-DNN operator list.

The detailed performance data collected on Intel Xeon CPU with MXNet built with Intel MKL-DNN can be found here.

Contents

Linux

Prerequisites

sudo apt-get update
sudo apt-get install -y build-essential git
sudo apt-get install -y libopenblas-dev liblapack-dev
sudo apt-get install -y libopencv-dev
sudo apt-get install -y graphviz

Clone MXNet sources

git clone --recursive https://github.com/apache/incubator-mxnet.git
cd incubator-mxnet

Build MXNet with MKL-DNN

make -j $(nproc) USE_OPENCV=1 USE_MKLDNN=1 USE_BLAS=mkl USE_INTEL_PATH=/opt/intel

If you don't have the full MKL library installation, you might use OpenBLAS as the blas library, by setting USE_BLAS=openblas.

MacOS

Prerequisites

Install the dependencies, required for MXNet, with the following commands:

  • Homebrew
  • llvm (clang in macOS does not support OpenMP)
  • OpenCV (for computer vision operations)
# Paste this command in Mac terminal to install Homebrew
/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

# install dependency
brew update
brew install pkg-config
brew install graphviz
brew tap homebrew/core
brew install opencv
brew tap homebrew/versions
brew install llvm

Clone MXNet sources

git clone --recursive https://github.com/apache/incubator-mxnet.git
cd incubator-mxnet

Build MXNet with MKL-DNN

LIBRARY_PATH=$(brew --prefix llvm)/lib/ make -j $(sysctl -n hw.ncpu) CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ USE_OPENCV=1 USE_OPENMP=1 USE_MKLDNN=1 USE_BLAS=apple USE_PROFILER=1

Windows

On Windows, you can use Micrsoft Visual Studio 2015 and Microsoft Visual Studio 2017 to compile MXNet with Intel MKL-DNN. Micrsoft Visual Studio 2015 is recommended.

Visual Studio 2015

To build and install MXNet yourself, you need the following dependencies. Install the required dependencies:

  1. If Microsoft Visual Studio 2015 is not already installed, download and install it. You can download and install the free community edition.
  2. Download and Install CMake 3 if it is not already installed.
  3. Download OpenCV 3, and unzip the OpenCV package, set the environment variable OpenCV_DIR to point to the OpenCV build directory (e.g.,OpenCV_DIR = C:\opencv\build ). Also, add the OpenCV bin directory (C:\opencv\build\x64\vc14\bin for example) to the PATH variable.
  4. If you have Intel Math Kernel Library (Intel MKL) installed, set MKL_ROOT to point to MKL directory that contains the include and lib. If you want to use MKL blas, you should set -DUSE_BLAS=mkl when cmake. Typically, you can find the directory in C:\Program Files (x86)\IntelSWTools\compilers_and_libraries\windows\mkl.
  5. If you don't have the Intel Math Kernel Library (MKL) installed, download and install OpenBLAS, or build the latest version of OpenBLAS from source. Note that you should also download mingw64.dll.zip along with openBLAS and add them to PATH.
  6. Set the environment variable OpenBLAS_HOME to point to the OpenBLAS directory that contains the include and lib directories. Typically, you can find the directory in C:\Downloads\OpenBLAS\.

After you have installed all of the required dependencies, build the MXNet source code:

  1. Start a Visual Studio command prompt by click windows Start menu>>Visual Studio 2015>>VS2015 X64 Native Tools Command Prompt, and download the MXNet source code from GitHub by the command:
git clone --recursive https://github.com/apache/incubator-mxnet.git
cd C:\incubator-mxent
  1. Enable Intel MKL-DNN by -DUSE_MKLDNN=1. Use CMake 3 to create a Visual Studio solution in ./build. Make sure to specify the architecture in the command:
>mkdir build
>cd build
>cmake -G "Visual Studio 14 Win64" .. -DUSE_CUDA=0 -DUSE_CUDNN=0 -DUSE_NVRTC=0 -DUSE_OPENCV=1 -DUSE_OPENMP=1 -DUSE_PROFILER=1 -DUSE_BLAS=open -DUSE_LAPACK=1 -DUSE_DIST_KVSTORE=0 -DCUDA_ARCH_NAME=All -DUSE_MKLDNN=1 -DCMAKE_BUILD_TYPE=Release
  1. Enable Intel MKL-DNN and Intel MKL as BLAS library by the command:
>"C:\Program Files (x86)\IntelSWTools\compilers_and_libraries\windows\mkl\bin\mklvars.bat" intel64
>cmake -G "Visual Studio 14 Win64" .. -DUSE_CUDA=0 -DUSE_CUDNN=0 -DUSE_NVRTC=0 -DUSE_OPENCV=1 -DUSE_OPENMP=1 -DUSE_PROFILER=1 -DUSE_BLAS=mkl -DUSE_LAPACK=1 -DUSE_DIST_KVSTORE=0 -DCUDA_ARCH_NAME=All -DUSE_MKLDNN=1 -DCMAKE_BUILD_TYPE=Release -DMKL_ROOT="C:\Program Files (x86)\IntelSWTools\compilers_and_libraries\windows\mkl"
  1. After the CMake successfully completed, in Visual Studio, open the solution file .sln and compile it, or compile the the MXNet source code by using following command:
msbuild mxnet.sln /p:Configuration=Release;Platform=x64 /maxcpucount

These commands produce mxnet library called libmxnet.dll in the ./build/Release/ or ./build/Debug folder. Also libmkldnn.dll with be in the ./build/3rdparty/mkldnn/src/Release/

  1. Make sure that all the dll files used above(such as libmkldnn.dll, libmklml*.dll, libiomp5.dll, libopenblas*.dll, etc) are added to the system PATH. For convinence, you can put all of them to \windows\system32. Or you will come across Not Found Dependencies when loading MXNet.

Visual Studio 2017

User can follow the same steps of Visual Studio 2015 to build MXNET with MKL-DNN, but change the version related command, for example,C:\opencv\build\x64\vc15\bin and build command is as below:

>cmake -G "Visual Studio 15 Win64" .. -DUSE_CUDA=0 -DUSE_CUDNN=0 -DUSE_NVRTC=0 -DUSE_OPENCV=1 -DUSE_OPENMP=1 -DUSE_PROFILER=1 -DUSE_BLAS=mkl -DUSE_LAPACK=1 -DUSE_DIST_KVSTORE=0 -DCUDA_ARCH_NAME=All -DUSE_MKLDNN=1 -DCMAKE_BUILD_TYPE=Release -DMKL_ROOT="C:\Program Files (x86)\IntelSWTools\compilers_and_libraries\windows\mkl"

Verify MXNet with python

Preinstall python and some dependent modules:

pip install numpy graphviz
set PYTHONPATH=[workdir]\incubator-mxnet\python

or install mxnet

cd python
sudo python setup.py install
python -c "import mxnet as mx;print((mx.nd.ones((2, 3))*2).asnumpy());"

Expected Output:

[[ 2.  2.  2.]
 [ 2.  2.  2.]]

Verify whether MKL-DNN works

After MXNet is installed, you can verify if MKL-DNN backend works well with a single Convolution layer.

import mxnet as mx
import numpy as np

num_filter = 32
kernel = (3, 3)
pad = (1, 1)
shape = (32, 32, 256, 256)

x = mx.sym.Variable('x')
w = mx.sym.Variable('w')
y = mx.sym.Convolution(data=x, weight=w, num_filter=num_filter, kernel=kernel, no_bias=True, pad=pad)
exe = y.simple_bind(mx.cpu(), x=shape)

exe.arg_arrays[0][:] = np.random.normal(size=exe.arg_arrays[0].shape)
exe.arg_arrays[1][:] = np.random.normal(size=exe.arg_arrays[1].shape)

exe.forward(is_train=False)
o = exe.outputs[0]
t = o.asnumpy()

More detailed debugging and profiling information can be logged by setting the environment variable 'MKLDNN_VERBOSE':

export MKLDNN_VERBOSE=1

For example, by running above code snippet, the following debugging logs providing more insights on MKL-DNN primitives convolution and reorder. That includes: Memory layout, infer shape and the time cost of primitive execution.

mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_nchw out:f32_nChw16c,num:1,32x32x256x256,6.47681
mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_oihw out:f32_OIhw16i16o,num:1,32x32x3x3,0.0429688
mkldnn_verbose,exec,convolution,jit:avx512_common,forward_inference,fsrc:nChw16c fwei:OIhw16i16o fbia:undef fdst:nChw16c,alg:convolution_direct,mb32_g1ic32oc32_ih256oh256kh3sh1dh0ph1_iw256ow256kw3sw1dw0pw1,9.98193
mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_oihw out:f32_OIhw16i16o,num:1,32x32x3x3,0.0510254
mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_nChw16c out:f32_nchw,num:1,32x32x256x256,20.4819

Enable MKL BLAS

With MKL BLAS, the performace is expected to furtherly improved with variable range depending on the computation load of the models. You can redistribute not only dynamic libraries but also headers, examples and static libraries on accepting the license Intel Simplified license. Installing the full MKL installation enables MKL support for all operators under the linalg namespace.

  1. Download and install the latest full MKL version following instructions on the intel website.

  2. Run make -j ${nproc} USE_BLAS=mkl

  3. Navigate into the python directory

  4. Run sudo python setup.py install

Verify whether MKL works

After MXNet is installed, you can verify if MKL BLAS works well with a single dot layer.

import mxnet as mx
import numpy as np

shape_x = (1, 10, 8)
shape_w = (1, 12, 8)

x_npy = np.random.normal(0, 1, shape_x)
w_npy = np.random.normal(0, 1, shape_w)

x = mx.sym.Variable('x')
w = mx.sym.Variable('w')
y = mx.sym.batch_dot(x, w, transpose_b=True)
exe = y.simple_bind(mx.cpu(), x=x_npy.shape, w=w_npy.shape)

exe.forward(is_train=False)
o = exe.outputs[0]
t = o.asnumpy()

You can open the MKL_VERBOSE flag by setting environment variable:

export MKL_VERBOSE=1

Then by running above code snippet, you probably will get the following output message which means SGEMM primitive from MKL are called. Layout information and primitive execution performance are also demonstrated in the log message.

Numpy + Intel(R) MKL: THREADING LAYER: (null)
Numpy + Intel(R) MKL: setting Intel(R) MKL to use INTEL OpenMP runtime
Numpy + Intel(R) MKL: preloading libiomp5.so runtime
MKL_VERBOSE Intel(R) MKL 2019.0 Update 3 Product build 20190125 for Intel(R) 64 architecture Intel(R) Advanced Vector Extensions 512 (Intel(R) AVX-512) enabled processors, Lnx 2.40GHz lp64 intel_thread NMICDev:0
MKL_VERBOSE SGEMM(T,N,12,10,8,0x7f7f927b1378,0x1bc2140,8,0x1ba8040,8,0x7f7f927b1380,0x7f7f7400a280,12) 8.93ms CNR:OFF Dyn:1 FastMM:1 TID:0  NThr:40 WDiv:HOST:+0.000

Enable graph optimization

Graph optimization by subgraph feature are available in master branch. You can build from source and then use below command to enable this experimental feature for better performance:

export MXNET_SUBGRAPH_BACKEND=MKLDNN

This limitations of this experimental feature are:

  • Use this feature only for inference. When training, be sure to turn the feature off by unsetting the MXNET_SUBGRAPH_BACKEND environment variable.

  • This feature will only run on the CPU, even if you're using a GPU-enabled build of MXNet.

Quantization and Inference with INT8

Benefiting from Intel MKL-DNN, MXNet built with Intel MKL-DNN brings outstanding performance improvement on quantization and inference with INT8 Intel CPU Platform on Intel Xeon Scalable Platform.

Next Steps and Support