remove MKL_EXPERIMENTAL and update make files for MKL-DNN (apache#9810)

* replace MKL2017 references with MKL-DNN

* remove MKLML_ROOT

* MKL_README.md for Full MKL

* update test_mkldnn

* update Jenkinsfile

* update jenkins

* trigger Jenkins with new changes

* trigger Jenkins with new changes

Jenkinsfile

@@ -24,6 +24,7 @@
 mx_lib = 'lib/libmxnet.so, lib/libmxnet.a, dmlc-core/libdmlc.a, nnvm/lib/libnnvm.a'
 // mxnet cmake libraries, in cmake builds we do not produce a libnvvm static library by default.
 mx_cmake_lib = 'build/libmxnet.so, build/libmxnet.a, build/dmlc-core/libdmlc.a, build/tests/mxnet_unit_tests, build/3rdparty/openmp/runtime/src/libomp.so'
+mx_cmake_mkldnn_lib = 'build/libmxnet.so, build/libmxnet.a, build/dmlc-core/libdmlc.a, build/tests/mxnet_unit_tests, build/3rdparty/openmp/runtime/src/libomp.so, build/3rdparty/mkldnn/src/libmkldnn.so, build/3rdparty/mkldnn/src/libmkldnn.so.0'
 mx_mkldnn_lib = 'lib/libmxnet.so, lib/libmxnet.a, lib/libiomp5.so, lib/libmklml_gnu.so, lib/libmkldnn.so, lib/libmkldnn.so.0, lib/libmklml_intel.so, dmlc-core/libdmlc.a, nnvm/lib/libnnvm.a'
 // command to start a docker container
 docker_run = 'tests/ci_build/ci_build.sh'
@@ -260,6 +261,23 @@ try {
         }
       }
     },
+    'GPU: CMake MKLDNN': {
+      node('mxnetlinux-cpu') {
+        ws('workspace/build-cmake-mkldnn-gpu') {
+          init_git()
+          def defines = """            \
+            -DUSE_CUDA=1               \
+            -DUSE_CUDNN=1              \
+            -DUSE_MKLML_MKL=1          \
+            -DUSE_MKLDNN=1             \
+            -DCMAKE_BUILD_TYPE=Release \
+            """
+            def flag = "-v"
+            cmake("build_cuda", defines, flag)
+          pack_lib('cmake_mkldnn_gpu', mx_cmake_mkldnn_lib)
+        }
+      }
+    },
     'GPU: CMake': {
       node('mxnetlinux-cpu') {
         ws('workspace/build-cmake-gpu') {

MKL_README.md

@@ -17,46 +17,3 @@ Installing and enabling the full MKL installation enables MKL support for all op
 
   5. Run 'sudo python setup.py install'
 
-# MKL2017 PLUGIN
-
-MKL2017 is an INTEL released library to accelerate Deep Neural Network (DNN) applications on Intel architecture.
-
-MKL2017_ML is a subset of MKL2017 and only contains DNN acceleration feature, MKL2017 release cycle is longer then MKL2017_ML and MKL2017_ML support latest feature
-
-This README shows the user how to setup and install MKL2017 library with mxnet.
-
-## Build/Install MXNet with MKL:
-
-  1. Enable USE_MKL2017=1 in make/config.mk
-
-    1.1 By default, MKL_2017_EXPRIEMENTAL=0. If setting MKL_2017_EXPRIEMENTAL=1, MKL buffer will be created and transferred between layers to achiever much higher performance.
-
-    1.2 By default, MKLML_ROOT=/usr/local, MKL2017_ML will be used
-
-      1.2.1 when excute make, Makefile will execute "prepare_mkl.sh" to download the MKL2017_ML library under <MKLML_ROOT>
-
-      1.2.2 manually steps for download MKL2017_ML problem
-
-        1.2.2.1 wget https://github.com/dmlc/web-data/raw/master/mxnet/mklml-release/mklml_lnx_<MKL VERSION>.tgz
-
-        1.2.2.2 tar zxvf mklml_lnx_<MKL VERSION>.tgz
-
-        1.2.2.3 cp -rf mklml_lnx_<MKL VERSION>/* <MKLML_ROOT>/
-
-      1.2.3 Set LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$MKLML_ROOT/lib
-
-    1.3 If setting USE_BLAS=mkl
-
-      1.3.1 mshadow can also utilize mkl blas function in mklml package  
-
-    1.4 MKL version compatibility
-
-        1.3.2.1 If you already have MKL installed and MKLROOT being set in your system, by default, it will not attempt to download the latest mklml package unless you unset MKLROOT. 
-
-  2. Run 'make -jX'
-
-  3. Navigate into the python directory
-
-  4. Run 'sudo python setup.py install'
-
-

docker_multiarch/arm.crosscompile.android.mk

@@ -82,21 +82,6 @@ USE_OPENCV = 0
 # use openmp for parallelization
 USE_OPENMP = 1
 
-# MKL ML Library for Intel CPU/Xeon Phi
-# Please refer to MKL_README.md for details
-
-# MKL ML Library folder, need to be root for /usr/local
-# Change to User Home directory for standard user
-# For USE_BLAS!=mkl only
-MKLML_ROOT=/usr/local
-
-# whether use MKL2017 library
-USE_MKL2017 = 0
-
-# whether use MKL2017 experimental feature for high performance
-# Prerequisite USE_MKL2017=1
-USE_MKL2017_EXPERIMENTAL = 0
-
 # whether use NNPACK library
 USE_NNPACK = 0
 
@@ -115,13 +100,10 @@ USE_LAPACK_PATH =
 USE_INTEL_PATH = NONE
 
 # If use MKL only for BLAS, choose static link automatically to allow python wrapper
-ifeq ($(USE_MKL2017), 0)
+USE_STATIC_MKL = NONE
 ifeq ($(USE_BLAS), mkl)
 USE_STATIC_MKL = 1
 endif
-else
-USE_STATIC_MKL = NONE
-endif
 
 #----------------------------
 # distributed computing

docker_multiarch/arm.crosscompile.mk

@@ -82,21 +82,6 @@ USE_OPENCV = 0
 # use openmp for parallelization
 USE_OPENMP = 1
 
-# MKL ML Library for Intel CPU/Xeon Phi
-# Please refer to MKL_README.md for details
-
-# MKL ML Library folder, need to be root for /usr/local
-# Change to User Home directory for standard user
-# For USE_BLAS!=mkl only
-MKLML_ROOT=/usr/local
-
-# whether use MKL2017 library
-USE_MKL2017 = 0
-
-# whether use MKL2017 experimental feature for high performance
-# Prerequisite USE_MKL2017=1
-USE_MKL2017_EXPERIMENTAL = 0
-
 # whether use NNPACK library
 USE_NNPACK = 0
 
@@ -115,13 +100,10 @@ USE_LAPACK_PATH =
 USE_INTEL_PATH = NONE
 
 # If use MKL only for BLAS, choose static link automatically to allow python wrapper
-ifeq ($(USE_MKL2017), 0)
+USE_STATIC_MKL = NONE
 ifeq ($(USE_BLAS), mkl)
 USE_STATIC_MKL = 1
 endif
-else
-USE_STATIC_MKL = NONE
-endif
 
 #----------------------------
 # distributed computing
@@ -176,4 +158,4 @@ USE_CPP_PACKAGE = 0
 # whether to use sframe integration. This requires build sframe
 # git@github.com:dato-code/SFrame.git
 # SFRAME_PATH = $(HOME)/SFrame
-# MXNET_PLUGINS += plugin/sframe/plugin.mk
+# MXNET_PLUGINS += plugin/sframe/plugin.mk

docs/faq/perf.md

@@ -18,10 +18,7 @@ Performance is mainly affected by the following 4 factors:
 ## Intel CPU
 
 For using Intel Xeon CPUs for training and inference, we suggest enabling
-both `USE_MKL2017 = 1` and `USE_MKL2017_EXPERIMENTAL = 1` in
-`config.mk`. Check
-[MKL_README.md](https://github.com/dmlc/mxnet/blob/master/MKL_README.md) for
-details.
+`USE_MKLDNN = 1` in`config.mk`. 
 
 We also find that setting the following two environment variables can help:
 - `export KMP_AFFINITY=granularity=fine,compact,1,0` if there are two physical CPUs

example/image-classification/benchmark_score.py

@@ -70,7 +70,7 @@ def score(network, dev, batch_size, num_batches):
 if __name__ == '__main__':
     networks = ['alexnet', 'vgg-16', 'inception-bn', 'inception-v3', 'resnet-50', 'resnet-152']
     devs = [mx.gpu(0)] if len(get_gpus()) > 0 else []
-    # Enable USE_MKL2017_EXPERIMENTAL for better CPU performance
+    # Enable USE_MKLDNN for better CPU performance
     devs.append(mx.cpu())
 
     batch_sizes = [1, 2, 4, 8, 16, 32]

make/config.mk

@@ -95,20 +95,8 @@ USE_LIBJPEG_TURBO_PATH = NONE
 # use openmp for parallelization
 USE_OPENMP = 1
 
-# MKL ML Library for Intel CPU/Xeon Phi
-# Please refer to MKL_README.md for details
-
-# MKL ML Library folder, need to be root for /usr/local
-# Change to User Home directory for standard user
-# For USE_BLAS!=mkl only
-MKLML_ROOT=/usr/local
-
-# whether use MKL2017 library
-USE_MKL2017 = 0
-
-# whether use MKL2017 experimental feature for high performance
-# Prerequisite USE_MKL2017=1
-USE_MKL2017_EXPERIMENTAL = 0
+# whether use MKL-DNN library
+USE_MKLDNN = 0
 
 # whether use NNPACK library
 USE_NNPACK = 0

make/osx.mk

@@ -88,7 +88,7 @@ USE_BLAS = apple
 USE_LAPACK = 1
 
 # by default, disable lapack when using MKL
-# switch on when there is a full installation of MKL available (not just MKL2017/MKL_ML)
+# switch on when there is a full installation of MKL available (not just MKL_ML)
 ifeq ($(USE_BLAS), mkl)
 USE_LAPACK = 0
 endif

tests/python/cpu/test_mklml.py → tests/python/cpu/test_mkldnn.py

@@ -16,24 +16,24 @@
 # under the License.
 
 """
-MKLML related test cases
+MKL-DNN related test cases
 """
 
 import logging
 import os
 from sys import platform
 
-def test_mklml_install():
+def test_mkldnn_install():
     """
     This test will verify that MXNet is built/installed correctly when 
-    compiled with Intel MKLML library. The method will try to import 
-    the mxnet module and see if the mklml library is mapped to this 
+    compiled with Intel MKL-DNN library. The method will try to import 
+    the mxnet module and see if the mkldnn library is mapped to this 
     process's address space.
     """
     logging.basicConfig(level=logging.INFO)
 
     if not platform.startswith('linux'):
-        logging.info("Bypass mklml install test for non-Linux OS")
+        logging.info("Bypass mkldnn install test for non-Linux OS")
         return
 
     try:
@@ -45,14 +45,14 @@ def test_mklml_install():
 
     pid = os.getpid()
     rc = os.system("cat /proc/" + str(pid) + \
-                       "/maps | grep libmklml_ > /dev/null")
+                       "/maps | grep libmkldnn > /dev/null")
 
     if rc == 0:
-        logging.info("MXNet is built/installed correctly with MKLML")
+        logging.info("MXNet is built/installed correctly with MKL-DNN")
     else:
-        assert 0, "MXNet is built/installed incorrectly with MKLML, please " \
+        assert 0, "MXNet is built/installed incorrectly with MKL-DNN, please " \
                "double check your build/install steps or environment " \
                "variable settings"
 
 if __name__ == '__main__':
-    test_mklml_install()
+    test_mkldnn_install()