1 # How to Cross-Compile ArmNN on x86_64 for arm64
3 * [Introduction](#introduction)
4 * [Cross-compiling ToolChain](#installCCT)
5 * [Build and install Google's Protobuf library](#buildProtobuf)
6 * [Build Caffe for x86_64](#buildCaffe)
7 * [Build Boost library for arm64](#installBaarch)
8 * [Build Compute Library](#buildCL)
9 * [Build ArmNN](#buildANN)
10 * [Run Unit Tests](#unittests)
11 * [Troubleshooting and Errors](#troubleshooting)
14 #### <a name="introduction">Introduction</a>
15 These are the step by step instructions on Cross-Compiling ArmNN under an x86_64 system to target an Arm64 system. This build flow has been tested with Ubuntu 16.04.
16 The instructions show how to build the ArmNN core library and the Boost, Protobuf, Caffe, Tensorflow, Tflite, Flatbuffer and Compute Libraries necessary for compilation.
18 #### <a name="installCCT">Cross-compiling ToolChain</a>
19 * Install the standard cross-compilation libraries for arm64:
21 sudo apt install crossbuild-essential-arm64
24 #### <a name="buildProtobuf">Build and install Google's Protobuf library</a>
26 ## We support protobuf version 3.12.0
27 * Get protobuf from here: https://github.com/protocolbuffers/protobuf :
29 git clone -b v3.12.0 https://github.com/google/protobuf.git protobuf
31 git submodule update --init --recursive
34 * Build a native (x86_64) version of the protobuf libraries and compiler (protoc):
35 (Requires cUrl, autoconf, llibtool, and other build dependencies if not previously installed: sudo apt install curl autoconf libtool build-essential g++)
39 ../configure --prefix=$HOME/armnn-devenv/google/x86_64_pb_install
43 * Build the arm64 version of the protobuf libraries:
47 export CC=aarch64-linux-gnu-gcc \
48 export CXX=aarch64-linux-gnu-g++ \
49 ../configure --host=aarch64-linux \
50 --prefix=$HOME/armnn-devenv/google/arm64_pb_install \
51 --with-protoc=$HOME/armnn-devenv/google/x86_64_pb_install/bin/protoc
56 #### <a name="buildCaffe">Build Caffe for x86_64</a>
57 * Ubuntu 16.04 installation. These steps are taken from the full Caffe installation documentation at: http://caffe.berkeleyvision.org/install_apt.html
58 * Install dependencies:
60 sudo apt-get install libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev
61 sudo apt-get install --no-install-recommends libboost-all-dev
62 sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
63 sudo apt-get install libopenblas-dev
64 sudo apt-get install libatlas-base-dev
66 * Download Caffe from: https://github.com/BVLC/caffe. We have tested using tag 1.0
68 git clone https://github.com/BVLC/caffe.git
70 git checkout eeebdab16155d34ff8f5f42137da7df4d1c7eab0
71 cp Makefile.config.example Makefile.config
73 * Adjust Makefile.config as necessary for your environment, for example:
78 #Add hdf5 and protobuf include and library directories (Replace $HOME with explicit /home/username dir):
79 INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/ $HOME/armnn-devenv/google/x86_64_pb_install/include/
80 LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnu/hdf5/serial/ $HOME/armnn-devenv/google/x86_64_pb_install/lib/
84 export PATH=$HOME/armnn-devenv/google/x86_64_pb_install/bin/:$PATH
85 export LD_LIBRARY_PATH=$HOME/armnn-devenv/google/x86_64_pb_install/lib/:$LD_LIBRARY_PATH
87 * Compilation with Make:
93 These should all run without errors
94 * caffe.pb.h and caffe.pb.cc will be needed when building ArmNN's Caffe Parser
96 #### <a name="installBaarch">Build Boost library for arm64</a>
97 * Build Boost library for arm64
98 Download Boost version 1.64 from http://www.boost.org/doc/libs/1_64_0/more/getting_started/unix-variants.html
99 Using any version of Boost greater than 1.64 will fail to build ArmNN, due to different dependency issues.
101 tar -zxvf boost_1_64_0.tar.gz
103 echo "using gcc : arm : aarch64-linux-gnu-g++ ;" > user_config.jam
104 ./bootstrap.sh --prefix=$HOME/armnn-devenv/boost_arm64_install
105 ./b2 install toolset=gcc-arm link=static cxxflags=-fPIC --with-test --with-log --with-program_options -j32 --user-config=user_config.jam
108 #### <a name="buildCL">Build Compute Library</a>
109 * Building the Arm Compute Library:
111 git clone https://github.com/ARM-software/ComputeLibrary.git
113 git checkout <branch_name>
115 scons arch=arm64-v8a neon=1 opencl=1 embed_kernels=1 extra_cxx_flags="-fPIC" -j8 internal_only=0
118 For example, if you want to checkout release branch of 20.02:
120 git checkout branches/arm_compute_20_02
124 #### <a name="buildtf">Build Tensorflow</a>
125 * Building Tensorflow version 2.3.1:
127 git clone https://github.com/tensorflow/tensorflow.git
129 git checkout fcc4b966f1265f466e82617020af93670141b009
130 ../armnn/scripts/generate_tensorflow_protobuf.sh ../tensorflow-protobuf ../google/x86_64_pb_install
133 #### <a name="buildflatbuffer">Build Flatbuffer</a>
134 * Building Flatbuffer version 1.12.0
136 wget -O flatbuffers-1.12.0.tar.gz https://github.com/google/flatbuffers/archive/v1.12.0.tar.gz
137 tar xf flatbuffers-1.12.0.tar.gz
138 cd flatbuffers-1.12.0
142 cmake .. -DFLATBUFFERS_BUILD_FLATC=1 \
143 -DCMAKE_INSTALL_PREFIX:PATH=$<DIRECTORY_PATH> \
144 -DFLATBUFFERS_BUILD_TESTS=0
148 * Build arm64 version of flatbuffer
152 # Add -fPIC to allow us to use the libraries in shared objects.
153 CXXFLAGS="-fPIC" cmake .. -DCMAKE_C_COMPILER=/usr/bin/aarch64-linux-gnu-gcc \
154 -DCMAKE_CXX_COMPILER=/usr/bin/aarch64-linux-gnu-g++ \
155 -DFLATBUFFERS_BUILD_FLATC=1 \
156 -DCMAKE_INSTALL_PREFIX:PATH=$<DIRECTORY_PATH> \
157 -DFLATBUFFERS_BUILD_TESTS=0
161 #### <a name="buildingONNX">Build Onnx</a>
164 git clone https://github.com/onnx/onnx.git
166 git fetch https://github.com/onnx/onnx.git 553df22c67bee5f0fe6599cff60f1afc6748c635 && git checkout FETCH_HEAD
167 export LD_LIBRARY_PATH=$<DIRECTORY_PATH>/protobuf-host/lib:$LD_LIBRARY_PATH
168 ../google/x86_64_pb_install/bin/protoc onnx/onnx.proto --proto_path=. --proto_path=../google/x86_64_pb_install/include --cpp_out ../onnx
171 #### <a name="buildingtflite">Build TfLite</a>
176 cp ../tensorflow/tensorflow/lite/schema/schema.fbs .
177 ../flatbuffers-1.12.0/build/flatc -c --gen-object-api --reflect-types --reflect-names schema.fbs
180 #### <a name="buildANN">Build ArmNN</a>
181 * Compile ArmNN for arm64:
183 git clone https://github.com/ARM-software/armnn.git
185 git checkout <branch_name>
191 For example, if you want to checkout release branch of 20.02:
193 git checkout branches/armnn_20_02
197 * Use CMake to configure your build environment, update the following script and run it from the armnn/build directory to set up the armNN build:
200 export CXX=aarch64-linux-gnu-g++ \
201 export CC=aarch64-linux-gnu-gcc \
203 -DARMCOMPUTE_ROOT=$HOME/armnn-devenv/ComputeLibrary \
204 -DARMCOMPUTE_BUILD_DIR=$HOME/armnn-devenv/ComputeLibrary/build/ \
205 -DBOOST_ROOT=$HOME/armnn-devenv/boost_arm64_install/ \
206 -DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMNNREF=1 \
207 -DCAFFE_GENERATED_SOURCES=$HOME/armnn-devenv/caffe/build/src \
208 -DBUILD_CAFFE_PARSER=1 \
209 -DONNX_GENERATED_SOURCES=$HOME/onnx \
210 -DBUILD_ONNX_PARSER=1 \
211 -DTF_GENERATED_SOURCES=$HOME/tensorflow-protobuf \
212 -DBUILD_TF_PARSER=1 \
213 -DBUILD_TF_LITE_PARSER=1 \
214 -DTF_LITE_GENERATED_PATH=$HOME/tflite \
215 -DFLATBUFFERS_ROOT=$HOME/flatbuffers-arm64 \
216 -DFLATC_DIR=$HOME/flatbuffers-1.12.0/build \
217 -DPROTOBUF_ROOT=$HOME/google/x86_64_pb_install \
218 -DPROTOBUF_ROOT=$HOME/armnn-devenv/google/x86_64_pb_install/ \
219 -DPROTOBUF_LIBRARY_DEBUG=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0 \
220 -DPROTOBUF_LIBRARY_RELEASE=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0
223 * If you want to include standalone sample dynamic backend tests, add the argument to enable the tests and the dynamic backend path to the CMake command:
225 -DSAMPLE_DYNAMIC_BACKEND=1 \
226 -DDYNAMIC_BACKEND_PATHS=$SAMPLE_DYNAMIC_BACKEND_PATH
233 #### <a name="buildStandaloneBackend">Build Standalone Sample Dynamic Backend</a>
234 * The sample dynamic backend is located in armnn/src/dynamic/sample
240 * Use CMake to configure your build environment, update the following script and run it from the armnn/src/dynamic/sample/build directory to set up the armNN build:
243 export CXX=aarch64-linux-gnu-g++ \
244 export CC=aarch64-linux-gnu-gcc \
246 -DCMAKE_CXX_FLAGS=--std=c++14 \
247 -DBOOST_ROOT=$HOME/armnn-devenv/boost_arm64_install/ \
248 -DBoost_SYSTEM_LIBRARY=$HOME/armnn-devenv/boost_arm64_install/lib/libboost_system.a \
249 -DARMNN_PATH=$HOME/armnn-devenv/armnn/build/libarmnn.so
257 #### <a name="unittests">Run Unit Tests</a>
258 * Copy the build folder to an arm64 linux machine
259 * Copy the libprotobuf.so.15.0.1 library file to the build folder
260 * If you enable the standalone sample dynamic tests, also copy libArm_SampleDynamic_backend.so library file to the folder specified as $SAMPLE_DYNAMIC_BACKEND_PATH when you build ArmNN
261 * cd to the build folder on your arm64 machine and set your LD_LIBRARY_PATH to its current location:
264 export LD_LIBRARY_PATH=`pwd`
266 * Create a symbolic link to libprotobuf.so.23.0.0:
268 ln -s libprotobuf.so.23.0.0 ./libprotobuf.so.23
273 Running 567 test cases...
275 *** No errors detected
277 #### <a name="troubleshooting">Troubleshooting and Errors:</a>
278 #### Error adding symbols: File in wrong format
279 * When building armNN:
281 /usr/local/lib/libboost_log.a: error adding symbols: File in wrong format
282 collect2: error: ld returned 1 exit status
283 CMakeFiles/armnn.dir/build.make:4028: recipe for target 'libarmnn.so' failed
284 make[2]: *** [libarmnn.so] Error 1
285 CMakeFiles/Makefile2:105: recipe for target 'CMakeFiles/armnn.dir/all' failed
286 make[1]: *** [CMakeFiles/armnn.dir/all] Error 2
287 Makefile:127: recipe for target 'all' failed
288 make: *** [all] Error 2
290 * Boost libraries are not compiled for the correct architecture, try recompiling for arm64
292 #### Virtual memory exhausted
293 * When compiling the boost libraries:
295 virtual memory exhausted: Cannot allocate memory
297 * Not enough memory available to compile. Increase the amount of RAM or swap space available.
300 #### Unrecognized command line option '-m64'
301 * When compiling the boost libraries:
303 aarch64-linux-gnu-g++: error: unrecognized command line option ‘-m64’
305 * Clean the boost library directory before trying to build with a different architecture:
309 * It should show the following for arm64:
317 #### Missing libz.so.1
318 * When compiling armNN:
320 /usr/lib/gcc-cross/aarch64-linux-gnu/5/../../../../aarch64-linux-gnu/bin/ld: warning: libz.so.1, needed by /home/<username>/armNN/usr/lib64/libprotobuf.so.23.0.0, not found (try using -rpath or -rpath-link)
323 * Missing arm64 libraries for libz.so.1, these can be added by adding a second architecture to dpkg and explicitly installing them:
325 sudo dpkg --add-architecture arm64
326 sudo apt-get install zlib1g:arm64
330 * If apt-get update returns 404 errors for arm64 repos refer to section 5 below.
331 * Alternatively the missing arm64 version of libz.so.1 can be downloaded and installed from a .deb package here:
332 https://launchpad.net/ubuntu/wily/arm64/zlib1g/1:1.2.8.dfsg-2ubuntu4
334 sudo dpkg -i zlib1g_1.2.8.dfsg-2ubuntu4_arm64.deb
337 #### Unable to install arm64 packages after adding arm64 architecture
338 * Using sudo apt-get update should add all of the required repos for arm64 but if it does not or you are getting 404 errors the following instructions can be used to add the repos manually:
339 * From stackoverflow:
340 https://askubuntu.com/questions/430705/how-to-use-apt-get-to-download-multi-arch-library/430718
341 * Open /etc/apt/sources.list with your preferred text editor.
343 * Mark all the current (default) repos as \[arch=<current_os_arch>], e.g.
345 deb [arch=amd64] http://archive.ubuntu.com/ubuntu/ xenial main restricted
347 * Then add the following:
349 deb [arch=arm64] http://ports.ubuntu.com/ xenial main restricted
350 deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates main restricted
351 deb [arch=arm64] http://ports.ubuntu.com/ xenial universe
352 deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates universe
353 deb [arch=arm64] http://ports.ubuntu.com/ xenial multiverse
354 deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates multiverse
355 deb [arch=arm64] http://ports.ubuntu.com/ xenial-backports main restricted universe multiverse
357 * Update and install again:
359 sudo apt-get install zlib1g:arm64
364 #### Undefined references to google::protobuf:: functions
365 * When compiling armNN there are multiple errors of the following type:
367 libarmnnCaffeParser.so: undefined reference to `google::protobuf:*
369 * Missing or out of date protobuf compilation libraries.
370 Use the command 'protoc --version' to check which version of protobuf is available (version 3.12.0 is required).
371 Follow the instructions above to install protobuf 3.12.0
372 Note this will require you to recompile Caffe for x86_64
375 #### Errors on strict-aliasing rules when compiling the Compute Library
376 * When compiling the Compute Library there are multiple errors on strict-aliasing rules:
378 cc1plus: error: unrecognized command line option ‘-Wno-implicit-fallthrough’ [-Werror]
380 * Add Werror=0 to the scons command:
382 scons arch=arm64-v8a neon=1 opencl=1 embed_kernels=1 extra_cxx_flags="-fPIC" -j8 internal_only=0 Werror=0