TensorFlow Installation Log

install-tensorflow.sh

# Note – this is not a bash script (some of the steps require reboot)
# I named it .sh just so Github does correct syntax highlighting.
#
# This is also available as an AMI in us-east-1 (virginia): ami-cf5028a5
#
# The CUDA part is mostly based on this excellent blog post:
# http://tleyden.github.io/blog/2014/10/25/cuda-6-dot-5-on-aws-gpu-instance-running-ubuntu-14-dot-04/

# Install various packages
sudo apt-get update
sudo apt-get upgrade -y # choose “install package maintainers version”
sudo apt-get install -y build-essential python-pip python-dev git python-numpy swig python-dev default-jdk zip zlib1g-dev

export LC_ALL="en_US.UTF-8"
export LC_CTYPE="en_US.UTF-8"
sudo dpkg-reconfigure locales

pip install --upgrade pip

# Blacklist Noveau which has some kind of conflict with the nvidia driver
echo -e "blacklist nouveau\nblacklist lbm-nouveau\noptions nouveau modeset=0\nalias nouveau off\nalias lbm-nouveau off\n" | sudo tee /etc/modprobe.d/blacklist-nouveau.conf
echo options nouveau modeset=0 | sudo tee -a /etc/modprobe.d/nouveau-kms.conf
sudo update-initramfs -u
sudo reboot # Reboot (annoying you have to do this in 2015!)

# Some other annoying thing we have to do
sudo apt-get install -y linux-image-extra-virtual
sudo reboot # Not sure why this is needed

# Install latest Linux headers
sudo apt-get install -y linux-source linux-headers-`uname -r` 

please install the `pkg-config` utility and the X.Org   
           SDK/development package

# Install CUDA 8.0
wget https://developer.nvidia.com/compute/cuda/8.0/prod/local_installers/cuda_8.0.44_linux-run
chmod +x cuda_8.0.44_linux-run
./cuda_8.0.44_linux-run -extract=`pwd`/nvidia_installers
cd nvidia_installers
sudo ./NVIDIA-Linux-x86_64-367.48.run
sudo modprobe nvidia
sudo ./cuda-linux64-rel-8.0.44-21122537.run
sudo ./cuda-samples-linux-8.0.44-21122537.run

# cd /usr/local 에서 확인

# ADD follwing lines at /.bashrc
```
# CUDA Toolkit
export CUDA_HOME=/usr/local/cuda-8.0
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
export PATH=${CUDA_HOME}/bin:${PATH}
```
source /.bashrc

# Install CUDNN 5.1 for CUDA 8.0
# YOU NEED TO SCP THIS ONE FROM SOMEWHERE ELSE – it's not available online.
# You need to register and get approved to get a download link. Very annoying.

# download cudnn 5.1 for cuda 8.0 at https://developer.nvidia.com/rdp/cudnn-download 
# 외부에서 
scp -i tokyo_test.pem cudnn-8.0-linux-x64-v5.1.tgz ubuntu@52.69.80.9:~

cd ~
tar -xzf cudnn-8.0-linux-x64-v5.1.tgz
cd cuda
sudo cp lib64/* /usr/local/cuda/lib64/
sudo cp include/* /usr/local/cuda/include/

## Cleanup
cd ~
rm -rf cuda installers
rm -f cuda_7.5.18_linux.run cudnn-7.5-linux-x64-v5.0-ga.tgz

# At this point the root mount is getting a bit full
# I had a lot of issues where the disk would fill up and then Bazel would end up in this weird state complaining about random things
# Make sure you don't run out of disk space when building Tensorflow!
sudo mkdir /mnt/tmp
sudo chmod 777 /mnt/tmp
sudo rm -rf /tmp
sudo ln -s /mnt/tmp /tmp
# Note that /mnt is not saved when building an AMI, so don't put anything crucial on it

# Install Bazel
cd /mnt/tmp
git clone https://github.com/bazelbuild/bazel.git
cd bazel
./compile.sh
sudo cp output/bazel /usr/bin

# Install TensorFlow
cd /mnt/tmp
export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64"
export CUDA_HOME=/usr/local/cuda
git clone --recurse-submodules https://github.com/tensorflow/tensorflow
cd tensorflow
# Patch to support older K520 devices on AWS
# wget "https://gist.githubusercontent.com/infojunkie/cb6d1a4e8bf674c6e38e/raw/5e01e5b2b1f7afd3def83810f8373fbcf6e47e02/cuda_30.patch"
# git apply cuda_30.patch
# According to https://github.com/tensorflow/tensorflow/issues/25#issuecomment-156234658 this patch is no longer needed
# Instead, you need to run ./configure like below (not tested yet)
TF_UNOFFICIAL_SETTING=1 ./configure
bazel build -c opt --config=cuda //tensorflow/cc:tutorials_example_trainer

# Build Python package
bazel build -c opt --config=cuda //tensorflow/tools/pip_package:build_pip_package
bazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/tensorflow_pkg

export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.11.0rc2-cp27-none-linux_x86_64.whl
sudo pip install --upgrade $TF_BINARY_URL

#sudo pip install /tmp/tensorflow_pkg/tensorflow-0.11.0-cp27-none-linux_x86_64.whl


# Test it!
cd ~
git clone https://gist.github.com/j-min/baae1aa56e861cab9831b3722755ae6d
python baae1aa56e861cab9831b3722755ae6d/test_gpu.py

# On a g2.2xlarge: step 100, loss = 4.50 (325.2 examples/sec; 0.394 sec/batch)
# On a g2.8xlarge: step 100, loss = 4.49 (337.9 examples/sec; 0.379 sec/batch)
# doesn't seem like it is able to use the 4 GPU cards unfortunately :(