FROM nvidia/cuda:10.0-base-ubuntu18.04

LABEL maintainer="Amazon AI"

# prevent stopping by user interaction
ENV DEBIAN_FRONTEND noninteractive
ENV DEBCONF_NONINTERACTIVE_SEEN true
ENV SAGEMAKER_TRAINING_MODULE sagemaker_tensorflow_container.training:main

ENV PYTHONDONTWRITEBYTECODE=1 
ENV PYTHONUNBUFFERED=1 
ENV PYTHONIOENCODING=UTF-8 
ENV LANG=C.UTF-8 
ENV LC_ALL=C.UTF-8

ARG FRAMEWORK_SUPPORT_INSTALLABLE=sagemaker_tensorflow_training.tar.gz
ARG TENSORFLOW_WHL=tensorflow_gpu-2.0.0-cp27-cp27mu-manylinux2010_x86_64.whl
ARG TF_URL=https://tensorflow-aws.s3-us-west-2.amazonaws.com/2.0/AmazonLinux/gpu/final/$TENSORFLOW_WHL

ARG PYTHON=python
ARG PYTHON_PIP=python-pip
ARG PIP=pip

RUN apt-get update && apt-get install -y --no-install-recommends --allow-unauthenticated \
    ca-certificates \
    cuda-command-line-tools-10-0 \
    cuda-cublas-dev-10-0 \
    cuda-cudart-dev-10-0 \
    cuda-cufft-dev-10-0 \
    cuda-curand-dev-10-0 \
    cuda-cusolver-dev-10-0 \
    cuda-cusparse-dev-10-0 \
    curl \
    libcudnn7=7.5.1.10-1+cuda10.0 \
    # TensorFlow doesn't require libnccl anymore but Open MPI still depends on it
    libnccl2=2.4.7-1+cuda10.0 \
    libgomp1 \
    libnccl-dev=2.4.7-1+cuda10.0 \
    libfreetype6-dev \
    libhdf5-serial-dev \
    libpng-dev \
    libzmq3-dev \
    git \
    wget \
    vim \
    build-essential \
    openssh-client \
    openssh-server \
    zlib1g-dev \
    # The 'apt-get install' of nvinfer-runtime-trt-repo-ubuntu1804-5.0.2-ga-cuda10.0
    # adds a new list which contains libnvinfer library, so it needs another
    # 'apt-get update' to retrieve that list before it can actually install the
    # library.
    # We don't install libnvinfer-dev since we don't need to build against TensorRT,
    # and libnvinfer4 doesn't contain libnvinfer.a static library.
 && apt-get update && apt-get install -y --no-install-recommends --allow-unauthenticated  \
    nvinfer-runtime-trt-repo-ubuntu1804-5.0.2-ga-cuda10.0 \
 && apt-get update && apt-get install -y --no-install-recommends --allow-unauthenticated  \
    libnvinfer5=5.0.2-1+cuda10.0 \
 && rm /usr/lib/x86_64-linux-gnu/libnvinfer_plugin* \
 && rm /usr/lib/x86_64-linux-gnu/libnvcaffe_parser* \
 && rm /usr/lib/x86_64-linux-gnu/libnvparsers* \
 && rm -rf /var/lib/apt/lists/* \
 && mkdir -p /var/run/sshd

# Install Open MPI
RUN mkdir /tmp/openmpi \
 && cd /tmp/openmpi \
 && curl -fSsL -O https://download.open-mpi.org/release/open-mpi/v4.0/openmpi-4.0.1.tar.gz \
 && tar zxf openmpi-4.0.1.tar.gz \
 && cd openmpi-4.0.1 \
 && ./configure --enable-orterun-prefix-by-default \
 && make -j $(nproc) all \
 && make install \
 && ldconfig \
 && rm -rf /tmp/openmpi

RUN apt-get update && apt-get install -y \
    ${PYTHON} \
    ${PYTHON_PIP}

# Create a wrapper for OpenMPI to allow running as root by default
RUN mv /usr/local/bin/mpirun /usr/local/bin/mpirun.real \
 && echo '#!/bin/bash' > /usr/local/bin/mpirun \
 && echo 'mpirun.real --allow-run-as-root "$@"' >> /usr/local/bin/mpirun \
 && chmod a+x /usr/local/bin/mpirun

# Configure OpenMPI to run good defaults:
#   --bind-to none --map-by slot --mca btl_tcp_if_exclude lo,docker0
RUN echo "hwloc_base_binding_policy = none" >> /usr/local/etc/openmpi-mca-params.conf \
 && echo "rmaps_base_mapping_policy = slot" >> /usr/local/etc/openmpi-mca-params.conf

# Set default NCCL parameters
RUN echo NCCL_DEBUG=INFO >> /etc/nccl.conf

ENV LD_LIBRARY_PATH=/usr/local/openmpi/lib:$LD_LIBRARY_PATH
ENV PATH /usr/local/openmpi/bin/:$PATH
ENV PATH=/usr/local/nvidia/bin:$PATH

# SSH login fix. Otherwise user is kicked off after login
RUN mkdir -p /var/run/sshd \
 && sed 's@session\s*required\s*pam_loginuid.so@session optional pam_loginuid.so@g' -i /etc/pam.d/sshd

# Create SSH key.
RUN mkdir -p /root/.ssh/ \
 && ssh-keygen -q -t rsa -N '' -f /root/.ssh/id_rsa \
 && cp /root/.ssh/id_rsa.pub /root/.ssh/authorized_keys \
 && printf "Host *\n  StrictHostKeyChecking no\n" >> /root/.ssh/config

WORKDIR /

RUN ${PIP} --no-cache-dir install --upgrade \
    pip \
    setuptools

# Some TF tools expect a "python" binary
RUN ln -s $(which ${PYTHON}) /usr/local/bin/python

COPY $FRAMEWORK_SUPPORT_INSTALLABLE .

# Setup TF Wheel
RUN wget $TF_URL -O /tmp/$TENSORFLOW_WHL

# install PyYAML==5.1.2 to avoid conflict with latest awscli
# # python-dateutil==2.8.0 to satisfy botocore associated with latest awscli
RUN ${PIP} install --no-cache-dir -U \
    numpy==1.16.5 \
    scipy==1.2.2 \
    scikit-learn==0.20.4 \
    pandas==0.24.2 \
    Pillow==6.2.1 \
    h5py==2.10.0 \
    keras_applications==1.0.8 \
    keras_preprocessing==1.1.0 \
    requests==2.22.0 \
    keras==2.3.1 \
    python-dateutil==2.8.0 \
    PyYAML==5.1.2 \
    awscli==1.16.303 \
    mpi4py==3.0.3 \
    "cryptography>=2.3" \
    "sagemaker-tensorflow>=2.0,<2.1" \
    # Let's install TensorFlow separately in the end to avoid
    # the library version to be overwritten
    # ${PIP} install --no-cache-dir -U ${TF_URL} \
 && ${PIP} install --no-cache-dir -U \
    /tmp/$TENSORFLOW_WHL \
 && rm -f /tmp/$TENSORFLOW_WHL \
 && ${PIP} install --no-cache-dir -U \
    $FRAMEWORK_SUPPORT_INSTALLABLE \
 && rm -f $FRAMEWORK_SUPPORT_INSTALLABLE 

# Install Horovod, temporarily using CUDA stubs
RUN ldconfig /usr/local/cuda/targets/x86_64-linux/lib/stubs \
 && HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_WITH_TENSORFLOW=1 ${PIP} install --no-cache-dir horovod==0.18.2 \
 && ldconfig

# Allow OpenSSH to talk to containers without asking for confirmation
RUN cat /etc/ssh/ssh_config | grep -v StrictHostKeyChecking > /etc/ssh/ssh_config.new \
 && echo "    StrictHostKeyChecking no" >> /etc/ssh/ssh_config.new \
 && mv /etc/ssh/ssh_config.new /etc/ssh/ssh_config

COPY dockerd-entrypoint.py /usr/local/bin/dockerd-entrypoint.py
COPY deep_learning_container.py /usr/local/bin/deep_learning_container.py

RUN chmod +x /usr/local/bin/dockerd-entrypoint.py \
 && chmod +x /usr/local/bin/deep_learning_container.py

RUN curl https://aws-dlc-licenses.s3.amazonaws.com/tensorflow-2.0/license.txt -o /license.txt

ENTRYPOINT ["python", "/usr/local/bin/dockerd-entrypoint.py"]
CMD ["bin/bash"]