dockerfile.gpu.test

# This file is used for the testing under docker environment.
# The bluefog folder is binded in the docker storage system so that
# a local modification can be reflected in the docker container as well.
FROM nvidia/cuda:10.1-devel-ubuntu18.04

# TensorFlow version is tightly coupled to CUDA and cuDNN so it should be selected carefully
ENV TENSORFLOW_VERSION=2.1.0
ENV PYTORCH_VERSION=1.4.0
ENV TORCHVISION_VERSION=0.5.0
ENV CUDNN_VERSION=7.6.0.64-1+cuda10.1
ENV NCCL_VERSION=2.7.8-1+cuda10.1

ARG python=3.7
ENV PYTHON_VERSION=${python}
ENV PYTORCH_CUDA=10.1

# Set default shell to /bin/bash
SHELL ["/bin/bash", "-cu"]

RUN apt-get update && apt-get install -y --allow-downgrades --allow-change-held-packages --no-install-recommends \
        build-essential \
        cmake \
        g++-4.8 \
        git \
        curl \
        vim \
        wget \
        ca-certificates \
        libcudnn7=${CUDNN_VERSION} \
        libnccl2=${NCCL_VERSION} \
        libnccl-dev=${NCCL_VERSION} \
        libjpeg-dev \
        libpng-dev \
        python${PYTHON_VERSION} \
        python${PYTHON_VERSION}-dev \
        librdmacm1 \
        libibverbs1 \
        ibverbs-providers

RUN if [[ "${PYTHON_VERSION}" == "3.7" ]]; then \
        apt-get install -y python${PYTHON_VERSION}-distutils; \
    fi
RUN ln -s /usr/bin/python${PYTHON_VERSION} /usr/bin/python

RUN curl -O https://bootstrap.pypa.io/get-pip.py && \
    python get-pip.py && \
    rm get-pip.py

# Install TensorFlow, Keras, PyTorch and MXNet
RUN pip install future typing pytest
RUN pip install numpy \
        tensorflow-gpu==${TENSORFLOW_VERSION} \
        keras \
        h5py

RUN pip install torch==${PYTORCH_VERSION} torchvision==${TORCHVISION_VERSION} -f https://download.pytorch.org/whl/cu${PYTORCH_CUDA}/torch_stable.html;
# Pin Pillow<7.0: https://github.com/pytorch/vision/issues/1718
RUN pip install "Pillow<7.0" --no-deps

# Install Open MPI
RUN mkdir /tmp/openmpi && \
    cd /tmp/openmpi && \
    wget https://www.open-mpi.org/software/ompi/v4.0/downloads/openmpi-4.0.2.tar.gz && \
    tar zxf openmpi-4.0.2.tar.gz && \
    cd openmpi-4.0.2 && \
    ./configure --enable-orterun-prefix-by-default --with-cuda && \
    make -j $(nproc) all && \
    make install && \
    ldconfig && \
    rm -rf /tmp/openmpi

# 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 HOROVOD_WITH_PYTORCH=1 HOROVOD_WITHOUT_MXNET=1 \
         pip install --no-cache-dir horovod==0.19.0 && \
    ldconfig

# Install OpenSSH for MPI to communicate between containers
RUN apt-get install -y --no-install-recommends openssh-client openssh-server && \
    mkdir -p /var/run/sshd

# 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