FROM nvidia/cuda:11.1.1-base-ubuntu18.04

LABEL maintainer="Amazon AI"
LABEL dlc_major_version="1"

ARG PYTHON=python3
ARG PYTHON_VERSION=3.6.13
ARG CUBLAS_VERSION=11.3.0.106
ARG OPEN_MPI_PATH=/opt/amazon/openmpi
ARG EFA_PATH=/opt/amazon/efa

ARG CUDA_HOME=/usr/local/cuda
ARG CONDA_PREFIX=/opt/conda
ARG METIS=metis-5.1.0
ARG RMM_VERSION=0.15.0

# disable prompts during package installation
ARG DEBIAN_FRONTEND=noninteractive

# The smdebug pipeline relies for following format to perform string replace and trigger DLC pipeline for validating
# the nightly builds. Therefore, while updating the smdebug version, please ensure that the format is not disturbed.
ARG SMDEBUG_VERSION=1.0.9

# Python won’t try to write .pyc or .pyo files on the import of source modules
# Force stdin, stdout and stderr to be totally unbuffered. Good for logging
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
ENV LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
ENV LD_LIBRARY_PATH="/opt/conda/lib:${LD_LIBRARY_PATH}"
ENV PYTHONIOENCODING=UTF-8
ENV LANG=C.UTF-8
ENV LC_ALL=C.UTF-8
ENV PATH /opt/conda/bin:$PATH
ENV TORCH_CUDA_ARCH_LIST="3.7 5.0 7.0+PTX 8.0"
ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all"
ENV CUDNN_VERSION=8.0.5.39
ENV NCCL_VERSION=2.7.8
ENV HOROVOD_VERSION=0.21.3
ENV EFA_VERSION=1.11.2
ENV OMPI_VERSION=4.1.1
ENV BRANCH_OFI=1.1.1
ENV DGLBACKEND=pytorch
ENV CMAKE_PREFIX_PATH="$(dirname $(which conda))/../"
ENV SAGEMAKER_TRAINING_MODULE=sagemaker_pytorch_container.training:main
ENV MANUAL_BUILD=0
ENV RDMAV_FORK_SAFE=1

ARG PT_TRAINING_URL=https://aws-pytorch-binaries.s3-us-west-2.amazonaws.com/r1.8.1_aws/20210325-012734/e1343088f0beb99438343e1e99e8d71ffb972b47/gpu/torch-1.8.1-cp36-cp36m-manylinux1_x86_64.whl
ARG PT_TORCHVISION_URL=https://torchvision-build.s3-us-west-2.amazonaws.com/1.8.1/gpu/torchvision-0.9.1-cp36-cp36m-linux_x86_64.whl
ARG SMD_MODEL_PARALLEL_URL=https://sagemaker-distributed-model-parallel.s3.us-west-2.amazonaws.com/pytorch-1.8.1/build-artifacts/2021-12-14-00-46/smdistributed_modelparallel-1.6.0-cp36-cp36m-linux_x86_64.whl
ARG SMDATAPARALLEL_BINARY=https://smdataparallel.s3.amazonaws.com/binary/pytorch/1.8.1/cu111/2021-12-13/smdistributed_dataparallel-1.2.3-cp36-cp36m-linux_x86_64.whl
ARG PT_S3_WHL_GPU=https://aws-s3-plugin.s3-us-west-2.amazonaws.com/binaries/0.0.1/93fdaed/awsio-0.0.1-cp36-cp36m-manylinux1_x86_64.whl

RUN apt-get update \
 && apt-get install -y --allow-change-held-packages --no-install-recommends \
    build-essential \
    ca-certificates \
    cmake \
    cuda-command-line-tools-11-1 \
    cuda-cudart-11-1 \
    cuda-libraries-11-1 \
    curl \
    emacs \
    git \
    jq \
    libcublas-11-1=${CUBLAS_VERSION}-1 \
    libcublas-dev-11-1=${CUBLAS_VERSION}-1 \
    libcudnn8=$CUDNN_VERSION-1+cuda11.1 \
    libcufft-dev-11-1 \
    libcurand-dev-11-1 \
    libcusolver-dev-11-1 \
    libcusparse-dev-11-1 \
    libglib2.0-0 \
    libgl1-mesa-glx \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    libibverbs-dev \
    libhwloc-dev \
    libnuma1 \
    libnuma-dev \
    libssl1.1 \
    libtool \
    hwloc \
    openssl \
    python3-dev \
    vim \
    wget \
    unzip \
    zlib1g-dev \
    jq \
    && apt-get install -y -qq libkrb5-dev \
    && apt-get install -y -qq libsasl2-dev libsasl2-modules \
    && apt-get install -y -qq krb5-user \
 && rm -rf /var/lib/apt/lists/*

RUN cd /tmp \
  && git clone https://github.com/NVIDIA/nccl.git -b v${NCCL_VERSION}-1 \
  && cd nccl \
  && make -j64 src.build BUILDDIR=/usr/local \
  && rm -rf /tmp/nccl

# Install EFA along without AWS OPEN_MPI
RUN mkdir /tmp/efa \
  && cd /tmp/efa \
  && curl -O https://s3-us-west-2.amazonaws.com/aws-efa-installer/aws-efa-installer-${EFA_VERSION}.tar.gz \
  && tar -xf aws-efa-installer-${EFA_VERSION}.tar.gz \
  && cd aws-efa-installer \
  && ./efa_installer.sh -y --skip-kmod -g \
  && rm -rf $OPEN_MPI_PATH \
  && rm -rf /tmp/efa \
  && rm -rf /tmp/aws-efa-installer-${EFA_VERSION}.tar.gz

# Install OpenMPI without libfabric support
RUN mkdir /tmp/openmpi && \
  cd /tmp/openmpi && \
  wget --quiet https://download.open-mpi.org/release/open-mpi/v4.1/openmpi-${OMPI_VERSION}.tar.gz && \
  tar zxf openmpi-${OMPI_VERSION}.tar.gz && \
  cd openmpi-${OMPI_VERSION} && \
  ./configure --enable-orterun-prefix-by-default --prefix=$OPEN_MPI_PATH && \
  make -j $(nproc) all && \
  make install && \
  ldconfig && \
  cd / && \
  rm -rf /tmp/openmpi

ENV PATH="$OPEN_MPI_PATH/bin:$PATH"
ENV LD_LIBRARY_PATH=$OPEN_MPI_PATH/lib/:$EFA_PATH/lib/:$LD_LIBRARY_PATH

# py37 is the oldest python version supported by Miniconda 4.10.3, py36 is installed below and will override py37 environment
RUN ompi_info --parsable --all | grep mpi_built_with_cuda_support:value \
 && curl -L -o ~/miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py37_4.10.3-Linux-x86_64.sh \
 && chmod +x ~/miniconda.sh \
 && ~/miniconda.sh -b -p ${CONDA_PREFIX} \
 && rm ~/miniconda.sh \
 && ${CONDA_PREFIX}/bin/conda install -c conda-forge \
    python=$PYTHON_VERSION \
 && ${CONDA_PREFIX}/bin/conda install -y \
    # conda 4.10.0 requires ruamel_yaml to be installed. Currently pinned at latest.
    ruamel_yaml==0.15.100 \
 && ${CONDA_PREFIX}/bin/conda install -y -c anaconda \
    numpy \
    ipython \
    mkl \
    mkl-include \
    cython \
    typing \
    future \
    "pyopenssl>=17.5.0" \
 && conda install -y -c dglteam dgl-cuda11.1==0.6.1 \
 && ${CONDA_PREFIX}/bin/conda clean -ya

RUN ${CONDA_PREFIX}/bin/conda config --set ssl_verify False \
 && pip install --upgrade pip --trusted-host pypi.org --trusted-host files.pythonhosted.org \
 && ln -s ${CONDA_PREFIX}/bin/pip /usr/local/bin/pip3

RUN conda install -c pytorch magma-cuda111==2.5.2 \
 && conda install -c conda-forge \
    opencv \
 && conda install -y scikit-learn \
    pandas \
    h5py \
    requests \
    libgcc \
 && conda clean -ya

# Install libboost from source. This package is needed for smdataparallel functionality [for networking asynchronous IO].
RUN wget https://sourceforge.net/projects/boost/files/boost/1.73.0/boost_1_73_0.tar.gz/download -O boost_1_73_0.tar.gz \
  && tar -xzf boost_1_73_0.tar.gz \
  && cd boost_1_73_0 \
  && ./bootstrap.sh \
  && ./b2 threading=multi --prefix=${CONDA_PREFIX} -j 64 cxxflags=-fPIC cflags=-fPIC install || true \
  && cd .. \
  && rm -rf boost_1_73_0.tar.gz \
  && rm -rf boost_1_73_0 \
  && cd ${CONDA_PREFIX}/include/boost

WORKDIR /opt/pytorch

# Copy workaround script for incorrect hostname
COPY changehostname.c /
COPY start_with_right_hostname.sh /usr/local/bin/start_with_right_hostname.sh

WORKDIR /root

# Uninstall torch and torchvision before installing the custom versions from an S3 bucket
RUN pip install --no-cache-dir -U \
    smdebug==${SMDEBUG_VERSION} \
    smclarify \
    "sagemaker>=2,<3" \
    sagemaker-experiments==0.* \
    # Pin SM Training toolkit as the latest version (4.0.0) dropped py36 support
    "sagemaker-training<4" \
    sagemaker-pytorch-training \
    --no-cache-dir fastai==1.0.61 \
    "pyyaml>=5.4,<5.5" \
    "awscli<2" \
    psutil \
    "pillow>=8.2.2,<8.4" \
    scipy \
    pybind11 \
    click \
    mpi4py==3.0.3 \
    cmake==3.18.2.post1 \
    torchnet \
    "cryptography>3.2" \
 && pip uninstall -y torch \
 && pip install --no-cache-dir -U ${PT_TRAINING_URL} \
 && pip uninstall -y torchvision \
 && pip install --no-deps --no-cache-dir -U ${PT_TORCHVISION_URL}

# Install extra packages
RUN pip install --no-cache-dir -U \
    "bokeh>=2.3,<3" \
    "imageio>=2.9,<3" \
    "opencv-python>=4.3,<5" \
    "plotly>=5.1,<6" \
    "seaborn>=0.11,<1" \
    "shap>=0.39,<1" \
    "boto3>1.0,<2.0" \
    "sasl<1" \
    "thrift_sasl<1" \
    "PyHive<1" \
    "sparkmagic<1" \
    "sagemaker-studio-sparkmagic-lib<1" \
    "sagemaker-studio-analytics-extension<1"

# Remove python kernel installed by sparkmagic
RUN /opt/conda/bin/jupyter-kernelspec remove -fy python3

# install metis
RUN wget -nv http://glaros.dtc.umn.edu/gkhome/fetch/sw/metis/${METIS}.tar.gz \
  && gunzip -f ${METIS}.tar.gz \
  && tar -xvf ${METIS}.tar \
  && cd ${METIS} \
  && apt-get update \
  && apt-get install -y build-essential \
  && apt-get install -y cmake \
  && make config shared=1 \
  && make install \
  && cd .. \
  && rm -rf ${METIS}.tar* \
  && rm -rf ${METIS} \
  && rm -rf /var/lib/apt/lists/* \
  && apt-get clean

# Install RAPIDSMemoryManager.
# Requires cmake>=3.14.
RUN  wget -nv https://github.com/rapidsai/rmm/archive/v${RMM_VERSION}.tar.gz \
  && tar -xvf v${RMM_VERSION}.tar.gz \
  && cd rmm-${RMM_VERSION} \
  && INSTALL_PREFIX=/usr/local ./build.sh librmm \
  && cd .. \
  && rm -rf v${RMM_VERSION}.tar* \
  && rm -rf rmm-${RMM_VERSION}

# Install Nvidia Apex
RUN git clone https://github.com/NVIDIA/apex.git \
 && cd apex \
 && pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

# Configure Open MPI and configure NCCL parameters
RUN mv $OPEN_MPI_PATH/bin/mpirun $OPEN_MPI_PATH/bin/mpirun.real \
 && echo '#!/bin/bash' > $OPEN_MPI_PATH/bin/mpirun \
 && echo 'mpirun.real --allow-run-as-root "$@"' >> $OPEN_MPI_PATH/bin/mpirun \
 && chmod a+x $OPEN_MPI_PATH/bin/mpirun \
 && echo "hwloc_base_binding_policy = none" >> $OPEN_MPI_PATH/etc/openmpi-mca-params.conf \
 && echo "rmaps_base_mapping_policy = slot" >> $OPEN_MPI_PATH/etc/openmpi-mca-params.conf \
 && echo NCCL_DEBUG=INFO >> /etc/nccl.conf \
 && echo NCCL_SOCKET_IFNAME=^docker0 >> /etc/nccl.conf

# Install AWS OFI NCCL plug-in
RUN apt-get update && apt-get install -y autoconf
RUN mkdir /tmp/efa-ofi-nccl \
  && cd /tmp/efa-ofi-nccl \
  && git clone https://github.com/aws/aws-ofi-nccl.git -b v${BRANCH_OFI} \
  && cd aws-ofi-nccl \
  && ./autogen.sh \
  && ./configure --with-libfabric=/opt/amazon/efa \
  --with-mpi=/opt/amazon/openmpi \
  --with-cuda=/usr/local/cuda \
  --with-nccl=/usr/local --prefix=/usr/local \
  && make \
  && make install \
  && rm -rf /tmp/efa-ofi-nccl

# Install OpenSSH for MPI to communicate between containers, allow OpenSSH to talk to containers without asking for confirmation
RUN apt-get update \
 && apt-get install -y  --allow-downgrades --allow-change-held-packages --no-install-recommends \
 && apt-get install -y --no-install-recommends openssh-client openssh-server \
 && mkdir -p /var/run/sshd \
 && 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 \
 && rm -rf /var/lib/apt/lists/*

# Configure OpenSSH so that nodes can communicate with each other
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

RUN rm -rf /root/.ssh/ && \
 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

# Install Horovod
RUN pip uninstall -y horovod \
 && ldconfig /usr/local/cuda-11.1/targets/x86_64-linux/lib/stubs \
 && HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_CUDA_HOME=/usr/local/cuda-11.1 HOROVOD_WITH_PYTORCH=1 pip install --no-cache-dir horovod==${HOROVOD_VERSION} \
 && ldconfig

# Install SM Distributed DataParallel binary
RUN SMDATAPARALLEL_PT=1 pip install --no-cache-dir ${SMDATAPARALLEL_BINARY}

# Install SM Distributed Modelparallel binary
RUN pip install --no-cache-dir -U ${SMD_MODEL_PARALLEL_URL}

ENV LD_LIBRARY_PATH="/opt/conda/lib/python3.6/site-packages/smdistributed/dataparallel/lib:$LD_LIBRARY_PATH"

# Install PT S3 plugin
RUN pip install --no-cache-dir -U ${PT_S3_WHL_GPU}
RUN mkdir -p /etc/pki/tls/certs && cp /etc/ssl/certs/ca-certificates.crt /etc/pki/tls/certs/ca-bundle.crt

WORKDIR /

COPY deep_learning_container.py /usr/local/bin/deep_learning_container.py

RUN chmod +x /usr/local/bin/start_with_right_hostname.sh \
 && chmod +x /usr/local/bin/deep_learning_container.py

RUN HOME_DIR=/root \
 && curl -o ${HOME_DIR}/oss_compliance.zip https://aws-dlinfra-utilities.s3.amazonaws.com/oss_compliance.zip \
 && unzip ${HOME_DIR}/oss_compliance.zip -d ${HOME_DIR}/ \
 && cp ${HOME_DIR}/oss_compliance/test/testOSSCompliance /usr/local/bin/testOSSCompliance \
 && chmod +x /usr/local/bin/testOSSCompliance \
 && chmod +x ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh \
 && ${HOME_DIR}/oss_compliance/generate_oss_compliance.sh ${HOME_DIR} ${PYTHON} \
 && rm -rf ${HOME_DIR}/oss_compliance*


RUN curl -o /license.txt https://aws-dlc-licenses.s3.amazonaws.com/pytorch-1.8/license.txt

# Starts framework
ENTRYPOINT ["bash", "-m", "start_with_right_hostname.sh"]
CMD ["/bin/bash"]