FROM nvidia/cuda:11.2.2-base-ubuntu20.04 AS base_image

ENV DEBIAN_FRONTEND=noninteractive \
    LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:/usr/local/lib"

RUN apt-get update \
 && apt-get upgrade -y \
 && apt-get autoremove -y \
 && apt-get clean \
 && rm -rf /var/lib/apt/lists/*

FROM base_image AS common

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

# TensorFlow major.minor version
ENV TF_VERSION=2.10

# prevent stopping by user interaction
ENV DEBIAN_FRONTEND noninteractive
ENV DEBCONF_NONINTERACTIVE_SEEN true

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

# Set environment variables for MKL
# For more about MKL with TensorFlow see:
# https://www.tensorflow.org/performance/performance_guide#tensorflow_with_intel%C2%AE_mkl_dnn
ENV KMP_AFFINITY=granularity=fine,compact,1,0
ENV KMP_BLOCKTIME=1
ENV KMP_SETTINGS=0
ENV RDMAV_FORK_SAFE=1

ARG PYTHON=python3.9
ARG PIP=pip3
ARG PYTHON_VERSION=3.9.16

ARG OPEN_MPI_PATH=/opt/amazon/openmpi
ARG EFA_PATH=/opt/amazon/efa
ARG EFA_VERSION=1.17.2
ARG OMPI_VERSION=4.1.1
ARG BRANCH_OFI=1.4.0-aws

ARG CUDA=11.2
ARG CUDA_DASH=11-2
ARG CUDNN=8.2.4.15-1

ARG NCCL_VERSION=2.12.10

# To be passed to ec2 and sagemaker stages
ENV PYTHON=${PYTHON}
ENV PYTHON_VERSION=${PYTHON_VERSION}
ENV PIP=${PIP}

RUN apt-get update && apt-get install -y --no-install-recommends --allow-unauthenticated --allow-downgrades  --allow-change-held-packages \
   ca-certificates \
   cuda-command-line-tools-${CUDA_DASH} \
   cuda-cudart-dev-${CUDA_DASH} \
   libcufft-dev-${CUDA_DASH} \
   libcurand-dev-${CUDA_DASH} \
   libcusolver-dev-${CUDA_DASH} \
   libcusparse-dev-${CUDA_DASH} \
   curl \
   emacs \
   libcudnn8=${CUDNN}+cuda11.4 \
   libgomp1 \
   libfreetype6-dev \
   libhdf5-serial-dev \
   liblzma-dev \
   libpng-dev \
   libtemplate-perl \
   libzmq3-dev \
   hwloc \
   git \
   unzip \
   wget \
   libtool \
   vim \
   libssl1.1 \
   openssl \
   build-essential \
   openssh-client \
   openssh-server \
   zlib1g-dev \
   # Install dependent library for OpenCV
   libgtk2.0-dev \
   jq \
 && apt-get update \
 && apt-get install -y --no-install-recommends --allow-unauthenticated --allow-change-held-packages \
   libcublas-dev-${CUDA_DASH} \
   libcublas-${CUDA_DASH} \
   # 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.
   # nvinfer-runtime-trt-repo doesn't have a 1804-cuda10.1 version yet. see:
   # https://developer.download.nvidia.cn/compute/machine-learning/repos/ubuntu1804/x86_64/
 && rm -rf /var/lib/apt/lists/* \
 && mkdir -p /var/run/sshd

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 without AWS OPEN_MPI
RUN apt-get update \
  && 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 \
  && rm -rf /var/lib/apt/lists/*

# 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

###########################################################################
# Horovod & its dependencies
###########################################################################

# Create a wrapper for OpenMPI to allow running as root by default
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

# 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" >> $OPEN_MPI_PATH/etc/openmpi-mca-params.conf \
 && echo "rmaps_base_mapping_policy = slot" >> $OPEN_MPI_PATH/etc/openmpi-mca-params.conf

# Set default NCCL parameters
RUN echo NCCL_DEBUG=INFO >> /etc/nccl.conf
ENV LD_LIBRARY_PATH=$OPEN_MPI_PATH/lib/:$EFA_PATH/lib/:$LD_LIBRARY_PATH
# /usr/local/lib/libpython* needs to be accessible for dynamic linking
ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
ENV PATH=$OPEN_MPI_PATH/bin/:$PATH
ENV PATH=$OPEN_MPI_PATH/nvidia/bin:$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 apt-get update \
   && apt-get install -y --no-install-recommends \
   libbz2-dev \
   libc6-dev \
   libffi-dev \
   libgdbm-dev \
   libncursesw5-dev \
   libreadline-gplv2-dev \
   libsqlite3-dev \
   libssl-dev \
   tk-dev \
   ffmpeg \
   libsm6 \
   libxext6 \
   # remove libsasl2-2 after Nvidia docker upstream fix CVE-2022-24407
   && rm -rf /var/lib/apt/lists/* \
   && apt-get clean

RUN wget https://www.python.org/ftp/python/$PYTHON_VERSION/Python-$PYTHON_VERSION.tgz \
   && tar -xvf Python-$PYTHON_VERSION.tgz \
   && cd Python-$PYTHON_VERSION \
   && ./configure --enable-shared \
   && make -j $(nproc) \
   && make install \
   && rm -rf ../Python-$PYTHON_VERSION* \
   # Starting from Python39, a xxx.pem file will be generated under /tmp folder during installation. Remove it to complete cleanup after installation from python source.
   && rm /tmp/*.pem

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 \
   && ln -s $(which ${PIP}) /usr/bin/pip

RUN apt-get update && apt-get -y install  protobuf-compiler

# 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 \
   pybind11 \
   cmake==3.18.2.post1 \
   scipy==1.8.0 \
   "Pillow>=9.0.0<9.1.0" \
   python-dateutil==2.8.1 \
   "pyYAML>=5.4,<5.5" \
   requests==2.27.1 \
   "awscli<2" \
   mpi4py==3.1.3 \
   h5py==3.6.0 \
   "absl-py>=0.9,<0.11" \
   "opencv-python>=4.3,<5" \
   "werkzeug>=2.0.2,<3" \
   "urllib3>1.26.0<1.27.0" \
   "protobuf>=3.20.2,<3.21"

# 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 -j $(nproc) \
  && make install \
  && rm -rf /tmp/efa-ofi-nccl

# Upgrade libsasl2-2 for fixing cyrus-sasl2 related CVE
RUN apt-get install -y --only-upgrade libsasl2-2

# Upgrade libsasl2-2 for fixing cyrus-sasl2 related CVE
RUN apt-get install -y --only-upgrade libsasl2-2

# 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

# Add NGC vars
ENV TF_AUTOTUNE_THRESHOLD=2

ADD https://raw.githubusercontent.com/aws/deep-learning-containers/master/src/deep_learning_container.py /usr/local/bin/deep_learning_container.py

RUN chmod +x /usr/local/bin/deep_learning_container.py

RUN curl https://aws-dlc-licenses.s3.amazonaws.com/tensorflow-${TF_VERSION}/license.txt -o /license.txt

########################################################
#  _____ ____ ____    ___
# | ____/ ___|___ \  |_ _|_ __ ___   __ _  __ _  ___
# |  _|| |     __) |  | || '_ ` _ \ / _` |/ _` |/ _ \
# | |__| |___ / __/   | || | | | | | (_| | (_| |  __/
# |_____\____|_____| |___|_| |_| |_|\__,_|\__, |\___|
#                                         |___/
#  ____           _
# |  _ \ ___  ___(_)_ __   ___
# | |_) / _ \/ __| | '_ \ / _ \
# |  _ <  __/ (__| | |_) |  __/
# |_| \_\___|\___|_| .__/ \___|
#                  |_|
########################################################

FROM common AS ec2

ARG TF_URL=https://framework-binaries.s3.us-west-2.amazonaws.com/tensorflow/r2.10_aws/gpu/2022-12-01-00-50/tensorflow_gpu-2.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

RUN ${PIP} install --no-cache-dir -U \
   ${TF_URL} \
   tensorflow-io==0.24.0 \
   tensorflow-datasets==4.5.2

# Install Horovod, temporarily using CUDA stubs
RUN ldconfig /usr/local/cuda-11.2/targets/x86_64-linux/lib/stubs \
 && HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_WITH_TENSORFLOW=1 ${PIP} install --no-cache-dir horovod==0.25.0 \
 && ldconfig

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*

# remove tmp files
RUN rm -rf /tmp/*

CMD ["/bin/bash"]

#################################################################
#  ____                   __  __       _
# / ___|  __ _  __ _  ___|  \/  | __ _| | _____ _ __
# \___ \ / _` |/ _` |/ _ \ |\/| |/ _` | |/ / _ \ '__|
#  ___) | (_| | (_| |  __/ |  | | (_| |   <  __/ |
# |____/ \__,_|\__, |\___|_|  |_|\__,_|_|\_\___|_|
#              |___/
#  ___                              ____           _
# |_ _|_ __ ___   __ _  __ _  ___  |  _ \ ___  ___(_)_ __   ___
#  | || '_ ` _ \ / _` |/ _` |/ _ \ | |_) / _ \/ __| | '_ \ / _ \
#  | || | | | | | (_| | (_| |  __/ |  _ <  __/ (__| | |_) |  __/
# |___|_| |_| |_|\__,_|\__, |\___| |_| \_\___|\___|_| .__/ \___|
#                      |___/                        |_|
#################################################################

FROM common AS sagemaker

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

ARG TF_URL=https://framework-binaries.s3.us-west-2.amazonaws.com/tensorflow/r2.10_aws/gpu/2022-12-01-00-50/tensorflow_gpu-2.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

# sagemaker-specific environment variable
ENV SAGEMAKER_TRAINING_MODULE sagemaker_tensorflow_container.training:main

# https://github.com/tensorflow/models/issues/9267
# tf-models does not respect existing installations of TF and always installs open source TF
RUN ${PIP} install --no-cache-dir -U \
    tf-models-official==2.10.0

RUN ${PIP} install --no-cache-dir -U \
    tensorflow-text==2.10.0

RUN ${PIP} uninstall -y tensorflow tensorflow-gpu \
  ; ${PIP} install --no-cache-dir -U \
    ${TF_URL} \
    tensorflow-io==0.24.0 \
    tensorflow-datasets==4.5.2

# Install Horovod, temporarily using CUDA stubs
RUN ldconfig /usr/local/cuda-11.2/targets/x86_64-linux/lib/stubs \
 && HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_WITH_TENSORFLOW=1 ${PIP} install --no-cache-dir horovod==0.25.0 \
 && ldconfig

RUN $PYTHON -m pip install --no-cache-dir -U \
    "sagemaker>=2.93.0,<3" \
    sagemaker-experiments==0.* \
    "sagemaker-tensorflow-training>=20.3.1" \
    "sagemaker-training>=4.2.8" \
    "sparkmagic<1" \
    "sagemaker-studio-sparkmagic-lib<1" \
    "sagemaker-studio-analytics-extension==0.0.2" \
    smclarify

# Remove python kernel installed by sparkmagic
RUN /usr/local/bin/jupyter-kernelspec remove -f python3

RUN $PYTHON -m pip install --no-cache-dir -U \
    numba \
    "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"

# install smdebug directly the specific branch
ARG SMDEBUG_TAG=1.0.26
RUN git clone https://github.com/awslabs/sagemaker-debugger.git \
    && cd sagemaker-debugger \
    && git checkout tags/$SMDEBUG_TAG -b $SMDEBUG_TAG \
    && $PYTHON setup.py install && cd .. && rm -rf sagemaker-debugger

# install sagemaker-tensorflow from source
ARG SAGEMAKER_TENSORFLOW_TAG=v1.16.0
RUN apt update && apt install -y libcurl4-openssl-dev
RUN git clone -b tf-2 https://github.com/aws/sagemaker-tensorflow-extensions.git \
    && cd sagemaker-tensorflow-extensions \
    && git checkout tags/$SAGEMAKER_TENSORFLOW_TAG -b $SAGEMAKER_TENSORFLOW_TAG \
    && $PYTHON -m pip install . \
    && cd .. && rm -rf sagemaker-tensorflow-extensions

# install boost
# tensorflow is compiled with --cxxopt="-D_GLIBCXX_USE_CXX11_ABI=1"
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 define=_GLIBCXX_USE_CXX11_ABI=1 threading=multi --prefix=/usr -j 64 cxxflags=-fPIC cflags=-fPIC install || true \
   && cd .. \
   && rm -rf boost_1_73_0.tar.gz \
   && rm -rf boost_1_73_0 \
   && cd /usr/include/boost

# add smdataparallel
# smdataparallel
ARG SMDATAPARALLEL_BINARY=https://smdataparallel.s3.amazonaws.com/binary/tensorflow/2.10.0/cu112/2022-09-08/smdistributed_dataparallel-1.4.1-cp39-cp39-linux_x86_64.whl

# Install SMD DP binary
RUN SMDATAPARALLEL_TF=1 ${PYTHON} -m pip install --no-cache-dir ${SMDATAPARALLEL_BINARY}

# Add NGC vars
ENV TF_AUTOTUNE_THRESHOLD=2

ENV LD_LIBRARY_PATH="/usr/local/lib/${PYTHON}/site-packages/smdistributed/dataparallel/lib:$LD_LIBRARY_PATH"

# remove tmp files
RUN rm -rf /tmp/*

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*
   
CMD ["/bin/bash"]