Horovod Install

Horovod documentation

安装

【Step1】安装Open MPI

注意： Open MPI 3.1.3 安装有些问题， 可以安装 Open MPI 3.1.2 或者 Open MPI 4.0.0.

【Step2】安装 TensorFlow

• pip install tensorflow 确保 g++-4.8.5 或者 g++-4.9
• 也可以用conda 安装

【Step3】安装 horovod

cpu

pip install horovod

GPUs with NCCL:

$ HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_GPU_BROADCAST=NCCL pip install horovod

Docker 文档：

https://horovod.readthedocs.io/en/stable/docker.html

https://raw.githubusercontent.com/horovod/horovod/master/Dockerfile.cpu
https://raw.githubusercontent.com/horovod/horovod/master/Dockerfile.gpu

CPU-Dockerfile

FROM ubuntu:18.04

ENV TENSORFLOW_VERSION=2.1.0
ENV PYTORCH_VERSION=1.4.0
ENV TORCHVISION_VERSION=0.5.0
ENV MXNET_VERSION=1.6.0

# Python 3.6 is supported by Ubuntu Bionic out of the box
ARG python=3.6
ENV PYTHON_VERSION=${python}

# 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 \
        libjpeg-dev \
        libpng-dev \
        python${PYTHON_VERSION} \
        python${PYTHON_VERSION}-dev \
        python${PYTHON_VERSION}-distutils \
        librdmacm1 \
        libibverbs1 \
        ibverbs-providers

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
RUN pip install numpy \
        tensorflow==${TENSORFLOW_VERSION} \
        keras \
        h5py
RUN pip install torch==${PYTORCH_VERSION} torchvision==${TORCHVISION_VERSION}
RUN pip install mxnet==${MXNET_VERSION}

# Install Open MPI
RUN mkdir /tmp/openmpi && \
    cd /tmp/openmpi && \
    wget https://www.open-mpi.org/software/ompi/v4.0/downloads/openmpi-4.0.0.tar.gz && \
    tar zxf openmpi-4.0.0.tar.gz && \
    cd openmpi-4.0.0 && \
    ./configure --enable-orterun-prefix-by-default && \
    make -j $(nproc) all && \
    make install && \
    ldconfig && \
    rm -rf /tmp/openmpi

# Install Horovod
RUN HOROVOD_WITH_TENSORFLOW=1 HOROVOD_WITH_PYTORCH=1 HOROVOD_WITH_MXNET=1 \
    pip install --no-cache-dir horovod

# 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

# Download examples
RUN apt-get install -y --no-install-recommends subversion && \
    svn checkout https://github.com/horovod/horovod/trunk/examples && \
    rm -rf /examples/.svn

WORKDIR "/examples"

GPU-Dockerfile

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=7.6.5.32-1+cuda10.1
ENV NCCL_VERSION=2.4.8-1+cuda10.1
ENV MXNET_VERSION=1.6.0

# Python 3.6 is supported by Ubuntu Bionic out of the box
ARG python=3.6
ENV PYTHON_VERSION=${python}

# 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${PYTHON_VERSION}-dev \
        python${PYTHON_VERSION}-distutils \
        librdmacm1 \
        libibverbs1 \
        ibverbs-providers

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
RUN pip install numpy \
        tensorflow-gpu==${TENSORFLOW_VERSION} \
        keras \
        h5py

RUN pip install https://download.pytorch.org/whl/cu101/torch-${PYTORCH_VERSION}-$(python -c "import wheel.pep425tags as w; print('-'.join(w.get_supported(None)[0][:-1]))")-linux_x86_64.whl \
        https://download.pytorch.org/whl/cu101/torchvision-${TORCHVISION_VERSION}-$(python -c "import wheel.pep425tags as w; print('-'.join(w.get_supported(None)[0][:-1]))")-linux_x86_64.whl
RUN pip install mxnet-cu101==${MXNET_VERSION}

# Install Open MPI
RUN mkdir /tmp/openmpi && \
    cd /tmp/openmpi && \
    wget https://www.open-mpi.org/software/ompi/v4.0/downloads/openmpi-4.0.0.tar.gz && \
    tar zxf openmpi-4.0.0.tar.gz && \
    cd openmpi-4.0.0 && \
    ./configure --enable-orterun-prefix-by-default && \
    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_OPERATIONS=NCCL HOROVOD_WITH_TENSORFLOW=1 HOROVOD_WITH_PYTORCH=1 HOROVOD_WITH_MXNET=1 \
         pip install --no-cache-dir horovod && \
    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

# Download examples
RUN apt-get install -y --no-install-recommends subversion && \
    svn checkout https://github.com/horovod/horovod/trunk/examples && \
    rm -rf /examples/.svn

WORKDIR "/examples"