Update Dockerfile to use CMake-based build (#1630)
* [DOCKER] Update Dockerfile to switch to CMake build * Fix typo in Dockerfile.ubuntu * Add README to docker sub-dir * Update Dockerfile and README * Modify markdown headings in docker/README * Update docs * Fix typo in docs * Update docs/install/docker-install.rst Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> * Update docs/install/docker-install.rst Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> * Update docs/install/docker-install.rst Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> * Update docker/README --------- Signed-off-by: nileshnegi <Nilesh.Negi@amd.com> Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
This commit is contained in:
+25
-10
@@ -11,10 +11,13 @@ ARG RCCL_BRANCH=develop
|
||||
ARG RCCL_TESTS_REPO=https://github.com/ROCm/rccl-tests
|
||||
ARG RCCL_TESTS_BRANCH=develop
|
||||
|
||||
## AMD GPU Targets
|
||||
ARG GPU_TARGETS=gfx942
|
||||
|
||||
## creating scratch space
|
||||
RUN mkdir -p /workspace
|
||||
WORKDIR /workspace
|
||||
ENV WORKDIR /workspace
|
||||
RUN mkdir -p ${WORKDIR}
|
||||
WORKDIR ${WORKDIR}
|
||||
|
||||
## install dependencies
|
||||
RUN apt-get update \
|
||||
@@ -55,6 +58,8 @@ RUN apt-get update \
|
||||
python3-dev \
|
||||
python3-tk \
|
||||
python3-yaml \
|
||||
vim \
|
||||
less \
|
||||
&& \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
@@ -64,6 +69,9 @@ RUN wget https://github.com/Kitware/CMake/releases/download/v3.28.0/cmake-3.28.0
|
||||
&& bash ./cmake-3.28.0-linux-x86_64.sh --prefix=/usr --exclude-subdir --skip-license \
|
||||
&& rm cmake-3.28.0-linux-x86_64.sh
|
||||
|
||||
## Set ROCm path
|
||||
ENV ROCM_PATH=/opt/rocm
|
||||
|
||||
## Install UCX
|
||||
ENV UCX_INSTALL_PREFIX=/opt/ucx
|
||||
RUN wget https://github.com/openucx/ucx/releases/download/v1.16.0/ucx-1.16.0.tar.gz \
|
||||
@@ -72,7 +80,7 @@ RUN wget https://github.com/openucx/ucx/releases/download/v1.16.0/ucx-1.16.0.tar
|
||||
&& cd ucx \
|
||||
&& mkdir build \
|
||||
&& cd build \
|
||||
&& ../configure --prefix=${UCX_INSTALL_PREFIX} --with-rocm=/opt/rocm \
|
||||
&& ../configure --prefix=${UCX_INSTALL_PREFIX} --with-rocm=${ROCM_PATH} \
|
||||
&& make -j16 install \
|
||||
&& cd ../.. \
|
||||
&& rm -rf ucx ucx-1.16.0.tar.gz
|
||||
@@ -92,18 +100,25 @@ RUN wget https://download.open-mpi.org/release/open-mpi/v4.1/openmpi-4.1.6.tar.g
|
||||
|
||||
|
||||
## building RCCL
|
||||
ENV RCCL_INSTALL_PREFIX=/opt/rocm
|
||||
RUN git clone --recurse-submodules -b "${RCCL_BRANCH}" "${RCCL_REPO}" ./rccl \
|
||||
&& cd ./rccl \
|
||||
&& ./install.sh -t --prefix=${RCCL_INSTALL_PREFIX}
|
||||
ENV RCCL_INSTALL_PREFIX=${WORKDIR}/rccl_develop/build/release
|
||||
RUN git clone --recurse-submodules -b "${RCCL_BRANCH}" "${RCCL_REPO}" ./rccl_develop \
|
||||
&& cd ./rccl_develop \
|
||||
&& ./install.sh --amdgpu_targets=${GPU_TARGETS}
|
||||
|
||||
## building RCCL-Tests
|
||||
RUN git clone -b "${RCCL_TESTS_BRANCH}" "${RCCL_TESTS_REPO}" ./rccl-tests \
|
||||
&& cd ./rccl-tests \
|
||||
&& make MPI=1 MPI_HOME=${MPI_INSTALL_PREFIX} NCCL_HOME=${RCCL_INSTALL_PREFIX} -j16
|
||||
&& mkdir build \
|
||||
&& cd build \
|
||||
&& CXX=${ROCM_PATH}/bin/amdclang++ MPI_HOME=${MPI_INSTALL_PREFIX} cmake -DCMAKE_BUILD_TYPE=Release -DUSE_MPI=ON -DAMDGPU_TARGETS=${GPU_TARGETS} .. \
|
||||
&& make -j16
|
||||
|
||||
|
||||
## set environment variables
|
||||
ENV PATH="${RCCL_INSTALL_PREFIX}/bin:${MPI_INSTALL_PREFIX}/bin:${PATH}"
|
||||
ENV LD_LIBRARY_PATH="${RCCL_INSTALL_PREFIX}/lib:${MPI_INSTALL_PREFIX}/lib:${LD_LIBRARY_PATH}"
|
||||
ENV PATH="${MPI_INSTALL_PREFIX}/bin:${ROCM_PATH}/bin:${PATH}"
|
||||
ENV LD_LIBRARY_PATH="${RCCL_INSTALL_PREFIX}:${MPI_INSTALL_PREFIX}/lib:${ROCM_PATH}/lib:${LD_LIBRARY_PATH}"
|
||||
ENV UCX_WARN_UNUSED_ENV_VARS=n
|
||||
ENV OMPI_ALLOW_RUN_AS_ROOT=1
|
||||
ENV OMPI_ALLOW_RUN_AS_ROOT_CONFIRM=1
|
||||
ENV NCCL_DEBUG=VERSION
|
||||
|
||||
|
||||
Reference in New Issue
Block a user