Files
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

119 lines
4.0 KiB
Docker

# Use amdsmi base image
FROM amdsmi-image
# Sync ROCm repositories
# Fetch the ROCm signing key over HTTPS, verify it against a pinned SHA-256
# checksum, and install it as a dedicated signed-by keyring instead of the
# deprecated "apt-key add" (which would trust the key for every repository).
# Update the checksum if AMD rotates the key
# (fingerprint CA8B B472 7A47 B4D0 9B4E E896 9386 B48A 1A69 3C5C).
RUN apt-get update && apt-get install -y wget gnupg2 ca-certificates && \
install -d -m 0755 /etc/apt/keyrings && \
wget -qO /tmp/rocm.gpg.key https://repo.radeon.com/rocm/rocm.gpg.key && \
echo '2de99e2354646a90d9903e2a669fc4e36b02c1bbff7075c481e12d7edab2c88b /tmp/rocm.gpg.key' | sha256sum -c - && \
gpg --dearmor < /tmp/rocm.gpg.key > /etc/apt/keyrings/rocm.gpg && \
chmod 0644 /etc/apt/keyrings/rocm.gpg && \
rm -f /tmp/rocm.gpg.key && \
echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/debian/ jammy main' > /etc/apt/sources.list.d/rocm.list && \
rm -rf /var/lib/apt/lists/*
# Install ROCm runtime and dependencies
RUN apt-get update && \
apt-get install -y \
rocm-smi-lib \
cmake \
make \
g++ \
doxygen \
texlive-latex-base \
automake \
unzip \
build-essential \
autoconf \
libtool \
pkg-config \
libgflags-dev \
libgtest-dev \
clang \
libc++-dev \
curl \
libcap-dev \
python3-argcomplete \
python3-pip \
bash && \
rm -rf /var/lib/apt/lists/*
# Update setuptools
RUN python3 -m pip install --upgrade setuptools==59.6.0
# Check for modprobe
RUN command -v modprobe || echo "modprobe not found"
# Set environment variables
ENV GRPC_ROOT=/opt/grpc
ENV RDC_LIB_DIR=/opt/rocm/lib/rdc
ENV CMAKE_ROOT=/usr/bin/cmake
# Install gRPC
RUN git clone -b v1.67.1 https://github.com/grpc/grpc --depth=1 --shallow-submodules --recurse-submodules && \
cd grpc && \
cmake -B build \
-DgRPC_INSTALL=ON \
-DgRPC_BUILD_TESTS=OFF \
-DBUILD_SHARED_LIBS=ON \
-DCMAKE_INSTALL_PREFIX="$GRPC_ROOT" \
-DCMAKE_INSTALL_LIBDIR=lib \
-DCMAKE_BUILD_TYPE=Release && \
make -C build -j $(nproc) && \
make -C build install && \
echo "$GRPC_ROOT" | tee /etc/ld.so.conf.d/grpc.conf
# Build and install RDC
RUN git clone https://github.com/ROCm/rocm-systems --recursive && \
cd rocm-systems/projects/rdc && \
cmake -B build -DGRPC_ROOT="$GRPC_ROOT" \
-DSMIDIR="$SMI_DIR" \
-DBUILD_TESTS=OFF \
-DBUILD_PROFILER=OFF \
-DBUILD_RUNTIME=OFF \
-DBUILD_RVS=OFF && \
make -C build -j $(nproc) && \
make -C build install
# Update system library path
RUN export RDC_LIB_DIR=/opt/rocm/lib/rdc && \
export GRPC_LIB_DIR="/opt/grpc/lib" && \
echo "${RDC_LIB_DIR}" | tee /etc/ld.so.conf.d/x86_64-librdc_client.conf && \
echo "${GRPC_LIB_DIR}" | tee -a /etc/ld.so.conf.d/x86_64-librdc_client.conf && \
ldconfig
# Expose the port for Prometheus
EXPOSE 50051
# Expose the prometheus plugin port
EXPOSE 5000
# Set working directory to /opt/rocm/libexec/rdc/python_binding
WORKDIR /opt/rocm/libexec/rdc/python_binding
# Install Prometheus
RUN wget https://github.com/prometheus/prometheus/releases/download/v2.41.0/prometheus-2.41.0.linux-amd64.tar.gz && \
tar xvfz prometheus-2.41.0.linux-amd64.tar.gz && \
mv prometheus-2.41.0.linux-amd64/prometheus /usr/local/bin/ && \
rm -rf prometheus-2.41.0.linux-amd64*
# Install Grafana
RUN wget https://dl.grafana.com/oss/release/grafana-9.3.2.linux-amd64.tar.gz && \
tar -zxvf grafana-9.3.2.linux-amd64.tar.gz && \
mv grafana-9.3.2 /usr/local/grafana && \
rm grafana-9.3.2.linux-amd64.tar.gz
# Install Prometheus client for Python
RUN python3 -m pip install prometheus_client
# Ensure sudo can run without a password for the rdcd command
RUN echo "ALL ALL=(ALL) NOPASSWD: /opt/rocm/bin/rdcd" >> /etc/sudoers
# Set the entry point to run the rdcd command
ENTRYPOINT ["sudo", "/opt/rocm/bin/rdcd", "-u"]