Bump rocm image and change arch for debug hip build

parthenon-hpc-lab · Nov 22, 2024 · 9c47692 · 9c47692
1 parent e8b7c65
commit 9c47692
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 10 deletions.
diff --git a/.github/workflows/check-compilers.yml b/.github/workflows/check-compilers.yml
@@ -61,7 +61,7 @@ jobs:
         parallel: ['serial', 'mpi']
     runs-on: ubuntu-latest
     container:
-      image: ghcr.io/parthenon-hpc-lab/rocm5.4.3-mpi-hdf5
+      image: ghcr.io/parthenon-hpc-lab/rocm6.2-mpi-hdf5
     env:
       CMAKE_GENERATOR: Ninja
     steps:
@@ -74,7 +74,11 @@ jobs:
             -DCMAKE_CXX_COMPILER=${{ matrix.cxx }} \
             -DCMAKE_BUILD_TYPE=${{ matrix.cmake_build_type }} \
             -DMACHINE_CFG=${PWD}/cmake/machinecfg/GitHubActions.cmake \
-            -DMACHINE_VARIANT=${{ matrix.device }}_${{ matrix.parallel }}
+            -DMACHINE_VARIANT=${{ matrix.device }}_${{ matrix.parallel }} \
+            # Manually chaning the arch for this (debug) build as the
+            # -O0 option causes compiler issue for the navi 1030 GPU at
+            # compile time, see https://github.com/parthenon-hpc-lab/parthenon/pull/1191#issuecomment-2492035364
+            -DKokkos_ARCH_AMD_GFX90A=ON -DKokkos_ARCH_NAVI1030=OFF
       - name: Build
         run: |
           cmake --build builddir --parallel 2
diff --git a/scripts/docker/Dockerfile.hip-rocm b/scripts/docker/Dockerfile.hip-rocm
@@ -1,4 +1,4 @@
-FROM rocm/dev-ubuntu-20.04:5.4.3
+FROM rocm/dev-ubuntu-24.04:6.2
 
 RUN apt-get clean && apt-get update -y && \
     DEBIAN_FRONTEND="noninteractive" TZ=America/New_York apt-get install -y --no-install-recommends git python3-minimal libpython3-stdlib bc hwloc wget openssh-client python3-numpy python3-h5py python3-matplotlib lcov curl cmake ninja-build openmpi-bin libopenmpi-dev && \
@@ -14,12 +14,10 @@ RUN cd /tmp && \
     cd / && \
     rm -rf /tmp/hdf5-1.10.8*
 
-# "mpic++ --showme" forgets open-pal in Ubuntu 20.04 + OpenMPI 4.0.3
-#   https://bugs.launchpad.net/ubuntu/+source/openmpi/+bug/1941786
-#   https://github.com/open-mpi/ompi/issues/9317
-ENV LDFLAGS="-lopen-pal"
-
 RUN update-alternatives --install /usr/bin/python python /usr/bin/python3 10
 
-# uid 1000 maps to the one running the container on the CI host
-RUN useradd --create-home --shell /bin/bash -u 1000 -G render ci
+# Latest image has default user with uid 1000 (which maps to the one running the container on the CI host
+# Need to add user to the group that can access the GPU
+RUN usermod -a -G render ubuntu
+
+WORKDIR /home/ubuntu