XMerge remote-tracking branch 'upstream/2023.06-pilot.eessi-hpc.org' …

…into cuda_install

.github/workflows/tests_archdetect.yml

@@ -14,14 +14,15 @@ jobs:
           - x86_64/amd/zen2/Azure-CentOS7-7V12
           - x86_64/amd/zen3/Azure-CentOS7-7V73X
           - ppc64le/power9le/unknown-power9le
-          - aarch64/arm/neoverse-n1/Azure-Ubuntu20-Altra
-          - aarch64/arm/neoverse-n1/AWS-awslinux-graviton2
-          - aarch64/arm/neoverse-v1/AWS-awslinux-graviton3
+          - aarch64/neoverse_n1/Azure-Ubuntu20-Altra
+          - aarch64/neoverse_n1/AWS-awslinux-graviton2
+          - aarch64/neoverse_v1/AWS-awslinux-graviton3
       fail-fast: false
     steps:
     - name: checkout
       uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v3.1.0
-
+    - name: Enable EESSI
+      uses: eessi/github-action-eessi@58b50fd2eead2162c2b9ac258d4fb60cc9f30503 # v2.0.13
     - name: test eessi_archdetect.sh
       run: |
           export EESSI_MACHINE_TYPE=${{matrix.proc_cpuinfo}}
@@ -34,3 +35,15 @@ jobs:
               echo "Test for ${{matrix.proc_cpuinfo}} FAILED: $CPU_ARCH" >&2
               exit 1
           fi
+          CPU_ARCHES=$(./init/eessi_archdetect.sh -a cpupath)
+          if [[ $CPU_ARCHES == "$( cat ./tests/archdetect/${{matrix.proc_cpuinfo}}.all.output )" ]]; then
+              echo "Test for ${{matrix.proc_cpuinfo}} PASSED: $CPU_ARCHES" >&2
+          else
+              echo "Test for ${{matrix.proc_cpuinfo}} FAILED: $CPU_ARCHES" >&2
+              exit 1
+          fi
+          # Check all those architectures actually exist
+          for dir in $(echo "$CPU_ARCHES" | tr ':' '\n'); do
+              # Search all EESSI versions as we may drop support at some point 
+              ls -d "$EESSI_PREFIX"/../*/software/linux/"$dir" 
+          done

configure_easybuild

@@ -25,8 +25,7 @@ fi
 
 # note: filtering Bison may break some installations, like Qt5 (see https://github.com/EESSI/software-layer/issues/49)
 # filtering pkg-config breaks R-bundle-Bioconductor installation (see also https://github.com/easybuilders/easybuild-easyconfigs/pull/11104)
-# problems occur when filtering pkg-config with gnuplot too (picks up Lua 5.1 from $EPREFIX rather than from Lua 5.3 dependency)
-DEPS_TO_FILTER=Autoconf,Automake,Autotools,binutils,bzip2,DBus,flex,gettext,gperf,help2man,intltool,libreadline,libtool,Lua,M4,makeinfo,ncurses,util-linux,XZ,zlib
+DEPS_TO_FILTER=Autoconf,Automake,Autotools,binutils,bzip2,DBus,flex,gettext,gperf,help2man,intltool,libreadline,libtool,M4,makeinfo,ncurses,util-linux,XZ,zlib
 # For aarch64 we need to also filter out Yasm.
 # See https://github.com/easybuilders/easybuild-easyconfigs/issues/11190
 if [[ "$EESSI_CPU_FAMILY" == "aarch64" ]]; then

eb_hooks.py

@@ -19,6 +19,7 @@
 
 
 CPU_TARGET_NEOVERSE_V1 = 'aarch64/neoverse_v1'
+CPU_TARGET_AARCH64_GENERIC = 'aarch64/generic' 
 
 EESSI_RPATH_OVERRIDE_ATTR = 'orig_rpath_override_dirs'
 
@@ -276,6 +277,24 @@ def pre_configure_hook_wrf_aarch64(self, *args, **kwargs):
         raise EasyBuildError("WRF-specific hook triggered for non-WRF easyconfig?!")
 
 
+def pre_configure_hook_LAMMPS_aarch64(self, *args, **kwargs):
+    """
+    pre-configure hook for LAMMPS:
+    - set kokkos_arch on Aarch64
+    """
+
+    cpu_target = get_eessi_envvar('EESSI_SOFTWARE_SUBDIR')
+    if self.name == 'LAMMPS':
+        if self.version == '23Jun2022':
+            if  get_cpu_architecture() == AARCH64:
+                if cpu_target == CPU_TARGET_AARCH64_GENERIC:
+                    self.cfg['kokkos_arch'] = 'ARM80'
+                else:
+                    self.cfg['kokkos_arch'] = 'ARM81'
+    else:
+        raise EasyBuildError("LAMMPS-specific hook triggered for non-LAMMPS easyconfig?!")
+
+
 def pre_test_hook(self,*args, **kwargs):
     """Main pre-test hook: trigger custom functions based on software name."""
     if self.name in PRE_TEST_HOOKS:
@@ -428,6 +447,7 @@ def inject_gpu_property(ec):
     'MetaBAT': pre_configure_hook_metabat_filtered_zlib_dep,
     'OpenBLAS': pre_configure_hook_openblas_optarch_generic,
     'WRF': pre_configure_hook_wrf_aarch64,
+    'LAMMPS': pre_configure_hook_LAMMPS_aarch64,
 }
 
 PRE_TEST_HOOKS = {

eessi-2023.06-eb-4.8.0-2021b.yml

@@ -4,4 +4,9 @@ easyconfigs:
       # see https://github.com/easybuilders/easybuild-easyconfigs/pull/18746
       options:
         from-pr: 18746
+  - gnuplot-5.4.2-GCCcore-11.2.0.eb:
+      # make sure that Lua dependency is correctly picked up,
+      # see https://github.com/easybuilders/easybuild-easyconfigs/pull/19261
+      options:
+        from-pr: 19261
   - OpenFOAM-v2112-foss-2021b.eb

eessi-2023.06-eb-4.8.1-2021b.yml

@@ -5,3 +5,11 @@ easyconfigs:
       options:
         from-pr: 18834
   - R-4.2.0-foss-2021b.eb
+  - PLUMED-2.7.3-foss-2021b.eb:
+      # the --enable-asmjit is not supported on Aarch64
+      options:
+        from-pr: 19110
+  - LAMMPS-23Jun2022-foss-2021b-kokkos.eb:
+      # TBB and ScaFaCos are optional dependencies when building on Intel arch
+      options:
+        from-pr: 19246

eessi-2023.06-eb-4.8.2-2021b.yml

@@ -0,0 +1,6 @@
+easyconfigs:
+  - Pillow-8.3.2-GCCcore-11.2.0.eb:
+      # avoid that hardcoded paths like /usr/include are used in build commands
+      options:
+        from-pr: 19226
+  - matplotlib-3.4.3-foss-2021b.eb

eessi-2023.06-eb-4.8.2-2022a.yml

@@ -5,27 +5,6 @@ easyconfigs:
   - AOFlagger-3.4.0-foss-2022a:
       options:
         from-pr: 19119
-        # Exclude Lua from `filter-deps` as the compat layer version is too old for the software
-        filter-deps:
-          - Autoconf
-          - Automake
-          - Autotools
-          - binutils
-          - bzip2
-          - DBus
-          - flex
-          - gettext
-          - gperf
-          - help2man
-          - intltool
-          - libreadline
-          - libtool
-          - ncurses
-          - M4
-          - makeinfo
-          - util-linux
-          - XZ
-          - zlib
   - EveryBeam-0.5.2-foss-2022a:
       options:
         from-pr: 19119
@@ -35,3 +14,8 @@ easyconfigs:
   - WSClean-3.4-foss-2022a:
       options:
         from-pr: 19119
+  - Pillow-9.1.1-GCCcore-11.3.0.eb:
+      # avoid that hardcoded paths like /usr/include are used in build commands
+      options:
+        from-pr: 19226
+  - matplotlib-3.5.2-foss-2022a.eb

eessi_container.sh

@@ -30,8 +30,8 @@
 # -. initial settings & exit codes
 TOPDIR=$(dirname $(realpath $0))
 
-source ${TOPDIR}/scripts/utils.sh
-source ${TOPDIR}/scripts/cfg_files.sh
+source "${TOPDIR}"/scripts/utils.sh
+source "${TOPDIR}"/scripts/cfg_files.sh
 
 # exit codes: bitwise shift codes to allow for combination of exit codes
 # ANY_ERROR_EXITCODE is sourced from ${TOPDIR}/scripts/utils.sh
@@ -46,6 +46,7 @@ SAVE_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 8))
 HTTP_PROXY_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 9))
 HTTPS_PROXY_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 10))
 RUN_SCRIPT_MISSING_EXITCODE=$((${ANY_ERROR_EXITCODE} << 11))
+NVIDIA_MODE_UNKNOWN_EXITCODE=$((${ANY_ERROR_EXITCODE} << 12))
 
 # CernVM-FS settings
 CVMFS_VAR_LIB="var-lib-cvmfs"
@@ -72,12 +73,17 @@ display_help() {
   echo "  -a | --access {ro,rw}  - ro (read-only), rw (read & write) [default: ro]"
   echo "  -c | --container IMG   - image file or URL defining the container to use"
   echo "                           [default: docker://ghcr.io/eessi/build-node:debian11]"
-  echo "  -h | --help            - display this usage information [default: false]"
   echo "  -g | --storage DIR     - directory space on host machine (used for"
   echo "                           temporary data) [default: 1. TMPDIR, 2. /tmp]"
+  echo "  -h | --help            - display this usage information [default: false]"
+  echo "  -i | --host-injections - directory to link to for host_injections "
+  echo "                           [default: /..storage../opt-eessi]"
   echo "  -l | --list-repos      - list available repository identifiers [default: false]"
   echo "  -m | --mode MODE       - with MODE==shell (launch interactive shell) or"
   echo "                           MODE==run (run a script or command) [default: shell]"
+  echo "  -n | --nvidia MODE     - configure the container to work with NVIDIA GPUs,"
+  echo "                           MODE==install for a CUDA installation, MODE==run to"
+  echo "                           attach a GPU, MODE==all for both [default: false]"
   echo "  -r | --repository CFG  - configuration file or identifier defining the"
   echo "                           repository to use [default: EESSI-pilot via"
   echo "                           default container, see --container]"
@@ -111,6 +117,8 @@ VERBOSE=0
 STORAGE=
 LIST_REPOS=0
 MODE="shell"
+SETUP_NVIDIA=0
+ADDITIONAL_SINGULARITY_FLAGS=
 REPOSITORY="EESSI-pilot"
 RESUME=
 SAVE=
@@ -141,6 +149,10 @@ while [[ $# -gt 0 ]]; do
       display_help
       exit 0
       ;;
+    -i|--host-injections)
+      USER_HOST_INJECTIONS="$2"
+      shift 2
+      ;;
     -l|--list-repos)
       LIST_REPOS=1
       shift 1
@@ -149,6 +161,11 @@ while [[ $# -gt 0 ]]; do
       MODE="$2"
       shift 2
       ;;
+    -n|--nvidia)
+      SETUP_NVIDIA=1
+      NVIDIA_MODE="$2"
+      shift 2
+      ;;
     -r|--repository)
       REPOSITORY="$2"
       shift 2
@@ -224,6 +241,13 @@ if [[ "${MODE}" != "shell" && "${MODE}" != "run" ]]; then
     fatal_error "unknown execution mode '${MODE}'" "${MODE_UNKNOWN_EXITCODE}"
 fi
 
+# Also validate the NVIDIA GPU mode (if present)
+if [[ ${SETUP_NVIDIA} -eq 1 ]]; then
+    if [[ "${NVIDIA_MODE}" != "run" && "${NVIDIA_MODE}" != "install" && "${NVIDIA_MODE}" != "all" ]]; then
+        fatal_error "unknown NVIDIA mode '${NVIDIA_MODE}'" "${NVIDIA_MODE_UNKNOWN_EXITCODE}"
+    fi
+fi
+
 # TODO (arg -r|--repository) check if repository is known
 # REPOSITORY_ERROR_EXITCODE
 if [[ ! -z "${REPOSITORY}" && "${REPOSITORY}" != "EESSI-pilot" && ! -r ${EESSI_REPOS_CFG_FILE} ]]; then
@@ -294,6 +318,7 @@ else
   echo "Using ${EESSI_HOST_STORAGE} as tmp directory (to resume session add '--resume ${EESSI_HOST_STORAGE}')."
 fi
 
+
 # if ${RESUME} is a file (assume a tgz), unpack it into ${EESSI_HOST_STORAGE}
 if [[ ! -z ${RESUME} && -f ${RESUME} ]]; then
   tar xf ${RESUME} -C ${EESSI_HOST_STORAGE}
@@ -310,12 +335,25 @@ fi
 #      |-overlay-work
 #      |-home
 #      |-repos_cfg
+#      |-opt-eessi (unless otherwise specificed for host_injections)
 
 # tmp dir for EESSI
 EESSI_TMPDIR=${EESSI_HOST_STORAGE}
 mkdir -p ${EESSI_TMPDIR}
 [[ ${VERBOSE} -eq 1 ]] && echo "EESSI_TMPDIR=${EESSI_TMPDIR}"
 
+# Set host_injections directory and ensure it is a writable directory (if user provided)
+if [ -z ${USER_HOST_INJECTIONS+x} ]; then
+    # Not set, so use our default
+    HOST_INJECTIONS=${EESSI_TMPDIR}/opt-eessi
+    mkdir -p $HOST_INJECTIONS
+else
+    # Make sure the host_injections directory specified exists and is a folder
+    mkdir -p ${USER_HOST_INJECTIONS} || fatal_error "host_injections directory ${USER_HOST_INJECTIONS} is either not a directory or cannot be created"
+    HOST_INJECTIONS=${USER_HOST_INJECTIONS}
+fi
+[[ ${VERBOSE} -eq 1 ]] && echo "HOST_INJECTIONS=${HOST_INJECTIONS}"
+
 # configure Singularity: if SINGULARITY_CACHEDIR is already defined, use that
 #   a global SINGULARITY_CACHEDIR would ensure that we don't consume
 #   storage space again and again for the container & also speed-up
@@ -394,12 +432,34 @@ fi
 [[ ${VERBOSE} -eq 1 ]] && echo "SINGULARITY_HOME=${SINGULARITY_HOME}"
 
 # define paths to add to SINGULARITY_BIND (added later when all BIND mounts are defined)
-BIND_PATHS="${EESSI_CVMFS_VAR_LIB}:/var/lib/cvmfs,${EESSI_CVMFS_VAR_RUN}:/var/run/cvmfs"
+BIND_PATHS="${EESSI_CVMFS_VAR_LIB}:/var/lib/cvmfs,${EESSI_CVMFS_VAR_RUN}:/var/run/cvmfs,${HOST_INJECTIONS}:/opt/eessi"
 # provide a '/tmp' inside the container
 BIND_PATHS="${BIND_PATHS},${EESSI_TMPDIR}:${TMP_IN_CONTAINER}"
 
 [[ ${VERBOSE} -eq 1 ]] && echo "BIND_PATHS=${BIND_PATHS}"
 
+# Configure anything we need for NVIDIA GPUs and CUDA installation
+if [[ ${SETUP_NVIDIA} -eq 1 ]]; then
+    if [[ "${NVIDIA_MODE}" == "run" || "${NVIDIA_MODE}" == "all" ]]; then
+        # Give singularity the appropriate flag
+        ADDITIONAL_SINGULARITY_FLAGS="--nv ${ADDITIONAL_SINGULARITY_FLAGS}"
+        [[ ${VERBOSE} -eq 1 ]] && echo "ADDITIONAL_SINGULARITY_FLAGS=${ADDITIONAL_SINGULARITY_FLAGS}"
+    fi
+    if [[ "${NVIDIA_MODE}" == "install" || "${NVIDIA_MODE}" == "all" ]]; then
+        # Add additional bind mounts to allow CUDA to install within a container
+        # (Experience tells us that these are necessary, but we don't know _why_
+        # as the CUDA installer is a black box. The suspicion is that the CUDA
+        # installer gets confused by the permissions on these directories when
+        # inside a container)
+        EESSI_VAR_LOG=${EESSI_TMPDIR}/var-log
+        EESSI_USR_LOCAL_CUDA=${EESSI_TMPDIR}/usr-local-cuda
+        mkdir -p ${EESSI_VAR_LOG}
+        mkdir -p ${EESSI_USR_LOCAL_CUDA}
+        BIND_PATHS="${BIND_PATHS},${EESSI_VAR_LOG}:/var/log,${EESSI_USR_LOCAL_CUDA}:/usr/local/cuda"
+        [[ ${VERBOSE} -eq 1 ]] && echo "BIND_PATHS=${BIND_PATHS}"
+    fi
+fi
+
 # set up repository config (always create directory repos_cfg and populate it with info when
 # arg -r|--repository is used)
 mkdir -p ${EESSI_TMPDIR}/repos_cfg
@@ -558,8 +618,8 @@ if [ ! -z ${EESSI_SOFTWARE_SUBDIR_OVERRIDE} ]; then
 fi
 
 echo "Launching container with command (next line):"
-echo "singularity ${RUN_QUIET} ${MODE} ${EESSI_FUSE_MOUNTS[@]} ${CONTAINER} $@"
-singularity ${RUN_QUIET} ${MODE} "${EESSI_FUSE_MOUNTS[@]}" ${CONTAINER} "$@"
+echo "singularity ${RUN_QUIET} ${MODE} ${ADDITIONAL_SINGULARITY_FLAGS} ${EESSI_FUSE_MOUNTS[@]} ${CONTAINER} $@"
+singularity ${RUN_QUIET} ${MODE} ${ADDITIONAL_SINGULARITY_FLAGS} "${EESSI_FUSE_MOUNTS[@]}" ${CONTAINER} "$@"
 exit_code=$?
 
 # 6. save tmp if requested (arg -s|--save)