Please follow the instructions in https://software.intel.com/content/www/us/en/develop/tools/oneapi/base-toolkit.html to install Intel oneAPI Base Toolkit on the management node according to your own needs.
Please follow the instructions in https://software.intel.com/content/www/us/en/develop/tools/oneapi/hpc-toolkit.html to install Intel oneAPI HPC Toolkit on the management node according to your own needs.
Before install AI Analytics Toolkit,make sure intel oneAPI Base Toolkit installed. Please follow the instructions in https://software.intel.com/content/www/us/en/develop/tools/oneapi/ai-analytics-toolkit.html to install Intel oneAPI AI Analytics Toolkit on the management node according to your own needs.
Run the following commands to initialize modulefiles for LiCO on the management node:
x# where is the intel oneapi installed, /opt/intel/oneapi is the default pathONEAPI_PATH="/opt/intel/oneapi"
source $ONEAPI_PATH/setvars.shbash $ONEAPI_PATH/modulefiles-setup.shPlease create a shared directory based on the upper directory of the oneapi installation path (task /opt/intel as an example):
Step 1. Manage node sharing /opt/intel for Intel oneAPI:
xxxxxxxxxxecho "/opt/intel *(rw,no_subtree_check,no_root_squash)" >> /etc/exportsexportfs -aStep 2. Configure the shared directory:
xxxxxxxxxx# IP address of management node in the compute intranetMANAGER_NODE_IP="192.168.0.1"
nodeshell all "echo '${MANAGER_NODE_IP}:/opt/intel /opt/intel nfs nfsvers=4.0,nodev,noatime \0 0' >> /etc/fstab"Step 3. Mount shared directory
xxxxxxxxxxnodeshell all mkdir -p /opt/intelnodeshell all mount /opt/intelStep 4. change write permission for socwatch
xxxxxxxxxxcd /opt/intel/oneapi/vtune/latest/socwatchchmod 777 x64Add the LiCO module path on the login and compute nodes.
xxxxxxxxxx# where is the intel oneapi installed, /opt/intel/oneapi is the default pathONEAPI_PATH="/opt/intel/oneapi"
nodeshell all "sed -i s#/opt/ohpc/pub/modulefiles#/opt/ohpc/pub/modulefiles:$ONEAPI_PATH/modulefiles#g /etc/profile.d/lmod.sh"
nodeshell all "sed -i s#/opt/ohpc/pub/modulefiles#/opt/ohpc/pub/modulefiles:$ONEAPI_PATH/modulefiles#g /etc/profile.d/lmod.csh"
nodeshell all "source /etc/profile.d/lmod.sh"Run the following commands on the management node:
xxxxxxxxxx# where is the intel oneapi installed, /opt/intel/oneapi is the default pathONEAPI_PATH="/opt/intel/oneapi"
sed -i s#/opt/ohpc/pub/modulefiles#/opt/ohpc/pub/modulefiles:$ONEAPI_PATH/modulefiles#g /etc/profile.d/lmod.sh
sed -i s#/opt/ohpc/pub/modulefiles#/opt/ohpc/pub/modulefiles:$ONEAPI_PATH/modulefiles#g /etc/profile.d/lmod.csh
source /etc/profile.d/lmod.sh
sed -i s#/opt/ohpc/pub/modulefiles#/opt/ohpc/pub/modulefiles:$ONEAPI_PATH/modulefiles#g /etc/lico/lico.ini.d/template.ini
lico lmod_syncxxxxxxxxxxvi /etc/lico/lico.ini.d/oneapi.ini
INTEL_MODULE_PATH = "<oneAPI install dir>"ENABLE = truexxxxxxxxxxlico initxxxxxxxxxx# add two kernel parameters in /etc/sysctl.conf on the compute nodes
nodeshell compute "echo 'kernel.kptr_restrict=0' >> /etc/sysctl.conf"nodeshell compute "echo 'kernel.perf_event_paranoid=0' >> /etc/sysctl.conf"nodeshell compute sysctl -p /etc/sysctl.confxxxxxxxxxx
vim /opt/intel/oneapi/vtune/latest/backend/config.yml
# change the type from passphrase to reverse-proxy
#type:passphrase type: reverse-proxyheader: AuthorizationRun the following commands on the compute nodes:
xxxxxxxxxx# where is the intel oneapi installed, /opt/intel/oneapi is the default pathONEAPI_PATH="/opt/intel/oneapi"
nodeshell compute "cd ${ONEAPI_PATH}/vtune/latest/sepdk/src && sudo ./rmmod-sep"nodeshell -c 1 compute "cd ${ONEAPI_PATH}/vtune/latest/sepdk/src && sudo ./build-driver -ni"
# The following errors may be reported:# c3: ERROR: kernel source directory "/usr/src/linux-4.18.0-305.3.1.el8.x86_64" either does not existor not a valid kernel source directory.# c3:# c3: Please use the following command to install kernel header on CentOS:# c3: yum install kernel-devel-4.18.0-305.3.1.el8.x86_64## If an error occurs, install the corresponding program on the corresponding node as prompted:# eg: nodeshell c3 "sudo yum install -y kernel-devel-4.18.0-305.3.1.el8.x86_64"
nodeshell compute "cd ${ONEAPI_PATH}/vtune/latest/sepdk/src && sudo ./insmod-sep"nodeshell compute "cd ${ONEAPI_PATH}/vtune/latest/sepdk/src && sudo ./boot-script -i -g vtune"nodeshell compute "sed -i 's#^After.*#& network.target\nRequiresMountsFor=${ONEAPI_PATH}#g' /usr/lib/systemd/system/sep5.service"
Run the following commands on the compute nodes:
xxxxxxxxxxnodeshell compute "dnf install -y dstat"Run the following commands on the management node:
xxxxxxxxxxdnf install sqliteRun the following commands on the management node to check if the installation is successful:
xxxxxxxxxx# The output may be /opt/intel/oneapi/intelpython/latest/bin/mpirunwhich mpirun
# The output may be /opt/intel/oneapi/intelpython/latest/bin/mpitunewhich mpitune
# The output may be /opt/intel/oneapi/mpi/2021.1.1/bin/mpiiccwhich mpiiccRun the following commands on the management node to check whether the module is successfully configured:
xxxxxxxxxx# The output contains /opt/intel/oneapi/modulefiles informationmodule avaRun the following commands on the management node to check whether the intel python is installed.
xxxxxxxxxx[root@head ~]# source /opt/intel/oneapi/setvars.sh[root@head ~]# conda env list# conda environments:#base * /opt/intel/oneapi/intelpython/latest2022.1.0 /opt/intel/oneapi/intelpython/latest/envs/2022.1.0modin /opt/intel/oneapi/intelpython/latest/envs/modinmodin-0.13.3 /opt/intel/oneapi/intelpython/latest/envs/modin-0.13.3pytorch /opt/intel/oneapi/intelpython/latest/envs/pytorchpytorch-1.10.0 /opt/intel/oneapi/intelpython/latest/envs/pytorch-1.10.0tensorflow /opt/intel/oneapi/intelpython/latest/envs/tensorflowtensorflow-2.8.0 /opt/intel/oneapi/intelpython/latest/envs/tensorflow-2.8.0
Run the following commands on the management node to check whether the Intel driver is installed.
# The output might be the following:# c1: sep5 2793472 0# c1: socperf3 602112 1 sep5# c2: sep5 2793472 0# c2: socperf3 602112 1 sep5nodeshell compute "lsmod |grep sep"