Add an example image that uses Intel MPI

examples/pi/intel-entrypoint.sh

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+set_intel_vars=/opt/intel/oneapi/setvars.sh
+if [ -f $set_intel_vars ]; then
+  source $set_intel_vars
+fi
+
+function resolve_host() {
+  host="$1"
+  check="nslookup $host"
+  max_retry=5
+  counter=0
+  backoff=0.1
+  until $check > /dev/null
+  do
+    if [ $counter -eq $max_retry ]; then
+      echo "Couldn't resolve $host"
+      return
+    fi
+    sleep $backoff
+    echo "Couldn't resolve $host... Retrying"
+    ((counter++))
+    backoff=$(echo - | awk "{print $backoff + $backoff}")
+  done
+  echo "Resolved $host"
+}
+
+if [ "$K_MPI_JOB_ROLE" == "launcher" ]; then
+  resolve_host "$HOSTNAME"
+  cat /etc/mpi/hostfile | while read host
+  do
+    resolve_host $host
+  done
+fi
+
+exec "$@"

examples/pi/intel.Dockerfile

@@ -0,0 +1,45 @@
+FROM bash AS downloader
+
+RUN wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB -O key.PUB
+
+
+FROM debian:buster
+
+COPY --from=downloader key.PUB /tmp/key.PUB
+
+# Install Intel oneAPI keys.
+RUN apt update \
+		&& apt install -y --no-install-recommends gnupg2 ca-certificates \
+    && apt-key add /tmp/key.PUB \
+		&& rm /tmp/key.PUB \
+		&& echo "deb https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list \
+		&& apt remove -y gnupg2 ca-certificates \
+		&& apt autoremove -y \
+		&& rm -rf /var/lib/apt/lists/*
+
+RUN apt update \
+		&& apt install -y --no-install-recommends \
+			openssh-server \
+			openssh-client \
+			dnsutils \
+			libstdc++-8-dev binutils \
+			intel-oneapi-compiler-dpcpp-cpp \
+			intel-oneapi-mpi \
+			intel-oneapi-mpi-devel \
+		&& rm -rf /var/lib/apt/lists/*
+
+# Add priviledge separation directoy to run sshd as root.
+RUN mkdir -p /var/run/sshd
+# Add capability to run sshd as non-root.
+RUN setcap CAP_NET_BIND_SERVICE=+eip /usr/sbin/sshd
+
+RUN useradd -m mpiuser
+WORKDIR /home/mpiuser
+COPY intel-entrypoint.sh /entrypoint.sh
+ENTRYPOINT ["/entrypoint.sh"]
+COPY --chown=mpiuser sshd_config .sshd_config
+RUN sed -i 's/[ #]\(.*StrictHostKeyChecking \).*/ \1no/g' /etc/ssh/ssh_config
+
+ENV I_MPI_CC=clang I_MPI_CXX=clang++
+COPY pi.cc /src/pi.cc
+RUN bash -c "source /opt/intel/oneapi/setvars.sh && mpicxx /src/pi.cc -o /home/mpiuser/pi"

examples/pi/pi-intel.yaml

@@ -0,0 +1,52 @@
+apiVersion: kubeflow.org/v2beta1
+kind: MPIJob
+metadata:
+  name: pi
+spec:
+  slotsPerWorker: 1
+  cleanPodPolicy: Running
+  sshAuthMountPath: /home/mpiuser/.ssh
+  mpiImplementation: Intel
+  mpiReplicaSpecs:
+    Launcher:
+      replicas: 1
+      template:
+        spec:
+          containers:
+          - image: docker.io/kubeflow/mpi-pi:intel
+            imagePullPolicy: Always
+            name: mpi-launcher
+            securityContext:
+              runAsUser: 1000
+            args:
+            - mpirun
+            - -n
+            - "2"
+            - /home/mpiuser/pi
+            resources:
+              limits:
+                cpu: 1
+                memory: 1Gi
+    Worker:
+      replicas: 2
+      template:
+        spec:
+          containers:
+          - image: docker.io/kubeflow/mpi-pi:intel
+            imagePullPolicy: Always
+            name: mpi-worker
+            securityContext:
+              runAsUser: 1000
+              capabilities:
+                add:
+                - NET_BIND_SERVICE
+            command:
+            args:
+            - /usr/sbin/sshd
+            - -De
+            - -f
+            - /home/mpiuser/.sshd_config
+            resources:
+              limits:
+                cpu: 1
+                memory: 1Gi

examples/pi/pi.yaml

@@ -19,13 +19,13 @@ spec:
             command:
             - mpirun
             args:
-            - -np
+            - -n
             - "2"
             - /home/mpiuser/pi
             resources:
               limits:
                 cpu: 1
-                memory: 2Gi
+                memory: 1Gi
     Worker:
       replicas: 2
       template:
@@ -46,5 +46,5 @@ spec:
             - /home/mpiuser/.sshd_config
             resources:
               limits:
-                cpu: 2
-                memory: 4Gi
+                cpu: 1
+                memory: 1Gi