apiVersion: batch/v1
kind: Job
metadata:
  name: batch-job
spec:
  parallelism: 10
  completions: 100
  backoffLimit: 3
  template:
    spec:
      containers:
      - name: worker
        image: <IMAGE>
        resources:
          requests:
            cpu: "1"
            memory: "2Gi"
      restartPolicy: Never

apiVersion: jobset.x-k8s.io/v1alpha2
kind: JobSet
metadata:
  name: training-job
spec:
  replicatedJobs:
  - name: workers
    replicas: 4
    template:
      spec:
        parallelism: 1
        completions: 1
        template:
          spec:
            containers:
            - name: worker
              image: <IMAGE>
              resources:
                requests:
                  cpu: "4"
                  memory: "8Gi"

# Install Kueue
kubectl apply --server-side -f https://github.com/kubernetes-sigs/kueue/releases/latest/download/manifests.yaml

# Define a ClusterQueue
apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: batch-queue
spec:
  namespaceSelector: {}
  resourceGroups:
  - coveredResources: ["cpu", "memory"]
    flavors:
    - name: default
      resources:
      - name: "cpu"
        nominalQuota: 100
      - name: "memory"
        nominalQuota: "200Gi"
---
# Allow a namespace to use the queue
apiVersion: kueue.x-k8s.io/v1beta1
kind: LocalQueue
metadata:
  name: batch-local
  namespace: batch-jobs
spec:
  clusterQueue: batch-queue

# Standard clusters: create node pool with compact placement
gcloud container node-pools create hpc-pool \
  --cluster <CLUSTER_NAME> --region <REGION> \
  --machine-type c3-standard-44 \
  --placement-type COMPACT \
  --num-nodes 8 \
  --enable-autoscaling --min-nodes 0 --max-nodes 16 \
  --quiet

# Install MPI Operator
kubectl apply -f https://raw.githubusercontent.com/kubeflow/mpi-operator/master/deploy/v2beta1/mpi-operator.yaml

apiVersion: kubeflow.org/v2beta1
kind: MPIJob
metadata:
  name: hpc-simulation
spec:
  slotsPerWorker: 4
  mpiReplicaSpecs:
    Launcher:
      replicas: 1
      template:
        spec:
          containers:
          - name: launcher
            image: <MPI_IMAGE>
            command: ["mpirun", "-np", "32", "./simulation"]
            resources:
              requests:
                cpu: "1"
                memory: "2Gi"
              limits:
                cpu: "2"
                memory: "4Gi"
    Worker:
      replicas: 8
      template:
        spec:
          containers:
          - name: worker
            image: <MPI_IMAGE>
            resources:
              requests:
                cpu: "4"
                memory: "8Gi"
              limits:
                cpu: "8"
                memory: "16Gi"