sean-smith

import argparse
import boto3


class ClusterDestroyer:
    """Destroy all ParallelCluster clusters in a given region."""

    def __init__(self, region, dryrun):
        self.__created_clusters = []
        self.region = region

sean-smith

import argparse
import boto3


class ClusterDestroyer:
    """Destroy all ParallelCluster clusters in a given region."""

    def __init__(self, region, dryrun):
        self.__created_clusters = []
        self.region = region

sean-smith

COVID-19 AWS HPC Cluster

User Setup

To deploy, click:

Region	Stack
us-east-1	[](https://us-east-1.console.aws.amazon.com/cloudformation/home?region=us-east-1#/stacks/create/template?stackName=AWS-HPC-Quickstart&templateURL=https://covid19hpc-quickstart.s3.amazonaws.com/cf

sean-smith

General

	sge	slurm	torque
Submit Interactive Job	qlogin	srun	qsub -I
Submit Batch Job	qsub	sbatch	qsub
Number of Slots	-pe mpi [n]	-n [n]	-l ppn=[n]
Number of Nodes	-pe mpi [slots * n]	-N [n]	-l nodes=[n]
Cancel Job	qdel	scancel	qdel
See Queue	qstat	squeue	qstat

sean-smith

AWS ParallelCluster Specific AZ Deployment

To use AWS ParallelCluster in a specific Availibility Zone, do the following:

1. In the VPC Dashboard , click "VPC Wizard"

sean-smith

AWS ParallelCluster Multi-Instance Type

This guide will help you setup a SPOT-based multi-instance type cluster. In order to accomplish this, we make a few assumptions:

a. Instances share the same number of vcpus, in this case it's all 96 vcpus:

sean-smith

Install Intel Parallel Studio Runtime on AWS ParallelCluster

Tested on Amazon Linux 2

On all AWS ParallelCluster clusters /opt/intel is already shared out via NFS:

$ showmount -e
Export list for ip-172-31-41-183:

sean-smith

DCV Native Client w/ AWS ParallelCluster

1. Setup a cluster with DCV
2. Install the Native client: NICE DCV | Download
3. Create a script pcluster-dcv-connect.py with the contents as shown below:
4. Execute that script

# make sure you have pcluster installed
$ pcluster list --color

sean-smith

Intel oneAPI for AWS ParallelCluster

First setup yum to get the right repo:

tee > /tmp/oneAPI.repo << EOF
[oneAPI]
name=Intel(R) oneAPI repository
baseurl=https://yum.repos.intel.com/oneapi
enabled=1

sean-smith

Install Spack on AWS ParallelCluster

1. Create a File spack.sh
2. Upload to S3:

aws s3 cp --acl public-read spack.sh s3://[bucket]

3. Include in your config file"

[cluster mycluster]