Getting Started

In order to use Research Computing resources, you'll need to get an RC account. You may also need to get a compute time allocation, or permission to access other resources you want to use.

This getting-started guide will help guide you through these first few steps toward using RC resources, based on your particular needs. More information is available in the User Guide, and links to more documentation will be provided throughout this process.

If, at any time, you are unsure how to proceed, please contact us at rc-help@colorado.edu. Your feedback will help us make this getting-started guide, and the rest of our documentation, better!

Get an account

Again, the first thing that every prospective Research Computing user must do is get an account. This process is dependent on your current affiliation.

If you already have an RC account, skip ahead to "Get access to resources." Otherwise, select from the following list:

I am affiliated with CU-Boulder or already have a CU-Boulder "IdentiKey" account.
If you already have a CU-Boulder account, you can directly request an RC account and 2-factor authentication.
I am affiliated with another institution and am collaborating with a CU-Boulder researcher.
You can access CU and RC resources through the CU sponsored affiliate program.

All users of Research Computing resources are responsible for complying with all university policies, including (but not limited to) those defined at http://oit.colorado.edu/policies/cu-boulder-it-policies.

Get access to resources

Once you have an RC account, you can request access to RC resources, or access resources that you are already authorized to use.

All RC users have access to the RC login environment, so you're welcome to start there. If you want to do any actual computation, or store any significant quantity of data, you'll need to get access to one of the more specialized Research Computing resources.

I want to run compute applications on the shared infrastructure.
The Summit Supercomputer, The Janus HPC cluster, Crestone bladecenter, GP-GPU nodes, large-memory nodes, and other compute resources are available to the RC community.
I want to purchase dedicated nodes in the Research Computing condo, or use condo nodes already purchased.
Dedicated nodes may be purchased as part of the Blanca condo cluster.
I want to purchase storage space in the PetaLibrary, or store or access data in an existing PetaLibrary allocation.
The PetaLibrary Active and PetaLibrary Archive storage services can be used to store data for compute or long-term storage.

Getting started as a CU-Boulder user

Users with an existing CU-Boulder account can use their IdentiKey credentials to request a Research Computing account using the RC Account Request portal, and once the account is created will authenticate to the RC environment using 2-factor authentication.

Complete the account request form

Visit the RC Account Request portal to complete the account request form. Choose your reason for requesting an account (this helps us guide you later) and Select "University of Colorado - Boulder" as your affiliation, and authenticate using your CU IdentiKey credentials (i.e., your UCB username and password) to complete your account request. After review, your account will be created by a member of the Research Computing staff and further details will be provided to you by email.

Set-up two-factor authentication

Access to Research Computing resources requires two-factor authentication. Request smartphone-based Duo access or a Vasco physical one-time-password (OTP) generator device by either

Be prepared to show your BuffOne card or other state-issued ID as part of the identity-confirmation process when you pick up your authenticator.

If you're using Duo, you'll receive credential registration instructions along with your invite.

If you're using the Vasco OTP authenticator (not the Duo Smartphone app) register it at the OTP Self Service portal, and verify that it works by following the instructions on the OTP Login Test page.

Next steps

Now that you have an RC account, you're ready to get started with the specific RC resources that you're interested in using.

Getting started as an external CU-Boulder user

People collaborating with CU-Boulder researchers may access RC resources, but must first obtain a CU-Boulder sponsored affiliate account. After that point, the process of getting an RC account is the same as for an internal CU-Boulder user.

Get a CU-Boulder sponsored affiliate account

The CU-Boulder faculty or staff member that you are collaborating with must apply for your sponsored account as your account sponsor by sending the required information to help@colorado.edu.

When your account request has been processed and approved, you will receive login details for your account, including your new CU username and IdentiKey password. You will use these credentials to apply for an RC account.

Complete the RC account request form

Visit the RC Account Request portal to complete the account reqeust form. Select "University of Colorado - Boulder" as your affiliation, and provide your CU IdentiKey credentials (i.e., your username and password) to complete the rest of the form. After review, your account will be created by a member of the Research Computing staff, and login details will be provided to you by email.

Set-up two-factor authentication

Access to Research Computing resources requires two-factor authentication. Request smartphone-based Duo access or a Vasco physical one-time-password (OTP) generator by either

Be prepared to show your BuffOne card or other state-issued ID as part of the identity-confirmation process when you pick up your authenticator.

If you're using Duo, you'll receive credential registration instructions along with your invite.

If you're using the Vasco OTP authenticator (not the Duo Smartphone app) register it at the OTP Self Service portal, and verify that it works by following the instructions on the OTP Login Test page.

Next steps

Now that you have an RC account, you're ready to get started with the specific RC resources that you're interested in using.

Getting started with a new PetaLibrary allocation

The PetaLibrary is a National Science Foundation-subsidized service for the storage, archival, and sharing of research data, housed in the Space Sciences data center at CU-Boulder. It provides both active (disk) and archive (disk+tape HSM) storage for a modest fee to any US-based researcher affiliated with the University of Colorado Boulder, and supports Globus / GridFTP for convenient high-performance data transfer into and out of the PetaLibrary.

Complete the End User Agreement and Order Form

Complete the PetaLibrary End User Agreement, part of the PetaLibrary Memorandum of Understanding. Also complete the included order form, and send both to rc-help@colorado.edu.

Once your order has been processed, your storage will be made available as part of the greater Research Computing filesystem hierarchy, and the path to your allocated storage will be provided to you. This path will be accessible from most Research Computing resources, including Janus and the login nodes.

Get a globus account

Sign up for an account at Globus.org, the recommended high-performance mechanism for transferring data in and out of the PetaLibraty. Once you have a Globus.org account, you can (optionally) associate your CU IdentiKey with your account: from the SignIn page, follow the "alternate login" link and select "InCommon" from the available choices.

Install Globus Connect

Download and install Globus Connect Personal, which serves as a Globus endpoint on your local workstation. (Globus Connect is available for Mac Os X, Linux, and Windows.)

With Globus Connect running, you can transfer data between your local workstation (e.g., your laptop or desktop) and The PetaLibrary using the globus.org web interface.

  1. Log in to Globus.org
  2. Use the Manage Endpoints interface to “add Globus Connect Personal” as an endpoint. (More information at Globus.org support.)
  3. Transfer Files, using your new workstation endpoint for one side of the transfer, the Research Computing endpoint (colorado#gridftp) for the other side. (You will be required to authenticate to the Research Computing endpoint using your RC account and OTP.)

Next steps

Now that you can access your PetaLibrary storage and transfer files, you may want to read a bit more from the User Guide.

Getting started with a new Research Computing Condo purchase

Research Computing maintains a Condo Computing service that offers researchers the opportunity to purchase and own compute nodes that will be operated as part of a cluster, named “Blanca.” The aggregate cluster is made available to all condo partners while maintaining priority for the owner of each node.

Purchase nodes in the Research Computing condo

Contact us at rc-help@colorado.edu if you are interested in purchasing nodes in the Research Computing condo cluster "Blanca." Visit our user guide for details on available node configurations, including a general-purpose compute node, a GPU-enabled node, and a high-memory node.

Once your nodes have been purchased and installed by Research Computing staff, you will be provided with a list of hostnames, as well as the name of a dedicated Slurm QOS that you can use to submit compute jobs to your nodes.

Log in

Access to Research Computing resources is primarily provided using the secure shell (SSH) protocol. The ssh command can be run from the Linux and OS X command-line. For Windows clients we recommend the PuTTY application, though alternatives exist.

ssh -l $rc_username login.rc.colorado.edu

When you're prompted for a password, do not enter a CU IdentiKey password. Most users should have already obtained an OTP authenticator device, in which case your RC "password" is the combination of your PIN and the one-time password generated by your OTP token.

password: 

If you are an NCAR user, authenticate using your NCAR Yubikey or CryptoCard.

Submit jobs to the queue

Research Computing uses a queueing system called Slurm to manage compute jobs on compute resources, including Blanca. In general, you'll submit compute jobs (in the form of job scripts) to the system using the sbatch command.

$ echo >test-job.sh '#!/bin/bash
#SBATCH --job-name test-job
#SBATCH --time 05:00
#SBATCH --nodes 1
#SBATCH --output test-job.out

echo "The job has begun."
echo "Wait one minute..."
sleep 60
echo "Wait a second minute..."
sleep 60
echo "Wait a third minute..."
sleep 60
echo "Enough waiting: job completed."'

$ module load slurm/blanca
$ sbatch test-job.sh

You can monitor the progress of your job in the queue using the squeue command.

$ squeue --user $USER

Once your job has completed (denoted by the CG state) you can find the output in the test-job.out file, as defined in the test-job.sh script.

$ cat test-job.out

Next steps

Now that you can log into the Research Computing environment and submit jobs to the queueing system, you may want to read a bit more from the User Guide.

Getting started with an existing PetaLibrary allocation

The PetaLibrary is a National Science Foundation-subsidized service for the storage, archival, and sharing of research data, housed in the Space Sciences data center at CU-Boulder. It provides both active (disk) and archive (disk+tape HSM) storage for a modest fee to any US-based researcher affiliated with the University of Colorado Boulder, and supports Globus / GridFTP for convenient high-performance data transfer into and out of the PetaLibrary.

Complete the End User Agreement, request access

Access to the PetaLibrary is moderated by an End User Agreement, included as APPENDIX A in the PetaLibrary Memorandum of Understanding. Complete this form and the Order Form (APPENDIX B), and send them both to rc-help@colorado.edu.

Have the PetaLibrary allocation owner contact rc-help@colorado.edu to grant you access.

Get a Globus account

Sign up for an account at Globus.org, the recommended high-performance mechanism for transferring data in and out of the PetaLibraty. Once you have a Globus.org account, you can (optionally) associate your CU IdentiKey with your account: from the SignIn page, follow the "alternate login" link and select "InCommon" from the available choices.

Install Globus Connect

Download and install Globus Connect Personal, which serves as a Globus endpoint on your local workstation. (Globus Connect is available for Mac Os X, Linux, and Windows.)

With Globus Connect running, you can transfer data between your local workstation (e.g., your laptop or desktop) and The PetaLibrary using the globus.org web interface.

  1. Log in to Globus.org
  2. Use the Manage Endpoints interface to “add Globus Connect Personal” as an endpoint. (More information at Globus.org support.)
  3. Transfer Files, using your new workstation endpoint for one side of the transfer, the Research Computing endpoint (colorado#gridftp) for the other side. (You will be required to authenticate to the Research Computing endpoint using your RC account and OTP.)

Next steps

Now that you can access your PetaLibrary storage and transfer files, you may want to read a bit more from the User Guide.

Getting started with existing Research Computing condo nodes

Research Computing maintains a Condo Computing service that offers researchers the opportunity to purchase and own compute nodes that will be operated as part of a cluster, named “Blanca.” The aggregate cluster is made available to all condo partners while maintaining priority for the owner of each node.

Log in

Access to Research Computing resources is primarily provided using the secure shell (SSH) protocol. The ssh command can be run from the Linux and OS X command-line. For Windows clients we recommend the PuTTY application, though alternatives exist.

ssh -l $rc_username login.rc.colorado.edu

When you're prompted for a password, do not enter a CU IdentiKey password. Most users should have already obtained an OTP authenticator device, in which case your RC "password" is the combination of your PIN and the one-time password generated by your OTP token.

password: 

If you are an NCAR user, authenticate using your NCAR Yubikey or CryptoCard.

Submit jobs to the queue

Research Computing uses a queueing system called Slurm to manage compute jobs on compute resources, including Blanca. In general, you'll submit compute jobs (in the form of job scripts) to the system using the sbatch command.

$ echo >test-job.sh '#!/bin/bash
#SBATCH --job-name test-job
#SBATCH --time 05:00
#SBATCH --nodes 1
#SBATCH --output test-job.out

echo "The job has begun."
echo "Wait one minute..."
sleep 60
echo "Wait a second minute..."
sleep 60
echo "Wait a third minute..."
sleep 60
echo "Enough waiting: job completed."'

$ module load slurm/blanca
$ sbatch test-job.sh

You can monitor the progress of your job in the queue using the squeue command.

$ squeue --user $USER

Once your job has completed (denoted by the CG state) you can find the output in the test-job.out file, as defined in the test-job.sh script.

$ cat test-job.out

Next steps

Now that you can log into the Research Computing environment and submit jobs to the queueing system, you may want to read a bit more from the User Guide.

Getting started with the shared computing environment

Research computing maintains a shared computing infrastructure for the RC user community, including the Janus HPC cluster, Crestone bladecenter, GP-GPU nodes, and large-memory nodes. Accessing these resources involves getting access to a compute allocation, logging in using SSH, and submitting jobs to the queueing system.

Request access to a compute allocation

A PI with an active allocations can contact us at rc-help@colorado.edu to request that you be added to it.

Request access to a general account if you are just getting started with Research Computing, and need some time to explore the capabilities of the system. Contact us at rc-help@colorado.edu to request that you be added to it.

If you're already comfortable with high-performance computing and know that you will need more compute time than is given with a startup allocation, please email rc-help@colorado.edu for allocation request or management questions during this transition to Summit.

In each case you will receive an allocation ID that is associated with a consumable allocation of compute time, measured in SU or core-hours. You can use this allocation ID when submitting compute jobs to the queueing system.

Log in

Access to Research Computing resources is primarily provided using the secure shell (SSH) protocol. The ssh command can be run from the Linux and OS X command-line. For Windows clients we recommend the PuTTY application, though alternatives exist.

ssh -l $rc_username login.rc.colorado.edu

When you're prompted for a password, do not enter a CU IdentiKey password. Most users should have already obtained an OTP authenticator device, in which case your RC "password" is the combination of your PIN and the one-time password generated by your OTP token.

password: 

If you are an NCAR user, authenticate using your NCAR Yubikey or CryptoCard.

Submit jobs to the queue

Research Computing uses a queueing system called Slurm to manage compute resources and to schedule jobs that use them. In general, you'll submit compute jobs (in the form of job scripts) to the system using the sbatch command.

$ echo >test-job.sh '#!/bin/bash
#SBATCH --job-name test-job
#SBATCH --time 05:00
#SBATCH --nodes 1
#SBATCH --output test-job.out

echo "The job has begun."
echo "Wait one minute..."
sleep 60
echo "Wait a second minute..."
sleep 60
echo "Wait a third minute..."
sleep 60
echo "Enough waiting: job completed."'

$ module load slurm
$ sbatch --qos janus-debug test-job.sh

You can monitor the progress of your job in the queue using the squeue command.

$ squeue --user $USER

Once your job has completed (denoted by the CG state) you can find the output in the test-job.out file, as defined in the test-job.sh script.

$ cat test-job.out

Next steps

Now that you can log into the Research Computing environment and submit jobs to the queueing system, you may want to read a bit more from the User Guide.