Skip to main content

Recently Updated Pages

Allowed directories for users software installations

Software User Software Installation

There are a few options for local users installation locations as showed on the next table, creat...

Updated 1 month ago by Jorge Gomes

Software List

Software

List of software centrally available via the modules tool at the Cirrus HPC and HTC clusters as o...

Updated 1 month ago by Jorge Gomes

Software Management

Software

The Cirrus software is managed using a tool called modules. This tool allows the user to load the...

Updated 1 month ago by Jorge Gomes

Cirrus nodes and specs

Compute Node Specs and Information

The list of server class types available to general users in the Cirrus HPC/HTC clusters. CNCA-L...

Updated 1 month ago by Jorge Gomes

How to Run a Job with a GPU

Manage jobs GPU user guide

Let's run the gravitational N-body simulation found on the CUDA toolkit samples on a GPU. This ex...

Updated 1 month ago by Jorge Gomes

My jobs need to run longer than the queues permit

Manage jobs Troubleshooting information

At Cirrus the default max elapsed time for the queues is 72h. The values for all queues can be...

Updated 1 month ago by Jorge Gomes

Quality of Service (QOS)

Manage jobs

Quality of Service (QoS) is used to limite the characteristics that a job can have. Default QOS p...

Updated 1 month ago by Jorge Gomes

UDocker Containers

Manage jobs

Availability of udocker containers directly on CVMFS read-only filesystem in order to speedup the...

Updated 1 month ago by Jorge Gomes

Deep Learning Example

Manage jobs GPU user guide

The Cirrus-A facility provides several GPUs, check the Compute Node Specs page. Login on the subm...

Updated 1 month ago by Jorge Gomes

Use QOS to run GPU jobs

Manage jobs GPU user guide

This page it's dedicate to users who want to run GPU's and have a QOS. GPU JOB submission using...

Updated 1 month ago by Jorge Gomes

How to run parallel job's with srun

Manage jobs Manage slurm jobs

srun : Used to submit/initiate job or job step Typically, srun is invoked from a SLURM job scrip...

Updated 1 month ago by Jorge Gomes

Use of user QOS for CPU jobs

Manage jobs Manage slurm jobs

In order to use QOS you will to have an assigned user QOS. In the following example the user will...

Updated 1 month ago by Jorge Gomes

Start here

Manage jobs

Cluster specific information CNCA provides acess to several HPC computing clusters. The policies,...

Updated 1 month ago by Jorge Gomes

Directories and filesystems

Filesystem User Guide

The Cirrus filesystems are based on the Lustre shared filesystem which is mounted in the compute ...

Updated 1 month ago by Jorge Gomes

Disk Quota Policy

Filesystem User Guide

To prevent storage misuse and problems resulting from filesystems becoming full, Cirrus has imple...

Updated 1 month ago by Jorge Gomes

How to transfer files between Cirrus and a local machine

Filesystem User Guide

NOTE Please note that the Cirrus Lustre storage is not designed for small files. Attempting to s...

Updated 1 month ago by Jorge Gomes

How to access files belonging to someone else or another project

Filesystem User Guide

Users are allowed to change the default permissions file permissions in all folders they own. The...

Updated 1 month ago by Jorge Gomes

Access

Getting Started

CNCA is open to all academic and scientific researchers and institutions. In order to use our ser...

Updated 1 month ago by Jorge Gomes

Enable access to a remote host

How to login Using ssh keys

In most cases you will not need to add your own SSH public key to other CNCA remote hosts as ther...

Updated 1 month ago by Jorge Gomes

Using SSH tunnels

How to login Using ssh keys

In some cases you may need to access remote hosts that have private IP addresses or are protected...

Updated 1 month ago by Jorge Gomes