Getting started/en: Difference between revisions

You have just received your Compute Canada account. Welcome! Now what do you do? This guide is intended to help you find your way into the technical documentation for Compute Canada’s services and systems.  

If you want to know how to get a Compute Canada account, see [https://www.computecanada.ca/research-portal/account-management/apply-for-an-account/ Apply for an account].

If you  

* are already an experienced HPC user and are ready to log on to a cluster, skip to the next section, "What resources are available?"

* would like some training, you can

** read about how to [[SSH|connect]] to our HPC systems.

** read an introduction to using [[Linux introduction|Linux]] systems.

** read about how to [[Transferring files|transfer files]] to and from our systems.

** look for a training event on [https://www.computecanada.ca/calendar/ this schedule]

<!-- ** Online training materials are here -->

* want to know what software and hardware is available for various disciplines, we are planning a series of discipline guides, but the only one available yet is on

** [[Visualization]]

* have hundreds of gigabytes of data to move across the network, read about [[Globus]] file transfer services

* want to experiment with software that doesn’t run well on our HPC systems, you should read about the [[CC-Cloud|Cloud resource]]

For any other questions, you might try the Search box in the upper right corner of this page, the [[Compute Canada Documentation|main page]] of technical documentation, or [[Technical support|contact us]] by email.

Compute Canada has begun to renew its infrastructure starting in 2016. The first phase of the new deployment is composed of four new clusters, called Arbutus (GP1), Cedar (GP2), Graham (GP3) and Niagara (LP). Arbutus, an extension of West cloud, has all its additional compute nodes install and is awaiting some additional storage. While the [https://www.computecanada.ca/research-portal/accessing-resources/migration/ details] are still subject to change Cedar (GP2) and Graham (GP3) will be general purpose clusters composed of a variety of nodes including large memory nodes and nodes with accelerators, and Niagra (LP) will be a large parallel cluster with nodes interconnected by a fast network.

[https://www.computecanada.ca/research-portal/national-services/compute/ Computing resources] which were installed between 2004 and 2015 and are scheduled to be decommissioned in the next few years are referred to as ''legacy resources''. The legacy resources are administered by regional organizations, one of [http://www.ace-net.ca/ ACENET], [http://cac.queensu.ca/ the Centre for Advanced Computing], [http://www.calculquebec.ca/en/ Calcul Québec], [http://www.scinethpc.ca/ SciNet], [https://www.sharcnet.ca/my/front/ SHARCNET], and [https://www.westgrid.ca/ WestGrid]. To use a legacy resource you must have an account with one of these entities, which you can do through [https://ccdb.computecanada.ca/me/facilities this page]. Resources deployed during and after 2016 will not require this step, nor do the two [[CC-Cloud|clouds]].  

There are some specialty clusters among the legacy resources. Applications which require more than 512 GB or memory per node require ''large shared memory systems''. Compute Canada has four such systems:

Compute Canada also has clusters equipped with accelerators such as [https://en.wikipedia.org/wiki/General-purpose_computing_on_graphics_processing_units GPUs] and Intel [https://en.wikipedia.org/wiki/Xeon_Phi Xeon Phis]. If your application benefits from such accelerators, you will find them on the following legacy systems:

=="What resources should I use?"==

In order to identify the best resource to use, we may ask many questions about what you want to do. Such questions will probably include:

** Does it require a commercial license?

** Can it be used in a non-interactive fashion? That is, can the software’s execution be controlled from a file which is prepared prior to its execution rather than through the use of a graphical interface?  

* How frequently will you need to run this kind of job?