Getting started
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 Apply for an account.
What do you want to do?
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 connect to our HPC systems.
- read an introduction to using Linux systems.
- read about how to transfer files to and from our systems.
- look for a training event on this schedule
- 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
- 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 Cloud resource
For any other questions, you might try the Search box in the upper right corner of this page, the main page of technical documentation, or contact us by email.
What resources are available?
Compute Canada is currently installing several million dollars’ worth of new computers while simultaneously retiring many old computers. During the transition period (2016-2018), a changing mix of old and new computers will be available to you. You can read about the progress of the migration from old to new systems here.
New resources (deployed in 2016 or after)
Compute Canada has begun to renew its infrastructure starting in 2016. The first phase of the new deployment is composed of four new clusters, currently called GP1, GP2, GP3 and LP. While the details are still subject to change, GP1 will be an extension of the existing West Cloud, GP2 and GP3 will be general purpose clusters composed of a variety of nodes including large memory nodes and nodes with accelerators, and LP will be a large parallel cluster with nodes interconnected by a fast network.
Legacy resources (deployed before 2016)
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 ACENET, the Centre for Advanced Computing, Calcul Québec, http://www.scinethpc.ca/ SciNet], SHARCNET, and WestGrid. To use a legacy resource you must have an account with one of these entities, which you can do through this page. Resources deployed during and after 2016 will not require this step, nor do the two clouds.
Most legacy clusters are classified as either capacity clusters or capability clusters. Capacity clusters contain nodes connected to each other by a relatively slow Ethernet network, while the capability clusters have a fast network, usually InfiniBand. Large parallel jobs will run better on capability clusters than capacity clusters, while smaller jobs will run almost anywhere.
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:
- Hungabee hosted by WestGrid
- M9000 hosted by the Centre for Advanced Computing
- Guillimin-ScaleMP hosted by Calcul Québec
- Fortier hosted by SHARCNET
Compute Canada also has clusters equipped with accelerators such as GPUs and Intel Xeon Phis. If your application benefits from such accelerators, you will find them on the following legacy systems:
- Helios, Hades and Guillimin, hosted by Calcul Québec
- Parallel, hosted by WestGrid
- Angel and Monk, hosted by SHARCNET
- Accelerator Research Cluster, hosted by SciNet
All of these have NVidia GPUs. Guillimin also has Intel Xeon Phis.
Finally, Compute Canada also hosts two clouds called East Cloud and West Cloud, as well as storage resources ranging from fast parallel filesystems to tape backup.
"What resources should I use?"
This question is hard to answer because of the range of needs Compute Canada serves, and because of the enormous variety of resources we have available --- especially during the 2016-2018 renewal period. If the descriptions above are insufficient, contact Compute Canada’s technical support or your regional support.
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:
- What software do you want to use?
- 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?
- Can it run on the Linux operating system?
- How much memory, time, computing power, accelerators, storage, network bandwidth and so forth --- are required by a typical job? Rough estimates are fine.
- How frequently will you need to run this kind of job?
You may know the answer to these questions or not. If you do not, our technical support team is there to help you find the answers. Then they will be able to direct you to the most appropriate resources for your needs.