Getting started

Any qualified researcher at a Canadian University is eligible to use SciNet’s Niagara supercomputer and related systems for free. The students, postdocs, and external collaborators of the qualified researcher can then also get an account. Note that there are no ‘group’ login accounts, and each individual should have their own login credentials.

To get access, one must first obtain a Digital Research Alliance of Canada (formerly Compute Canada) account on the CCDB system. The PI (Principle Investigator, a faculty member) of a group first applies for their account on CCDB, after which group members can request accounts sponsored by the PI.

Here is a synopsis of the account application process:

1. [STEP 1] If you do not have a Digital Research Alliance of Canada CCDB account: get one as explained in the Apply for an Account page.
2. [STEP 2] Make sure you setup multifactor authentication: see this Wiki page page on how to set it up for your CCDB account.
3. [STEP 3] Opt in to Niagara and Mist service: to enable your access to SciNet systems (including the Niagara supercomputer and the Mist GPU Cluster), click the “join” button on the CCDB opt-in page. You should receive an email within one or two days confirming that access has been granted. Usage of these systems is subject to the SciNet Acceptable usage policy.
4. [STEP 4] create an SSH key pair: upload the public key to CCDB and use the private key to login. Details of setting up SSH key authentication on Niagara are described on the SSH Keys page on the Alliance documentation site.

Note that accounts are subjects to default limits, but those users with especially large resource requirements may apply for more resources in the annual national Resource Allocation Competition (RAC).

The SciNet Scientific and Technical Advisory Committee has set the following conditions of use for SciNet facilities.  Accessing SciNet systems implies that you accept these conditions.

1. I am responsible for all activities associated with my account.
2. I will not share my account with another person.
3. I will use my account and allocation(s) exclusively for the purposes and program(s)/project(s) for which they have been approved. SciNet resources are not to be used for instructional or administrative purposes.
4. I will be fair and considerate of others in my use of the resources.
5. If requested, I will show evidence of the parallel and/or serial efficiency of my codes. I understand that SciNet staff may reduce my scheduling priority if I am not using resources efficiently.
6. When requested, I will provide data for reporting to the SciNet funding agencies in a timely manner.
7. I understand that use of the SciNet systems may be monitored and recorded.
8. I will not use my account for illegal or unsanctioned activities including, but not limited to, software piracy, spam, profit-making, and harassment.

SciNet reserves the right to take whatever actions are necessary to identify and resolve suspected abuse. For cases not covered by this Usage Policy the computing policies in effect at your home institution will apply. Failure to abide by these conditions may result in loss of access to SciNet facilities. If you have a question about these conditions, please contact us at support@scinet.utoronto.ca.

In publications

When submitting a publication based on results from SciNet computations, we ask that you use the following line in the acknowledgements:

Computations were performed on the [system name] supercomputer at the SciNet HPC Consortium. SciNet is funded by Innovation, Science and Economic Development Canada; the Digital Research Alliance of Canada; the Ontario Research Fund: Research Excellence; and the University of Toronto.

(replace [system name] with the appropriate system, e.g. Niagara, Mist, Rouge, …)

Also please cite the Niagara deployment paper:

M. Ponce et al. 2019, “Deploying a Top-100 Supercomputer for Large Parallel Workloads: the Niagara Supercomputer”, PEARC’19 Proceedings doi: (10.1145/3332186.3332195)

and the SciNet datacentre paper:

Chris Loken et al. 2010, “SciNet: Lessons Learned from Building a Power-efficient Top-20 System and Data Centre”, J. Phys.: Conf. Ser. 256 012026 doi: (10.1088/1742-6596/256/1/012026)

This helps us automatically track publications that use SciNet. Such publications are are both useful evidence of scientific merit for future resource allocations for you the user, and help us demonstrate the importance of computational resources such as SciNet to our funding partners. Also please feel free to email details of any such publications, along with PDF preprints, to support@scinet.utoronto.ca.

In talks

Please feel free to use the logos below, and images of Niagara, Mist, and the data centre, in any talks you give.