We offer assistance with usage of compute clusters, such as how to access the systems, using or compiling your software, and how to run your programs in the most efficient way.
High-performance computing
High-performance computing (HPC) is a powerful tool in today’s research and allows for large-scale computations of complex systems, for big data analysis, or for data visualization. To achieve this, HPC systems have thousands of processors, multiple GPUs, hundreds of gigabytes of memory, and terabytes of storage available.
Parallel computing
When writing a program, by default it will be a serial program. This means a single CPU core is used. However, most computers and, in particular, HPC clusters will have multiple cores available. To access the multiple CPUs, your program needs to be designed as a parallel program. This allows it to use many CPU cores simultaneously and this cuts down processing time substantially.
AI/machine learning
Using a grant provided by Compute Ontario, the University of Ottawa has created a series of notebooks to teach about using AI and machine learning for your research. They also explain research data management for your input and output data. These notebooks work on their own and are also frequently presented through our seminar series.
Resources
Each consortium has their own specific cluster documentation page.
Consortium | Documentation |
---|---|
ACENET | http://www.ace-net.ca/wiki |
CAC | http://cac.queensu.ca/wiki |
Calcul Québec | https://wiki.calculquebec.ca |
SciNet | https://wiki.scinet.utoronto.ca |
General documentation is available on the Digital Research Alliance of Canada at https://docs.alliancecan.ca/wiki/Technical_documentation
Seminars
Additional resources
Compute Ontario offers virtual weekly informational series hosted on Zoom on a wide range of Digital Research Infrastructure (DRI) topics such as advanced research computing (ARC), research data management (RDM), and research software (RS).
Discover Compute Ontario Colloquia series