MATLAB Parallel Computing Hands-On Workshop

Instructor: Sam Marshalik (MathWorks)

Helper: Reece Teramoto (MathWorks)

During this hands-on workshop, MathWorks engineers will introduce you to parallel and distributed computing in MATLAB with a focus on speeding up your application code and offloading compute. By working through common scenarios and workflows using hands-on demos, you will gain an understanding of the parallel constructs in MATLAB, their capabilities, and some of the common hurdles that you’ll encounter when using them. You’ll also learn how to run your MATLAB code on Compute Canada resources.

You can download the course materials as a ZIP file (will be available closer to the date of the course).

Target audience: Anyone interested in learning more about speedup and parallelizing their MATLAB code.

Course plan:

  1. Speeding up programs with parallel computing
  2. Offloading computations and cluster computing
  3. Working with large data sets
  4. GPU Computing
  5. Running MATLAB on Compute Canada Cedar/Graham resources

Duration: 3 hours

Level: beginner

Prerequisites: Taking the self-paced MATLAB Onramp course (2 hours) is recommended. The course can be accessed for free.

Also, we expect all attendees to have a working knowledge of cluster (high-performance computing) environment: how to prepare and to submit jobs with Slurm, how to view job output, best practices on the login nodes and with parallel filesystems, etc. If you are new to cluster workflows, please consider attending the Introduction to HPC session.

Laptop software: