The workshop will consist of one day course in which attendees will be introduced to how to submit parallel computing jobs with MATLAB on CINECA pre-exascale HPC cluster Leonardo to solve compute- and data-intensive problems using its multicore processors and GPUs. In the form of hands-on workshop, attendees will learn how to access Leonardo, configure and submit MATLAB jobs and fetch results using MATLAB. By working through common scenarios to parallelize MATLAB algorithms, attendees will gain an understanding of parallel computing with MATLAB on HPC clusters and learn about best practices.

Both admitted and non admitted participants will be notified via email before October 25th 2024

Skills:

· Optimizing your MATLAB code by utilizing multiple cores
· Scaling up your computations: GPU and Cluster computing
· Working with big data in MATLAB
· Accessing MATLAB on CINECA Leonardo HPC Cluster
· Moving/submitting jobs from your local machine to the CINECA Leonardo HPC Cluster
· Parallel Cluster configuration via local MATLAB GUI
· Remote access to HPC systems and job submission via local MATLAB GUI

Target audience:

The course is aimed at scientific university students, as well as PhD students and researchers. In principle, anyone who meets the required prerequisites can send a request to participate. MATLAB beginners Advanced computing beginners Master of Science and PHD students, and PHD researchers Postdocs and other scientists

Pre-requisites:

University student (or higher) in a scientific domain Beginner, intermediate or higher-level expertise in MATLAB parallel computing

Affiliation at least to one italian institute.

Good knowledge of English

Mandatory!!

Attendees need to bring their own laptop with following programs installed
· One of the following MATLAB releases: R2022b,R2023a,R2023b,R2024a,2024b
· Parallel Computing Toolbox

Attendees who are working with currently using/planning to use the CINECA HPC clusters for their research, are encouraged to bring examples of their code for consultation with MathWorks experts.

About the presenter:

Raymond Norris is an Application Engineer Manager who has worked at MathWorks for over 30 years and leads a team of engineers to integrate MathWorks parallel tools with end-users' HPC cluster and cloud environments as well as gives talks and workshops focused on parallelization of MATLAB. Raymond holds a B.S. in computer science and applied mathematics from the University of Massachusetts Boston and an M.S. in software engineering from Brandeis University.

Criteria for selection:

The number of participants for this workshop is limited to 40 students. Applicants will be selected according to their experience, qualifications and scientific interest BASED ON WHAT WRITTEN IN THE REGISTRATION FORM.

Approved participants will have to confirm their attendance within 3 days from the notification, without which the admittance will be cancelled.