Skip to main content

Introduction to MCMeSU

This page should help you to get a better understanding of the machine you are going to use.
Make sure to fully understand the first sections in order to be able to follow the walkthrough in the “Guide” section.

A note on parallel computing: Newcomers unfamiliar with the basis of parallel computing are invited to consult the excellent LLNL tutorial on the subject, as well as an explanation of the differences between the two main programming methods used in parallel computing: OpenMP & MPI.

System Overview​

Schema mesu

MCMeSU supercomputer architecture is more complex than a personal computer. It is made of different kinds of servers (aka nodes) - login nodes and computing nodes - which communicate together via a specific program called a batch scheduler.

The main steps for performing a computation on MCMeSU are :

  • Log in to the login node,
  • Send your data and your script,
  • Prepare your environment by loading the necessary module(s),
  • Create a SLURM submission script,
  • Submit your job using SLURM,
  • Monitor your job,
  • Retrieve your results.

Login Nodes​

In order to run a program on a computing resource, you will have to first log into the login nodes. Login nodes are dedicated and separate small servers which act as a secure gateway between your computer and the computing nodes, on which your program will be running.

Note: login nodes are not meant for heavy computation, any CPU-intensive process running on them will be automatically killed.

The login nodes are dedicated to the following tasks:

  • Transferring files from/to your personal computer,
  • Compiling your source code,
  • Setting up your jobs’ parameters and variables,
  • Monitoring the execution of your jobs.

Software Modules​

Modules are a system used to dynamically modify a user's environment. On MCMeSU, modules allow you to load and manage different software packages and their dependencies without causing conflicts. By loading a module, you set up your environment with the necessary paths, variables, and configurations required for that software. This ensures that the correct versions of the software and libraries are used for your calculations.

Proper use of modules helps streamline the workflow and ensures compatibility and reproducibility in your computational tasks.

Computing Nodes​

Computing nodes constitute the core of the supercomputer.

Your jobs will run on those nodes, and will be submitted, managed and monitored with the batch scheduler.

Data Directories​

Different filesystems are mounted on MCMeSU supercomputer. When logged in, you have access to your HOME directory, which is meant to host your codes, programs, and allows you to submit jobs. This directory is not meant for large data storage, and is limited to 100 GB per user. Datasets used during computation must be stored in your SCRATCH directory. This directory resides in a high-performance storage system where users have no usage quota. Datasets that you want to keep after computation should be stored in your STORE directory.

SLURM - The Batch Scheduler​

A batch scheduler is a very specific software managing all users' jobs submissions in order to prioritize and allocate resources for every of them.
Acting as a gateway between the login nodes and the computing nodes, its role is to optimize the cluster utilization according to the stack of pending jobs, and their requested resources (execution time, number of CPUs, maximum memory...).
The batch scheduler used on MCMeSU is called Slurm.