This page was translated by an AI (LLM) with a cursory human check and is awaiting full review.
Introduction to the PETSc library
Manager : Serge Van Criekingen
Instructors : Rémi Lacroix, Dimitri Lecas, Serge Van Criekingen
Objectives
- Learn the basics needed to get started with the PETSc library (Portable, Extensible Toolkit for Scientific Computation)
- Familiarise yourself with PETSc's online documentation
- Be able to build and solve simple examples of partial differential equations
- Be able to use and compare different solution methods on these examples, on CPU and GPU
- Be ready to deepen your knowledge of PETSc features useful for your application
- Target audience
- Prerequisites
- Duration and practical info
- Course content
- Course materials
- Upcoming sessions
Prerequisites
- Basic knowledge of Linux and a text editor.
- Knowledge and use of Fortran or C languages.
- Basic notions of linear algebra and the MPI parallel programming standard.
Duration and practical info
This training lasts 2 days:
- from 09:30 to 12:30 and
- from 13:30 to 17:30.
It takes place exclusively in-person at the premises ofIDRIS in Orsay (91).
Attendance
Minimum : 8 people ;
Maximum : 20 people.
Course content
The course offers an alternation of lectures (~7h) and practical work (~7h).
- Introduction: description of the PETSc ecosystem and its main components
- Vectors: definition of different vector types, operations and access (with notions of efficiency)
- Matrices: definition of different types, operations, pre-allocation
- Solvers: overview of the different accessible solution methods, application to the case of the two-dimensional Laplacian, execution on a CPU or GPU node of the Jean Zay supercomputer
- Complements: profiling and debugging tools specific to PETSc, overview of the potential for automatic management of structured meshes (DMDA)
For an efficient execution of the practical parts, these will take place on the Jean Zay supercomputer. A workstation with access to the IDRIS supercomputer is provided to the learners. Experience in using a supercomputer, as well as prior access to it, are not required.
Course materials
All course materials, including slides, notes, and practical exercises, are provided under the following license: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). For more details on the license, please consult this page.
To view the dates of the upcoming sessions for this training, go to the following page:
Registration
CNRS/French university staff | External participants |
Are you a member of CNRS or a French university? Your registration is free via our server. | Our training courses are aimed at all professionals from companies, public bodies and individuals. |