Master’s in High Performance Computing (HPC)
- Course duration : Two years
- Language of instruction : English
- Diplomas delivered : Master in Computer science or Mathematics (Sorbonne Université) and potentially a second Master’s degree from one of the partner universities (option 2 : EUMaster4HPC)
- Course locations : Sorbonne Université, France and for option 2 EUMaster4HPC either Bulgaria, Germany, Italy, Luxemburg, Spain, Switzerland or Sweden
High Performance Computing plays a major role in scientific research and industrial innovation. The architecture of large scale computers is evolving rapidly and is becoming more and more complex. These computers are formed by heterogeneous units and the number of computing cores can now exceed one million. The arrival of exascale computing capability opens new promising perspectives for scientific computing, but requires new algorithms and a deep understanding of computer architectures, parallel algorithms and programming and mathematical modelling.
The availability of HPC experts, such as HPC administrators and architects, HPC proficient data scientists, HPC application developers, and expert users, is a key factor driving digital transformation in Europe, and requires the training of highly skilled and talented graduate students.
The areas of research are currently blooming, with many advances required in order to efficiently exploit current and upcoming parallel computers. However, the required skills are still rare, both in research and in academic training courses. This is also the case for the research and development divisions of major industry groups that have the necessary teams to work in this field. They base their competitiveness not only on better management and optimisation, but also on a deeper understanding of their products through the use of mathematical modelling. Every single high-tech industry is involved, from banks to organisations focusing on society-relevant issues (global warming, pollution, management).
Sorbonne Université is one of the eight awarding universities of the Pan-European High Performance Computing Pilot Master’s programme, “EUMaster4HPC”. This programme brings together major players in HPC education in Europe and emphasises collaboration across Europe with innovative teaching paradigms such as co-teaching and strong connections with the industry and the best specialists in HPC education to develop the most relevant and up-to-date teaching content. A particular focus on mobility of students and teachers will enable students to rapidly gain experience through internships and exposure to European supercomputing centres.
The study programme at SU will provide a balanced curriculum between the computer science aspects and the applied mathematics aspects of HPC. The students will have the opportunity to do an internship in an academic laboratory or an industrial group.
In the frame of this programme, Sorbonne Université offers two options :
1– Double degree Master's for High Performance Computing (HPC)
Full study programme at Sorbonne Université (M1 and M2 without compulsory international mobility).
This double Master's degree in computer science and mathematics will provide a demanding curriculum, balanced between the computer science aspects and applied mathematics aspects of HPC. It offers the possibility, under certain conditions, of acquiring both a Master's degree in computer science and a Master's degree in mathematics.
It is also possible to validate a single degree: either the Master in Computer Science or the Master in Mathematics.
2– European Master's for High Performance Computing (EUMaster4HPC) :
European double degree with a mandatory mobility period at one of the seven European partner universities of EUMaster4HPC (Universities in Germany, Bulgaria, Spain, Italy, Luxembourg, Sweden, and Switzerland).
This European Master's degree offers the possibility of validating :
- At Sorbonne University: the double degree of Master in Computer Science and Master in Mathematics OR one of these two degrees ;
- At the second university attended: the Master's degree delivered in the framework of the EUMaster4HPC programme.
M1 courses or teaching units (UE)
Listing of courses per semester
Computer hardware and parallel architectures
Foundations of mathematical algorithms: from complexity to basic linear algebra
Scientific computing for large linear systems
Data structures and algorithms for programming
Foundations of numerical methods: difference and finite elements, Fourier, wavelets
Numerical algorithms: arithmetics and reliability
Multicore and multiprocessor architectures
Numerical optimization and data science
Approximation of elliptic PDEs and numerical simulation
M2 courses or teaching units (UE)
Computer arithmetics and numerical validation
Advanced high performance computing algorithms and programming
Parallel Programming for Embedded Systems / Embedded High-Performance Computing
From PDEs to their numerical resolution by finite elements
High performance computing for numerical methods and data Analysis
Variational approximations of PDEs
Modern methods and algorithms for parallel computation (domain decomposition) (elective)
Approximation and processing of high dimensional data (elective)
Neural networks and adaptive numerical approximation (elective)
Theoretical and numerical aspects of incompressible fluids (elective)
Students who successfully complete the two years of study will earn the following postgraduate diploma (s) :
- A diploma issued by Sorbonne University ;
- A diploma issued by the second university attended (option EUMaster4HPC).
The main educational objectives of this programme are to:
- Educate students in areas such as the design, deployment, operation, and/or use of current and future generation HPC and HPC-related technologies in Europe ;
- Educate experts skilled in driving HPC adoption and knowledge transfer in industry and academia in different strategic domains, thereby linking HPC activities in industry and academia.
- HPC Solution designer
- Numerical modeling expert
- HPC programmer
- HPC expert
- Supercomputing expert
Entry Requirements & Admissions
Students with a Bachelor’s (Licence) degree in Mathematics and/or Computer Science with English speaking/writing skills (English proficiency of at least CEFR B2 / TOEFL 85/ IELTS 5 or higher, within the last 3 years; or a certificate proving that you have completed a bachelor/master program of higher education in English).
Highly motivated students with a strong background in mathematics (Bachelor level) and computer science (Bachelor level). Precisely, applicants should have knowledge of linear algebra notions and related algorithms, as well as basic numerical analysis. Concerning computer science, applicants are expected to be familiar with a programming language (preferably C or C++), as well as algorithm design and complexity.
The application for the academic year 2023-2024 needs to be submitted online during the official application periods for Master programmes.
Students must apply online via two different websites :
- Apply to the Master for High Performance Computing : Application (step 1)
- Apply to the European Master for High Performance Computing : Application (step 2)
Department of Computer Science
Head of the Department
Department of Mathematics and Applications
Head of the Department