Call for Proposals for DECI-17

Call for Proposals for HPC Compute Resources from DECI-17 (Tier-1) and EUDAT services and resources for data management.

The PRACE DECI programme provides cross-national access to European Tier-1 HPC resources (national systems). Access will be awarded for a period of 12 months, beginning 1 June 2021. Resources are available on the following architectures listed in the table below:

[ONLINE] Efficient Use of HPC Systems

14-15 December 2020

Description

The purpose of this course is to guide existing and potential users on how to efficiently use HPC systems, and to present typical HPC tools, the software environment, compilers, libraries, parallel environments, batch system and best practices.

The trainees will learn what the HPC systems offer, how they work, how to make efficient use of resources and how to apply for access to PRACE and similar infrastructures.

ONLINE – PRACE Training Centre: Introduction to Parallel Programming

11 – 13 November 2020

Purpose of the course

The focus is to understand the basics of parallel programming with the message-passing interface (MPI) and OpenMP parallel programming paradigms. MPI is the dominant parallelization paradigm in high performance computing and enables one to write programs that run on distributed memory machines, such as the ARIS Greek supercomputer and other systems of the PRACE infrastructure. OpenMP is a threading based approach which enables one to parallelize a program over a single shared memory machine, such as a single node in ARIS. The course also contains performance and best practice considerations, e.g., hybrid MPI+OpenMP parallelization. The course ends with a section presenting profiling and code optimizations to understand the behavior and performance of parallelized codes.

The 3 day course consist of lectures and hands-on exercises on parallel programming. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the taught constructs of the Message Passing  Interface (MPI) and the shared memory directives of OpenMP. The course ends with a section presenting profiling and code optimizations to understand the behavior and performance of parallelized codes.

ONLINE – PRACE Training Centre: Introduction to Parallel Programming

11 – 13 November 2020

Purpose of the course

The focus is to understand the basics of parallel programming with the message-passing interface (MPI) and OpenMP parallel programming paradigms. MPI is the dominant parallelization paradigm in high performance computing and enables one to write programs that run on distributed memory machines, such as the ARIS Greek supercomputer and other systems of the PRACE infrastructure. OpenMP is a threading based approach which enables one to parallelize a program over a single shared memory machine, such as a single node in ARIS. The course also contains performance and best practice considerations, e.g., hybrid MPI+OpenMP parallelization. The course ends with a section presenting profiling and code optimizations to understand the behavior and performance of parallelized codes.

The 3 day course consist of lectures and hands-on exercises on parallel programming. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the taught constructs of the Message Passing  Interface (MPI) and the shared memory directives of OpenMP. The course ends with a section presenting profiling and code optimizations to understand the behavior and performance of parallelized codes.

Introduction to Biomolecular modeling and Molecular dynamics in HPC

(Classical and Quantum)

Purpose of the course

The purpose of this course is to present to existing and potential users of Molecular Dynamics packages the method, the necessary steps for a successful simulation, common practices, common mistakes. The steps for a complete simulation workflow i.e. system setup up to final properties evaluation will be presented using popular software packages.

Outcomes

After the course the participants should be able to efficiently use their prefered MD application (i.e. NAMD, GROMACS, LAMMPS, CP2K), for molecular modelling and molecular dynamics simulations,  how to create configuration files based on their needs, tuning the models, how to efficiently use the resources based on the simulation details, avoid common mistakes

RESCHEDULED, ONLINE – PRACE Training Centre: Machine Learning in HPC, 11-12 June 2020.

Machine Learning in HPC

RESCHEDULED, ONLINE

11-12 June 2020

Description

After the course the participants should be able to understand basic principles in Machine Learning and apply basic machine learning methods.

Learn how to efficiently use HPC infrastructures to get
the best performance out of different machine learning tools. How to use these machine learning frameworks like: Tensorflow, PyTorch, Keras, Horovood with hands-on sessions.

Learn using multiple GPUs to significantly shorten the time required to train lots of data, making solving complex problems feasible.

Learn best-practices to avoid common mistakes to efficiently use the HPC infrastracture and overcome the scalability challenges when using parallel computing techniques