Höchstleistungsrechenzentrum Stuttgart: alpaka and openPMD Workshop and Hackathon

Prerequisites and content levels

Prerequisites

Basic Knowledge of High-Performance Computing (HPC): Participants should have a foundational understanding of HPC concepts, architectures, and programming.
Basic Linux/Unix Skills: Ability to navigate, use command-line tools, and perform basic operations in a Linux/Unix environment.
Programming Skills: Proficiency in programming languages commonly used in HPC, such as C, C++, Fortran, or Python. Knowledge of parallel programming paradigms (e.g., MPI, OpenMP) is beneficial.

Content levels

Community-target-level: 16 hours

Learn more about course curricula and content levels.

Instructors

Tapish Narwal, t.narwal(at)hzdr.de
Julian Lenz, j.lenz(at)hzdr.de
Mehmet Yusufoglu, m.yusufoglu(at)hzdr.de
Franz Pöschel, f.poeschel(at)hzdr.de
Simeon Ehrig, s.ehrig(at)hzdr.de

Agenda

Introduction to alpaka: Learn about the alpaka library, its architecture, and how it enables portable and performant parallel programming across various hardware backends.
Optimizing with alpaka: Discover advanced techniques for optimizing kernels and managing memory in alpaka to achieve maximum performance.
Getting Started with openPMD: Dive into the openPMD standard, exploring how it facilitates scalable I/O for scientific data in simulations and experiments.
Integrating openPMD with Simulation Codes: Learn best practices for integrating openPMD with your existing simulation frameworks and how to leverage its full potential.
Showcasing use of alpaka and openPMD with PIConGPU: PIConGPU is a user of both these libraries and leverages them to do exascale simulations. Take a short look inside PIConGPU to see how these libraries are used in a large project and run a test simulation with PIconGPU.

Hands-on sessions

alpaka

alpaka (Abstraction Library for Parallel Kernel Acceleration) is a powerful C++ library designed to enable portable and efficient parallel programming across a variety of hardware platforms. It provides a uniform API that abstracts the underlying hardware, allowing developers to write parallel code that can be executed on different backends, such as CPUs, GPUs, and FPGAs. By using alpaka, developers can achieve high performance and maintain portability, making it an ideal choice for high-performance computing (HPC) applications.

Key features of Alpaka include:

Hardware Abstraction: Write once, run anywhere. alpaka abstracts the specifics of different hardware architectures.
Performance: Optimize your applications to run efficiently on any supported backend.
Flexibility: Support for various parallel programming paradigms and patterns.
Scalability: Suitable for both small-scale and large-scale HPC environments.

GitHub: https://github.com/alpaka-group/alpaka

openPMD

openPMD (Open Standard for Particle-Mesh Data) is a community-driven metadata standard for describing and storing scientific data in a portable and scalable manner. It provides a FAIR data format for particle and mesh data, enabling blazingly fast and easy IO, sharing, analysis, and visualization of large datasets. The openPMD standard ensures consistency and interoperability across different software and hardware platforms, promoting reproducible research and collaboration.

Key features of openPMD include:

Standardization: Defines a common format for metadata and data, facilitating data exchange and analysis.
Scalability: Efficient handling of large datasets, suitable for HPC environments.
Interoperability: Seamless integration with various simulation codes and data analysis tools.
Extensibility: Flexible and extensible to accommodate specific needs of different scientific domains.

GitHub: https://github.com/openPMD/openPMD-standard

Registration information

Please register at course via the button at the top of this page with your institutional e-mail address to prove your affiliation.

The final participants will be selected and informed after the registration deadline has passed.

This course is offered in cooperation by HLRS, HZDR/CASUS and Plasma-PEPSC CoE. Your registration data will be transferred to these partners (legal notes at the provided links).

Registration closes on October 11, 2024 at 23:55.

Fees

Students without Master's degree or equivalent. Participants from EU or EuroCC countries only: 0 EUR
PhD students or employees at a German university or public research institute: 0 EUR
PhD students or employees at a university or public research institute in an EU or EuroCC country other than Germany: 0 EUR.
Other participants, e.g., from industry, other public service providers, or government. Participants from EU or EuroCC countries only: 0 EUR

Our course fee includes coffee breaks (in classroom courses only).

For lists of EU and EuroCC countries have a look at the Horizon Europe and EuroCC website.

Only participants from institutions belonging to these countries can take part in this course.

Contact

Tapish Narwal, t.narwal(at)hzdr.de
Julian Lenz, j.lenz(at)hzdr.de

HLRS Training Collaborations in HPC

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich. EuroCC@GCS is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC.

This course is provided within the framework of EuroCC2.

Plasma-PEPSC CoE

This course is partly realised in cooperation with the Centre of Excellence Plasma-PEPSC. Funded by the European Union through Grant Agreement No. 101093261.

Official course URL(s)

https://events.hifis.net/event/1657/ and course website at Alpaka.

Further courses

See the training overview and the Supercomputing Academy pages.