-
Dr Matthias Mayr (Universität der Bundeswehr München)2/25/26, 9:30 AMDeveloper Talk
-
Daniel Arndt (Oak Ridge National Laboratory)2/25/26, 10:30 AMDeveloper Talk
-
Dr Philipp Edelmann (Los Alamos National Laboratory)2/25/26, 1:00 PM
Developing multiphysics applications that run on the supercomputers of the exascale era is a daunting task. The varying workload in different regions of a problem can make load balancing difficult, especially when simultaneously handling GPU and CPU resources. Task-based parallelism is a promising way out of this dilemma but it introduces significant complexity for the application developer...
Go to contribution page -
Trévis Morvany (CEA)2/25/26, 1:30 PM
The Discrete Domain Computation (DDC) library is a modern C++ library that aims to offer to the C++ world an equivalent to the xarray.DataArray Python environment. The Xarray library introduces labeled multidimensional arrays, enabling more intuitive data manipulation by associating dimensions with user-provided names rather than relying on positional indexing. This approach simplifies...
Go to contribution page -
Paul Gannay (CEA)2/25/26, 2:00 PM
Kokkos-FFT is a library which started development in December 2023, as a part of the CExA project, and is now an official part of the Kokkos project. Its initial goals were to offer access to a Kokkos-aware performance-driven and portable FFT, with an API as simple as possible. It has been done by building an API inspired by NumPy FFT, which dispatch work to existing FFT libs (such as cufft,...
Go to contribution page -
Dr Cedric Chevalier (CEA)2/25/26, 2:30 PM
In this presentation, we’ll introduce our work on Krokkos, an experimental library designed to bridge the gap between Kokkos and Rust.
Rust, a modern systems programming language, excels in multi-threaded and memory-safe applications. Its ownership model guarantees that data races are caught at compile time, making it an attractive choice for scientific software development on shared‑memory...
Go to contribution page -
Romin Tomasetti (GNOI)2/25/26, 4:00 PM
ReProspectis a Python framework designed to support reproducible prospecting of CUDA code - that is, the systematic analysis of CUDA-based libraries and software components through API tracing, kernel profiling, and binary analysis.
Go to contribution pageReProspectbuilds on NVIDIA tools: Nsight Systems, Nsight Compute, and the CUDA binary utilities. It streamlines data collection and extraction using these... -
Adrien Taberner (CEA)2/25/26, 4:30 PM
Kokkos
Go to contribution pageMDRangePolicyprovides a high-level abstraction for iterating over multi-dimensional index spaces. Used withparallel_forandparallel_reduceconstructs, it enables computations over N-dimensional spaces (up to 6 dimensions).MDRangePolicyis the most intuitive and commonly used approach for iterating over multi-dimensional arrays and implementing stencil computations in... -
Andreas Adelmann (Paul Scherrer Institut & ETH Zurich)2/25/26, 5:00 PM
Particle–mesh methods such as Particle-in-Cell (PIC) remain central to plasma, beam, and astrophysical simulation. We present the current state of the IPPL (Independent Parallel Particle Layer) library, which provides performance portable and dimension independent building blocks for scientific simulations requiring particle-mesh methods. IPPL makes use of Kokkos, HeFFTe, and MPI (Message...
Go to contribution page -
Sonali Mayani (ETH Zürich / Paul Scherrer Institute (PSI))2/25/26, 5:30 PM
This research is in the context of IPPL (Independent Parallel Particle Layer), an open-source C++ framework providing performance-portable, dimension-independent building blocks for particle–mesh simulations, which combine Eulerian field solvers and Lagrangian particle dynamics. IPPL leverages Kokkos for on-node portability, MPI for distributed parallelism, and heFFTe for scalable FFTs,...
Go to contribution page -
Prof. Hartwig Anzt (TUM)2/26/26, 9:30 AMKeynote
The AI boom is reshaping processor design. Hardware vendors now prioritize high throughput for matrix multiplications and dense linear algebra, optimize aggressively for low precision, and integrate specialized units such as tensor cores. Meanwhile, compute performance continues to grow much faster than memory bandwidth, and latency improvements lag behind both. The result is a widening gap...
Go to contribution page -
Dr Matthias Mayr (Universität der Bundeswehr München)2/26/26, 10:30 AM
Trilinos is an advanced software framework designed to facilitate the development of high-performance scientific applications. It provides a comprehensive suite of libraries and tools that support a wide range of computational tasks, from linear algebra and optimization to differential equations and mesh generation. Particular emphasis is put on large-scale parallel software and algorithm...
Go to contribution page -
Christoph P. Schmidt (Institute for Computational Mechanics, TUM School of Engineering and Design, Technical University of Munich, Boltzmannstraße 15, 85748 Garching, Germany)2/26/26, 1:00 PM
Solid-state batteries (SSBs) are a promising technology to overcome physicochemical limitations of the currently dominant battery technology, lithium-ion batteries with liquid electrolytes. However, the interaction between solid mechanics and electrochemical phenomena remains an unresolved challenge in these systems. To gain a deeper understanding, microstructure-resolved computational models...
Go to contribution page -
Matthias Mayr (Universität der Bundeswehr München)2/26/26, 1:30 PM
The 4C (Comprehensive Computational Community Code, https://4c-multiphysics.org) multiphysics simulation framework has been developed to address complex physical phenomena across various scientific and engineering domains. From its inception, 4C has relied on the Trilinos project, an open-source software library for scalable numerical computations, as its backbone for sparse linear algebra and...
Go to contribution page -
Daniel Arndt (Oak Ridge National Laboratory)2/26/26, 2:00 PM
deal.II has been used Trilinos for linear algebra for more than 15 years. This talk will give a brief overview over the history through that time span and highlight issues with moving from Epetra to Tpetra.
Go to contribution page -
Gabriel Dos Santos (CEA)2/26/26, 2:30 PM
Kokkos Comm is a lightweight C++ library providing performance-portable explicit communication primitives for distributed Kokkos applications. It aims to eliminate code duplication across the Kokkos ecosystem by centralizing solutions to common pain points. Kokkos Comm addresses critical integration challenges between the Kokkos execution model and distributed memory programming by...
Go to contribution page -
Luca Fedeli (CEA)2/26/26, 4:00 PMDeveloper Talk
-
Malte Buschmann (DESY)2/26/26, 5:00 PM
Approximately 70% of the matter content of our Universe consists of dark matter, yet its fundamental nature remains unknown. Among the many proposed candidates, the axion stands out as particularly compelling because it not only provides a viable explanation for dark matter but also offers an elegant solution to the strong CP problem, one of the most persistent puzzles in the Standard Model of...
Go to contribution page -
Dr Nils Schild (IPP)2/26/26, 5:30 PM
In this talk we report our initial steps on the interoperability between Kokkos and AMReX within an internal codebase. Our goal is to explore how Kokkos capabilities can be integrated into an existing AMReX-based code. In addition to CUDA and HIP, the parallel dispatch provided by Kokkos::parallel_for enables the use of OpenMP for parallel loop constructs. Furthermore, we investigate whether...
Go to contribution page -
Massimiliano Culpo2/27/26, 9:30 AM
-
Pit Steinbach (Forschungszentrum Juelich)2/27/26, 10:30 AM
A key aspect of developing research software is testing the installation and the expected results on various configurations, as well as benchmarking the performance preferably continuously. This applies especially to software that targets high-performance computing (HPC) installations around Europe and the world. For these applications performance, scalability, and efficiency are key metrics...
Go to contribution page -
Alexandre Escoubas (ETH Zurich / Swiss National Supercomputing Center (CSCS))2/27/26, 11:00 AM
OpenCHAMI, the open-source successor to the Cray System Management (CSM) stack, reimagines HPC system management through a modular, microservices-based architecture. While this shift offers flexibility, it introduces complexity in replicating the environment for development and testing. To address this, we present a versatile tooling suite designed to empower developers by tightening the...
Go to contribution page
Choose timezone
Your profile timezone: