

The Heterogeneous Exascale Particle-In-Cell (HEXAPIC)
Wednesday, June 24, 2026 3:45 PM to 5:15 PM · 1 hr. 30 min. (Europe/Berlin)
Foyer D-G - 2nd Floor
Project Poster
Extreme-scale SystemsHeterogeneous System ArchitecturesParallel Programming LanguagesParallel Numerical AlgorithmsPhysics
Information
Poster is on display.
This research investigates the potential enhancements of particle-in-cell (PIC) codes through modern heterogeneous computer architectures, focusing on two key hypotheses. First, we propose that implementing advanced algorithms designed for complex physical mechanisms will significantly improve PIC code algorithms by optimizing workload distribution, efficiently utilizing computing accelerators, and enhancing communication and memory management, thereby achieving substantial performance gains. Second, we emphasize the critical need for fully-kinetic PIC codes to accurately model plasma technological processes. Our aim is to optimize our PIC code using state-of-the-art techniques that facilitate the integration of realistic geometries and comprehensive plasma dynamics, ultimately enhancing predictive and optimization capabilities and achieving unprecedented precision in plasma simulations.
This research investigates the potential enhancements of particle-in-cell (PIC) codes through modern heterogeneous computer architectures, focusing on two key hypotheses. First, we propose that implementing advanced algorithms designed for complex physical mechanisms will significantly improve PIC code algorithms by optimizing workload distribution, efficiently utilizing computing accelerators, and enhancing communication and memory management, thereby achieving substantial performance gains. Second, we emphasize the critical need for fully-kinetic PIC codes to accurately model plasma technological processes. Our aim is to optimize our PIC code using state-of-the-art techniques that facilitate the integration of realistic geometries and comprehensive plasma dynamics, ultimately enhancing predictive and optimization capabilities and achieving unprecedented precision in plasma simulations.
Format
on-demandon-site