DPG Phi
Verhandlungen
Verhandlungen
DPG

Dresden 2013 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 115: Beschleunigerphysik II (PWA I)

T 115.6: Vortrag

Montag, 4. März 2013, 12:15–12:30, WIL-C205

PIConGPU - A Highly-Scalable Particle-in-Cell Implementation for GPU Clusters — •Michael Bussmann1, Heiko Burau1, Alexander Debus1, Axel Hübl1, Thomas Kluge1, Richard Pausch1, Nils Schmeisser1, Benjamin Schneider1,2, Klaus Steiniger1, Rene Widera1, Nikolai Wyderka1, Ulrich Schramm1, Thomas Cowan1, Felix Schmitt3, Sebastian Grottel2, Stefan Gumhold2, Guido Juckeland2,4 und Wolfgang Angel2,41HZDR, Dresden — 2TU Dresden — 3NVIDIA, Austin — 4ZIH, Dresden

PIConGPU can handle large-scale simulations of laser plasma and astrophysical plasma dynamics on GPU clusters with thousands of GPUs. High data throughput allows to conduct large parameter surveys but makes it necessary to rethink data analysis and look for new ways of analyzing large simulation data sets. The speedup seen on GPUs enables scientists to add physical effects to their code that up until recently have been too computationally demanding. We present recent results obtained with PIConGPU, discuss scaling behaviour, the most important building blocks of the code and new physics modules recently added. In addition we give an outlook on data analysis, resiliance and load balancing with PIConGPU.

100% | Mobil-Ansicht | English Version | Kontakt/Impressum/Datenschutz
DPG-Physik > DPG-Verhandlungen > 2013 > Dresden