Multi-GPU Approach for Training of Graph ML Models on large CFD Meshes

no code implementations • 25 Jul 2023 • Sebastian Strönisch, Maximilian Sander, Andreas Knüpfer, Marcus Meyer

This paper scales a state-of-the-art surrogate model from the domain of graph-based machine learning to industry-relevant mesh sizes of a numerical flow simulation.

Performance-Portable Many-Core Plasma Simulations: Porting PIConGPU to OpenPower and Beyond

1 code implementation • 9 Jun 2016 • Erik Zenker, René Widera, Axel Huebl, Guido Juckeland, Andreas Knüpfer, Wolfgang E. Nagel, Michael Bussmann

With the appearance of the heterogeneous platform OpenPower, many-core accelerator devices have been coupled with Power host processors for the first time.

Distributed, Parallel, and Cluster Computing

Alpaka - An Abstraction Library for Parallel Kernel Acceleration

1 code implementation • 26 Feb 2016 • Erik Zenker, Benjamin Worpitz, René Widera, Axel Huebl, Guido Juckeland, Andreas Knüpfer, Wolfgang E. Nagel, Michael Bussmann

The model exploits parallelism and memory hierarchies on a node at all levels available in current hardware.

Distributed, Parallel, and Cluster Computing Mathematical Software