For the first time the AER is participating in the [TUM Data Innovation Lab](https://www.mdsi.tum.de/di-lab/tum-di-lab/) of the [Munich Data Science Institute](https://www.mdsi.tum.de/mdsi/startseite/) with its own project on the software-level acceleration of neural network kernels used in the acceleration of traditional computational fluid dynamics simulations.
The students will work on the acceleration of research-level neural networks, specifically a generative adversarial network (GAN), and a graph neural network (GNN) for the acceleration of smoothed-particle hydrodynamics. For this we will begin by introducing the Microsoft DeepSpeed concepts at the beginning of the project, and the successively building on the gained knowledge by first accelerating a classical GAN, the research-level GAN, to finally accelerate the kernels used in the graph neural network acceleration.
For more information please have a look at the [project page](https://www.mdsi.tum.de/di-lab/projekte/ss2022-chair-of-aerodynamics-and-fluid-mechanics-acceleration-of-neural-network-training-with-microsoft-deepspeed/), and feel free to approach Ludger Paehler (ludger.paehler(at)tum.de) if you need more information.