Accepted paper at ProTools'25 (SC Conference Workshop) titled MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies by Stepan Vanecek et al.
[weiterlesen]
CAPS recently had the pleasure of visiting the German Aerospace Center (DLR) in Oberpfaffenhofen, one of Germany’s largest and most advanced research hubs. Thanks to our colleagues Maron and Cedric—external PhDs at CAPS working at DLR—we got an inside look at how high-performance computing meets…
[weiterlesen]
In this work, we developed a python-based tool called TppFaaS on top of OpenWhisk serverless platform which uses neural Temporal Point Processes…
[weiterlesen]
In this paper, the authors Christoph Reile, Mohak Chadha, Valentin Hauner, Anshul Jindal, Benjamin Hofmann, and Michael Gerndt present Bunk8s a tool…
[weiterlesen]
In this paper, the authors Andreas Grafberger, Mohak Chadha, Anshul Jindal, Jianfeng Gu, and Michael Gerndt present FedLess a framework for serverless…
[weiterlesen]
In this paper, the authors Michael Kiener, Mohak Chadha, and Michael Gerndt analyse the effect of parallelising serverless workloads wrt performance…
[weiterlesen]
In this paper, we present a software system called Courier that is responsible for optimally distributing the invocations of the functions within the…
[weiterlesen]
