SORS: HPC simulation using xSim – The Extreme-scale Simulator

Date: 28/Feb/2014 Time: 09:00

Primary tabs

You can view the presentation here

Abstract: The Extreme-scale Simulator (xSim) is an HPC performance investigation toolkit developed at the Oak Ridge National Laboratory (ORNL). It allows for hardware and software co-design and to model behaviour of HPC applications. Native HPC applications can be executed in a controlled environment with millions of concurrent execution threads. MPI applications can be simulated on a much smaller system in a highly oversubscribed fashion. To achieve these simulations the development of xSim traded off scalability and simulation performance against simulation accuracy. Performance data can be extracted based on a processor and a network model with an appropriate simulation. The simulator supports user-level failure mitigation (ULFM) extensions at the simulated MPI layer and permits injection of MPI process failures to aid development and debugging of resilient fault tolerant applications. Examples on selected applications will be presented and applicability discussed.          

Short Bio: Janko Strassburg is a PhD student in Computational Science. His research interests are in the areas of High Performance Computing, Network Centered Computations, Scalable and Fault-Tolerand Algorithms and Accelerator Architectures. His current work is focusing on Monte Carlo algorithms that are applied in the fields of Linear Algebra and Computational Finance. He is studying for his PhD at the University of Reading, UK and is currently working as a researcher at the Barcelona Supercomputing Center.