Presentation Details |
|||||
Name: | (PP21) Enhancing HPC for Scheduling & Deploying Game-Based Simulation Training on the Cloud | ||||
Time: | Tuesday, June 20, 2017 03:15 pm - 03:45 pm |
||||
Room: | Booth #L-212 | ||||
Breaks: | 03:15 pm - 03:45 pm Coffee Break | ||||
Presenter: | Brian Goldiez, University of Florida | ||||
Abstract: | Interactive training simulation through the use of game-based and virtual simulators pose challenges on traditional networks of computing assets. A variety of organizations and domains, including the entertainment industry, energy and financial sectors, military, and video gaming, have turned to high performance computing (HPC) as a powerful enough platform to run these interactive simulations. This project explores the feasibility of extending a traditional HPC environment into a cloud-based service capable of supporting multiple simultaneous interactive simulations, while continuing to solve compute-intensive tasks. The goal of this work is to extend the scope of software that can be applied to an HPC environment while preserving performance efficacy.
To accomplish the proposed HPC goal, this work investigates HPC load-balancing techniques through virtualization, software containers, and cluster federation to simultaneously and optimally analyze, schedule, and execute traditional HPC tasks and game-based simulation applications. With virtualization, the HPC environment can host a wide variety of operating systems and software. Through software containers, simulators, their components, and their libraries can be prepackaged for easy deployment and management. Finally, with cluster federation (multiple connected clusters), software jobs can be distributed to other clusters to load-balance and distribute workloads. The proposed experimentation compares these different techniques for performance and to determine the feasibility of extending HPC capability. Authors:
Anastasia Angelopoulou, University of Central Florida Brian Goldiez, Institute for Simulation and Training at University of Central Florida Sean Mondesire, Institute for Simulation and Training at University of Central Florida |
||||
Download | PP21_Goldiez.pdf (689 KB) |
||||