The International Conference for High Performance Computing, Networking, Storage and Analysis
Federated Computing for the Masses - Tackling Large-Scale Engineering Problems.
Authors: Javier Diaz-Montes (Rutgers University), Yu Xi (Iowa State University), Ivan Rodero (Rutgers University), Jaroslaw Zola (Rutgers University), Baskar Ganapathysubramanian (Iowa State University), Manish Parashar (Rutgers University)
Abstract: The complexity of many problems in science and engineering requires computational capacity greatly exceeding what average user can expect from a single computational center.This work explores the use of aggregated HPC resources to solve large-scale scientific problems. We show that it is possible to build a computational federation that is easy to use by end-users, elastic, resilient and scalable. We argue that the fusion of federated computing and real-life problems can be brought to average user if relevant middleware infrastructure is provided. To support our claims, we report on the use of federation of 10 geographically distributed HPC resources to perform a large-scale interrogation of the parameter space in the microscale fluid-flow problem. This problem is of great importance in many domains such as biological processing, guiding chemical reactions, and creating structured materials. As a result, we obtained the most comprehensive data on the effect of pillars on microfluid channel-flow.