Cloud computing for teaching and learning MPI with improved network communications

Nowadays, the teaching-learning processes are being supported by the development of new technologies. During the recent past, technologies such as email, chat, audioconferencing, videoconferencing and webconferencing were incorporated as new tools in the teaching-learning process. Currently, another step is being walked with the development and the popularization of cloud technologies that are arousing great interest in educational environments. There has been an actively development of cloud platforms with the release of several open-source solutions to build private, public and hybrid clouds such as OpenNebula, Eucalyptus, OpenStack and CloudStack. Each of them has unique features that are not found in the others. In the most basic cloud service model, Infrastructure as a Service, it is possible to provide computational resources as virtual machines. In Computer Science this model offers to teachers and students the possibility of managing virtual infrastructures in which system administration and programming languages practices can be performed without compromising the configuration of the underlying physical compute nodes. In order to test a cloud infrastructure as a tool for learning MPI, two different scenarios were evaluated in this work using CloudStack: a virtual cluster as a MPI execution environment, and an improved virtual cluster whose MPI communication latency was improved. The results of this study are presented in this paper.

keywords: CloudStack, OpenMPI, Open-MX