High-performance computing without commitment: SC2IT: A cloud computing interface that makes computational science available to non-specialists

Abstract

Computational work is a vital part of many scientific studies. In materials science research in particular, theoretical models are often needed to understand measurements. There is currently a double barrier that keeps a broad class of researchers from using state-of-the-art materials science codes: the software typically lacks user-friendliness, and the hardware requirements can demand a significant investment, e.g. the purchase of a Beowulf cluster. Scientific Cloud Computing has the potential to remove this barrier and make computational science accessible to a wider class of scientists who are not computational specialists. We present a set of interface tools, SC2IT, that enables seamless control of virtual compute clusters in the Amazon EC2 cloud and is designed to be embedded in user-friendly Java GUIs. We present applications of our Scientific Cloud Computing method to the materials science codes FEFF9, WIEN2k, and MEEP-mpi. SC2IT and the paradigm described here are applicable to other fields of research outside materials science within current Cloud Computing capability.