51 Copyright © 2013, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. Chapter 3 DOI: 10.4018/978-1-4666-2854-0.ch003 1. INTRODUCTION Service-oriented computing, with its focus on coupling distributed components through well- defined interfaces and protocols, can be seen as an extension to concepts such as distributed computing and even grid computing. Likewise, Clouds can very much be seen as an evolution from Grid computing, with the addition of vir- tualisation and sharing of resources. Distributed and Grid computing have long been exploited for high performance computing and scientific simulation and as such Cloud computing, and service-oriented architectures, are an interesting Adrian Jackson Edinburgh Parallel Computing Centre, The University of Edinburgh, UK Michèle Weiland Edinburgh Parallel Computing Centre, The University of Edinburgh, UK Cloud Computing for Scientifc Simulation and High Performance Computing ABSTRACT This chapter describes experiences using Cloud infrastructures for scientifc computing, both for serial and parallel computing. Amazon’s High Performance Computing (HPC) Cloud computing resources were compared to traditional HPC resources to quantify performance as well as assessing the complexity and cost of using the Cloud. Furthermore, a shared Cloud infrastructure is compared to standard desktop resources for scientifc simulations. Whilst this is only a small scale evaluation these Cloud oferings, it does allow some conclusions to be drawn, particularly that the Cloud can currently not match the parallel performance of dedicated HPC machines for large scale parallel programs but can match the serial performance of standard computing resources for serial and small scale parallel programs. Also, the shared Cloud infrastructure cannot match dedicated computing resources for low level benchmarks, although for an actual scientifc code, performance is comparable.