High performance computing in Windows Azure cloud

Dejan Ambruš (2013) High performance computing in Windows Azure cloud. EngD thesis.

Preview

PDF Download (1637Kb)

Abstract

High performance, security, availability, scalability, flexibility and lower costs of maintenance have essentially contributed to the growing popularity of cloud computing in all spheres of life, especially in business. In fact cloud computing offers even more than this. With usage of virtual computing clusters a runtime environment for high performance computing can be efficiently implemented also in a cloud. There are many advantages but also some disadvantages of cloud computing, some of them are addressed in our thesis, mainly regarding to the Microsoft's public cloud computing platform Windows Azure. We describe the underlying infrastructure and software configuration as well as its functions and server usage charges. In the second part we describe how to set up a Windows Azure account and configure it for high-performance computing and also how to run many virtual machines simultaneously using HPC Cluster Manager. Dynamic resource allocation, improved flexibility, broad network access, performance enhancements as well as business benefits convinced us there are many benefits of cloud computing comparing to the on-site computing resources.

Actions (login required)