HPC+Azure Environment for Bioinformatics Applications

Abstract

In the past 20 years, huge flow of data, produced by the nonstop rise of computational power has led to a paradigm shift in large scale data processing mechanisms and computing architecture. As a result, human and computational resources are needed to aid data-intensive operations which will cause the high degree of storage and management expenses. An organized and standard approach is important to manage these issues with an architecture that able to scale into the predictable future. Instead of the fastest and largest single computer solution, economical clusters of computers can better manage and process all data. Most of the high-performance computing (HPC) systems need a huge amount of processing power and Windows Azure is capable of providing a huge quantity of processing power on demand. As the Windows HPC server and Windows Azure combine, the cloud and on-premises world are now able to function together. In this paper we explore a HPC+Azure implementation model and demonstrate by running a genome sequence assembly application.