Custom hardware versus cloud computing in big data

Abstract

The computational and data handling challenges in big data are immense yet a market is steadily growing traditionally supported by technologies such as Hadoop for management and processing of huge and unstructured datasets. With this ever increasing deluge of data we now need the algorithms, tools and computing infrastructure to handle the extremely computationally intense data analytics, looking for patterns and information pertinent to creating a market edge for a range of applications. Cloud computing has provided opportunities for scalable high-performance solutions without the initial outlay of developing and creating the core infrastructure. One vendor in particular, Amazon Web Services, has been leading this field. However, other solutions exist to take on the computational load of big data analytics. This chapter provides an overview of the extent of applications in which big data analytics is used. Then an overview is given of some of the high-performance computing options that are available, ranging from multiple Central Processing Unit (CPU) setups, Graphical Processing Units (GPUs), Field Programmable Gate Arrays (FPGAs) and cloud solutions. The chapter concludes by looking at some of the state of the art solutions for deep learning platforms in which custom hardware such as FPGAs and Application Specific Integrated Circuits (ASICs) are used within a cloud platform for key computational bottlenecks.