Data and Systems Heterogeneity: Analysis on Data, Processing, Workload, and Infrastructure

This paper is our survey toward a general understanding of the requirements for handling large volumes of heterogeneous data, and moreover, presents an overview of the employed computing techniques and technologies necessary for analyzing and processing those datasets. As of our attempt to picture how the data heterogeneity meets the systems heterogeneity, we summarize the identified key issues for multiple dimensions, including data, processing, workload, and infrastructure.