About the Research Center

We aim to explore the design, analysis and application of massive-scale computing systems for processing data, in the most general sense.

The goal is to address the underlying systems aspects of big data—including data processing, storage and retrieval—which are central to some of the key research and societal challenges of the 21st Century.

The group is a nexus to connect (i) those who design and analyze high-performance computing systems for big data, and (ii) system users, from a variety of application areas. The former area includes researchers developing massively-parallel processors, energy-efficient hardware systems, distributed computing, software and databases, but also, in a broader view, those studying the brain. Several members are exploring and developing new parallel computing paradigms and architectures. The latter area includes those who need to process, store, retrieve, analyze and understand massive data sets, where computation and storage breakthroughs are essential. The goal is to have synergy and interaction between these two classes of researchers.

The group has a diverse set of members, working on systems research (computer science, electrical engineering, neuroscience) and application areas (oceanography, climate science, astronomy, physics, materials science, civil engineering, neuroscience, biomedical informatics and computational genomics). Many are working at the cutting edge of high-performance computing (HPC, i.e. scientific computing) and high-performance data analytics (HPDA, i.e. machine learning, pattern matching, and massive-scale search) applications. These two areas are melding with key national initiatives to support both, and with data analytic techniques migrating into biological and physical computation problems.

In a simple view, most of science has become computational—many researchers need number crunching. But, in terms of application areas, this group is instead interested in problems where extreme-scale data processing is a central core of the research, and a critical bottleneck.

The Center for Computing Systems for Data-Driven Science aims to serve as the thought leader and intellectual locus at the University for massive-scale systems research and applications.