ABSTRACT: In the past decade the amount of data we produce and consume has grown exponentially. As a result, science, society and business are witnessing a data revolution. Data are now created by faster and cheaper physical technologies, software tools and digital collaborations. Examples of these include satellite imagery, simulation models, business process artefacts, and social network data. To transform these data successfully into information then into knowledge and finally into solutions to the grand challenges facing society today, we need new forms of computational thinking. The world of supercomputing has not been immune to this revolution and the scale and complexity of the data produced by today’s HPC simulations is breathtaking.
Recently a small group of pioneers have started to explore better, more resource efficient ways of accessing, integrating and analysing data – the complementary domains of data intensive research and data analytics have been born. Data intensive computing offers a number of different hardware and software paradigms compared to "traditional" high performance and parallel computing. A fledgling community exists that is creating machines and software to satisfy the needs of the business and research communities which have data intensive problems, such as astronomy, astrophysics, systems biology, finance and retail etc.
This BOF session, led by EPCC, the supercomputing centre at The University of Edinburgh, will bring together a number of the prominent researchers in the fields of Data Intensive Research and Data Analytics to provide an insight into the status of current research and thinking as well as providing an opportunity for researchers and other interested parties to discuss their experience, needs, and general interest. The session will be panel based with an experienced moderator and discussion and debate amongst all present will be encouraged.
Session Leader Details:
Mark I Parsons (Primary Session Leader) - Edinburgh Parallel Computing Centre