Extreme-Scale Visualisation

Exascale-class systems will generate huge data sets that are impossible to comprehend without further processing. Visualisation and analysis tools, techniques and algorithms have undergone a rapid evolution in recent decades to accommodate the increasing volume and complexity of modern data sets. Nonetheless, producing real-time, high-quality graphics of extreme-scale data sets presents many technical issues that are only now becoming surmountable with emerging hardware and software solutions.

Once new post-processing and visualisation techniques have been developed and integrated into data-analysis tools and problem-solving environments, the future discoveries dependent on the ready visualisation of big data can be realised.

Aims

  • At the Exascale Lab, we are designing solid-state storage test beds that will be combined with large-scale rendering compute engines and leading graphical software to render extreme-scale data sets in real time.
  • We are experimenting with different modes of in-situ visualisation and refining different visualisation working environments in collaboration with researchers at the University of Cambridge.
  • Our visualisation techniques will be documented and packaged, resulting in simple, flexible tools. These tools will allow for an interactive, three-dimensional visualisation of data stored by a remote service provider. Researchers will be able to manipulate and inspect data, as well as transform it into high-quality outreach material.
  • At the Exascale Lab, our ambition is to host a remote-access implementation of these tools. We aim to make visualisation technology accessible to working scientists, engineers and clinicians, helping them to gain further insight into their data.

Related Projects