Skip to Content
UK e-Science

All Hands Meeting 2009

« Past, Present and Future »

Theme 6: Distributed and High Performance Computing Technologies

Led by Richard Sinnott, Arthur Trew and Jeremy Yates

Distributed and high performance computing (HPC) has been one of the primary drivers of e-Science. Developing applications that can utilise rapidly evolving and complex infrastructure remains a challenge however. This is especially so with HPC facilities becoming increasingly
heterogeneous with single, multi-core, Cell, GPU and FPGA technologies all now available. This heterogeneity of HPC resources leads to many new challenges in software development and algorithm strategies. One of the main challenges is how can application developers best exploit this HPC hardware heterogeneity?

The aim of this workshop is to explore a range of computational science applications that have successfully exploited distributed and/or massively parallel infrastructure to produce novel scientific results. Applications that target heterogeneous HPC infrastructures are especially sought. By showcasing applications spanning large scale computing and data resource requirements, we aim to highlight the potential of distributed infrastructures and assess future directions in high performance and distributed scientific applications.

This workshop will bring together leading scientists exploiting the boundaries of high performance and distributed computing and application domain researchers with requirements that can only be addressed by access to larger scale HPC facilities. This workshop invites submissions from computational researchers with use cases that have successfully utilised distributed and/or high performance infrastructure in particular application domains. We also encourage papers on tools and techniques that have been developed for grid-enabling applications to best exploit HPC and/or support improved (optimised) usage of HPC resources.

This workshop invites papers on topics that include but are not limited to:

  • Case studies of new scientific work made possible by high performance and distributed computing;
  • Applications exploiting heterogeneous hardware infrastructures including optimised use of single, multicore, Cell, GPUs and FPGAs;
  • Tool support and/or experience reports on (auto-)parallelisation of codes to heterogeneous architectures;
  • Applications utilising novel distributed algorithms;
  • HPC case studies especially those combining large scale data, computational and other requirements, e.g. security;
  • Novel tools, techniques and infrastructure that assist the development, deployment and execution of distributed applications;
  • Methods frameworks, compilers, solvers, algorithms, programming models that facilitate larger scale HPC applications.