The scientific case for high-performance computing in Europe

Kenneth Ruud, University of Tromsø

Computational sciences is becoming increasingly important for scientific progress. I will give some examples of the advances made possible through high-permance computing. In the talk, I will also summarize the PRACE Scientific Case for High-Performance computing in Europe, and discuss the evolution of HPC at national, nordic and european levels.

Supporting Research Communities with XSEDE

John Towns, University of Illinois

XSEDE is a major research infrastructure in the United States with collaborations worldwide supporting thousands of researchers across a wide range of domains. XSEDE has taken an integrative and holistic approach to supporting researchers in the use of the varying resources and services available via XSEDE. This presentation will breifly review XSEDE and its vision and provide a discussion of the efforts within XSEDE targeted at supporting research communities.

Developing needs of HPC in Climate modeling

Ralf Döscher, SMHI

Challenges in developing the field of climate modeling are manifold, ranging from improved physical descriptions, increased resolution, to inclusion of bio-geo-chemical components and better end user value. All of those require increased HPC capacities, complemented by access to storage, data publication and associated infrastructure. The presentation will describe the roles of Global Climate Models (GCMs), Earth System Models (ESMs) and Regional Climate Models (RCMs), the computational performance of coupled codes, experience with PRACE, and development of new numerical schemes. The major upcoming task for global scale climate modeling is the Coupled Model Intercomparison Project (CMIP6) which will provide information to the next IPCC assessment. The Swedish climate modeling community is currently preparing for that project with the help of SNIC application experts.

UPPNEX - Bioinformatics Compute and Storage

Martin Dahlö, UPPNEX

Molecular biology has in the last couple of years seen an immense growth in experimental data, with perhaps the largest contributor being next-generation sequencing. With constantly increasing throughput, these technologies have transformed molecular biology into a data-intensive field that presents new challenges in storing and analyzing the huge volumes of data generated.