High performance computing in the EU : progress on the implementation of the European HPC strategy : final report

This is the Final Report D3 of the study SMART 2014/0021 High Performance Computing in the EU: Progress on the Implementation of the European HPC Strategy that IDC conducted for the European Commission Directorate-General for Communications Networks, Content & Technology, Unit C1 eInfrastructure. The main goal was to assess progress against the Action Plan in the EC Communication, High Performance Computing (HPC): Europe's Place in a Global Race (February 2012) and provide recommendations regarding the strategy and its implementation. The findings will support the EC report to the European Parliament and Council on the implementation of the Communication, planned for 2015. The European HPC strategy has made impressive overall progress, especially in organizing Europe's HPC community to pursue the strategy's leadership goals, narrowing the gap between the largest European supercomputers and their counterparts elsewhere, and providing fair access to leading supercomputers for scientists and engineers throughout Europe. To achieve the goal of HPC leadership-meaning at minimum parity in HPC capabilities with the best in the world-Europe needs to acquire at least one exascale supercomputer in the same timeframe as the U.S., Japan and China. The current European HPC strategy provides no clear path for doing this. IDC recommends that Europe extends the end date for its HPC strategy from 2020 to 2022, to match the exascale time frames of the U.S., Japan and China, and that Europe plans to acquire two exascale systems, one of which stresses innovative European technologies (such as those being advanced within ETP4HPC). To amass the €1 billion-plus funding needed for the exascale supercomputers, the Member States must find a way to pool funding, and the European Commission must find a way to boost its contribution to the needed funding amount. Rules for collaboration will likely need to change, in order to allow the Commission and Member States to work more closely together. European HPC suppliers face protective barriers in the U.S., Japanese and Chinese HPC markets. These market asymmetries should be addressed at a government-to-government level, preferably by the European Commission. The European Commission and Member States should also collaborate to address the shortage of qualified HPC job applicants, especially by ensuring that HPC competency is required in university scientific and engineering curricula, and that students are aware from an early age of attractive, rewarding HPC careers.