I have been invited to participate in the panel discussion “European Exascale vision and strategy on Big Data and Extreme Computing” organised in the context of Big Data and Extreme-scale Computing for Europe workshop that takes place in Barcelona, Spain on January 28, 2015. I thank the organisers for their kind invitation. This blog post summarises the main points of my intervention.
Applications are a strategic asset for Europe in the HPC arena. Europe is leader in HPC-powered applications that address societal challenges or are important for industrial competitiveness. A considerable demand for HPC is also present in emerging domains such as Big Data, High-Performance Data Analytics, Global System Science, as well as flagship projects such as the Human Brain Project.
However, only very few applications using HPC really take advantage of current petaflop machines. Current application owners and users find it a challenge to adapt to increasing performance and parallelism and to new architectures.
In the previous European research framework programme, FP7, no specific activity was dedicated to HPC application work. A certain amount was carried out inside PRACE, mainly to scale applications for efficient use of Tier-0 machines and to offer some support to industrial applications, but not in a systematic way and not always led by the application users as we believe it should be the case.
Our European HPC strategy identifies “Excellence in applications” as one of the three critical pillars in Horizon 2020, the current European research framework programme. This pillar focuses on supporting the establishment of Centres of Excellence (CoEs) for computing applications.
In our view, these CoEs should further consolidate the EU’s strong position in HPC applications by coordinating and stimulating parallel software code development and scaling, and by ensuring the availability of quality HPC software to users. There is a need to gather multidisciplinary teams, associating computer scientists, mathematicians and scientists to define better computational methods and algorithms
The CoEs will focus and coordinate the application work of HPC in scientific or industrial domains that are most important for Europe. The objective of the CoEs will be to develop a culture of excellence, both scientific and industrial, placing computational science at the centre of scientific discovery and industrial competitiveness
CoEs will aim at the development, provisioning and support of leading edge software and associated expertise and skills for both scientific and industrial applications. Moreover, increased productivity and competitiveness require that codes are well maintained and validated by communities rather than individual users. They should be made available through clear license terms with professional support, rather than the “best effort” approach used for many codes today.
Preparing applications for exascale imply that very advanced software and new computational methods and algorithms must be made available and adopted by practitioners, radically changing the way that large-scale applications are conceived and programmed. We expect that this activity will link with the support to applications/algorithmic developments that are carried out in the FET-HPC programme (also part of Horizon 2020).
Last but not least, CoEs should work in synergy with the other two pillars of the HPC strategy: the pan-European HPC infrastructure, and the technology-supply effort towards exascale. This could be done by identifying suitable applications for co-design activities relevant to the development of HPC technologies towards exascale, and the collaboration with supercomputing centres for the re-use of common tools and methods and the validation the new approaches to applications
The topics of the CoEs will be chosen following the recently closed call for proposals. Our goal is not to cover all possible HPC application areas, but to have at the end of the day some excellent ones that can become Europe and world-wide references in their specific domain
Personal views on research eInfrastructures 