An e-infrastructure for software, training and consultancy in simulation and modelling

Informations projet

E-CAM

N° de convention de subvention: 676531

DOI

10.3030/676531

Projet clôturé

Date de signature de la CE 28 Juillet 2015

Date de début 1 Octobre 2015

Date de fin 31 Mars 2021

Financé au titre de

• EXCELLENT SCIENCE - Research Infrastructures

Coût total

€ 4 836 896,25

Contribution de l’UE

€ 4 836 895,75

Coordonné par

ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE
Switzerland

Periodic Reporting for period 4 - E-CAM (An e-infrastructure for software, training and consultancy in simulation and modelling)

Période du rapport: 2019-07-01 au 2021-03-31

Résumé du contexte et des objectifs généraux du projet

E-CAM has sought to prepare the extended E-CAM community for the demands of upcoming exascale systems, paving the way for the portability of entire application stacks and workflows to all the architectures that will be available through EuroHPC. We have addressed core cross-cutting topics such as load balancing, intelligent high throughput computing, accelerator portability and the portability of entire software stacks, and repeatedly worked with individual applications to evaluate and improve their performance, collaborating with other projects in the EuroHPC eco-system along the way. In addition, E-CAM has raised awareness of best practices in scientific computing, and encouraged people to consistently use version control, documentation, continuous integration, modular software development, configure/build/install installation processes and supporting tools, and open source software licences.

E-CAM has disseminated the EuroHPC eco-system among the thousands of scientists associated with CECAM, and trained hundreds of them, exposing them to HPC resources that they might never otherwise have known, embedding HPC as a go-to tool in their computational workflows.

The scientific output from E-CAM is remarkable, both in terms of the development of new algorithms and methods and the related scientific publications with clear benefits for academic and industrial researchers. E-CAM has supported academic and industrial research via pilot projects focused on industrially oriented problems. Our scoping workshops and state-of-the-art workshops on topics of interest for industry represented new forums for discussion with industry.

Dissemination efforts towards the general public have been pursued, specifically through success stories and interviews with industrialists and academics on topics of general interest, and a Comic book about E-CAM and how it enables modelling, simulation and HPC.

Several actions (software development, new formats for workshops) initiated in the project have clearly proved of strategic interest for the community and will be maintained and further developed.

Travail effectué depuis le début du projet jusqu’à la fin de la période considérée dans le rapport et principaux résultats atteints jusqu’à présent

E-CAM built a library of software with more than 200 contributions in the areas of classical molecular dynamics, electronic structure, quantum dynamics and meso- and multi-scale modelling. Many of these have applications in industry and are targeted at solving an industrial problem. E-CAM’s software modules satisfy the E-CAM style guidelines for best-practice programming, documentation and testing.

E-CAM has developed two transversal libraries that tackle issues that become increasingly important when running applications at scale: a high throughput computing library (jobqueue_features) and a load balancing library (ALL). We have disseminated our software through deliverables, the project website, our quarterly newsletters, and at E-CAM workshops and in international conferences. 44 scientific papers related to the software produced in the project were published in international journals, and we have more than 1980 citations so far. All our publications have open access versions available.

Access to leading-edge discussions on software and computer applications has been delivered through our programme of events. We held 7 state-of-the-art and 6 scoping workshops on topics of interest to industry. Industry acted as co-organiser for 5 scoping workshops. 66 industrial researchers accessed E-CAM’s expertise at these events. The outcomes from these meetings have been shared with our target groups through the workshop scientific reports stored on our website, and taken into account in project activities. Support for academic and industrial research was delivered through pilot projects focused on industrial oriented problems, and 116 certified software modules were produced by our PDRAs during these activities.

We have organised 18 Extended Software Development Workshops (ESDWs) and 12 transversal training events, 8 of which in collaboration with PRACE. We trained 474 participants at these events, on topics such as co-design of applications, code rewriting to improve performance, HPC best programming practices, among others. Lectures are stored on our online training infrastructure, which now contains training material on more than 100 topics. The contents of this portal range from talks focused on state of the art methods to tutorials on the writing of robust software and performance optimisation on massively parallel computer platforms.

Progrès au-delà de l’état des connaissances et impact potentiel prévu (y compris l’impact socio-économique et les conséquences sociétales plus larges du projet jusqu’à présent)

E-CAM improved access to software and computer applications via the creation of the E-CAM software library, where open source software is accessible to academics and industry for further research activities.

We have improved competitiveness of companies and SMEs through our pilot projects and via discussions promoted at our workshops. Developments are accessible to users via the E-CAM website and our repository. Furthermore, E-CAM has established a series of new events targeted at training industrial researchers on the simulation and modelling techniques implemented in specific codes and in the direct use of this software for their industrial applications.

E-CAM made significant efforts in improving code performance. The development of the Multi-GPU version of DL_MESO is an example of that. Code performance of individual software packages was also pursed on other codes such as OPS, n2p2, MaZe, Quantics, MPM, PaPIM, ESPResSo++, ParaDiS, Cubble, GC-AdResS. With its activities, E-CAM prepared the user communities towards the exascale. We have strongly contributed to put the community in a position where their entire software stack will be portable to these systems, and created the tools for them to use these resources.

Our impact in training the next generation of scientist was significant through our training events, the engagement with other initiatives such as LearnHPC, EESSI, HPC Carpentry, and the creation of the online training portal. These efforts will continue beyond the EU funding period.

E-CAM helped catalysing and expanding new communities, in particular, through our ESDWs. Examples are the ESL, the quantum dynamics community and the community of rare events.

Our pilot projects have socio-economic impact with applications in drug design, diagnostics, food/dairy industry, materials science, discovery of new materials, clean energy, etc. We have developed a biosensor with applications in detecting COVID-19 and influenza A&B. The sensor is aimed to be accessible, and distributed to impoverished areas or communities in the world.

Finally, E-CAM has pursued a number of activities targeted at bringing HPC to the general public, with highly original activities such as the Comic book “EKHAM the wise”.

ecam-logo.png