SPACE
Scalable Parallel Astrophysical Codes for Exascale
High Performance Computing (HPC)
In Astrophysics and Cosmology (A&C) today, High Performance Computing (HPC)-based numerical simulations are exceptional tools for scientific discovery. They are essential instruments and theoretical laboratories capable of investigating, interpreting, and understanding the physical processes underlying the observed sky. For these laboratories, the efficient and effective exploitation of exascale computing capabilities is vital.
The main specific objective of SPACE is to enable the most widely used European A&C HPC codes (which are also among the most widely used worldwide) to efficiently and effectively exploit the pre-exascale systems funded by EuroHPC Joint Undertaking and available at the end of 2022, and to prepare them for the transition to exascale and beyond.
The SPACE Centre of Excellence aims to extensively re-engineer the target codes to interface with new computing solutions and adopt innovative programming and software paradigms, solutions, and libraries. SPACE aims to foster the reuse and sharing of algorithms and software components within the A&C application domain, through joint design activities that bring together scientists, code developers, HPC experts, hardware manufacturers, and software developers, thereby advancing lighthouse exascale A&C applications, codes, services, and expertise by promoting the use of incoming exascale and post-exascale computing capabilities.
SPACE will address high-performance analysis of the data torrent produced by exascale A&C simulation applications using machine-learning and visualization tools. The deployment of applications running on different platforms will be facilitated by pooling capabilities focused on code repositories and data sharing, and by integrating European astrophysical communities around exascale computing by adopting software and data standards and interoperability protocols.
EnginSoft is the leader of work packages WP4 and WP5. WP4 provides and deploys services to these processes such as a continuous integration platform, and an Internal Data Archive (IDA) for internal data (benchmarks datasets, benchmark results and metrics) that will be the source of co-design feedback and internal analysis on the impact of the routing and operations (R&O) cycle on the codes.
WP5 addresses the dissemination of the project results, focusing on communication, training activities, and user support to encourage and foster the engagement of the scientific community and a much wider public awareness.
EnginSoft is also the deputy coordinator for all financial and administrative matters of the Centre of Excellence and its interactions with the EuroHPC Joint Undertaking and MIMIT (the Ministero delle Imprese e del Made in Italy or Ministry of Enterprise and Made-in-Italy Manufacturing).
Università degli Studi di Torino | BARCELONA SUPERCOMPUTING CENTER-CENTRO NACIONAL DE SUPERCOMPUTACION | CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE | CINECA | E4 Computer Engineering SPA | EnginSoft SPA | EVIDEN (BULL SAS) | IDRYMA TECHNOLOGIAS KAI EREVNAS | HITS GGMBH | Istituto Nazionale di Astrofisica (INAF) | IT4Innovations National Supercomputing Center | JOHANN WOLFGANG GOETHE-UNIVERSITAET FRANKFURT AM MAIN | KATHOLIEKE UNIVERSITEIT LEUVEN | LUDWIG-MAXIMILIANS-UNIVERSITAET MUENCHEN | UNIVERSITETET I OSLO
Funded by the European Union. This work has received funding from the European High Performance Computing Joint Undertaking (JU) and Belgium, Czech Republic, France, Germany, Greece, Italy, Norway, and Spain under grant agreement No 101093441. | Call identifier: Centres of Excellence for HPC Applications – Horizon-EuroHPC-JU-2021-COE-01
48 months
January 2023 - December 2026
Università degli Studi di Torino
Gino Perna, Marisa Zanotti
15
Some of our competences in research and technology transfer
Research project
The ISAF – Integrated Smart Assembly Factory – project was created to address the problem of joining two or more large parts/structures made of composite materials and therefore affected by the natural variability of the manufacturing process. The variability creates empty space (“gap”) between the parts of the joint .
Research project
DigiPrime will create and operate a federated model of digital platforms by developing reliable data sharing mechanisms and preserving the confidentiality of business-critical data, governed by smart contracts and using block-chain tracking.
Research project
The goal of the project was to design a full Plant Characterization Unit (PCU) chamber with a completely sealed environment for the plants and roots. The designed plant control unit inherited the know-how from two previous projects, HySSE and AtSSE.