The ADMIRE project will create a European adaptive storage system to boost data-intensive applications comprising HPC simulation, bioinformatics, and artificial intelligence. The project aims to integrate novel and existing technologies through the co-design of six applications Pillars with high industrial and social relevance: weather forecasting, molecular dynamics, turbulence simulations, planetary scale cover mapping, brain super-resolution imaging, and Software Heritage catalog management and indexing.
ADMIRE aims to deliver an Input/Output software stack and a clearly defined Application Programming Interface for the optimization of data-intensive HPC and machine learning applications. The main objective of the ADMIRE project is to establish this control by creating an active I/O stack that dynamically adjusts computation and storage requirements through intelligent global coordination, malleability of computation and I/O, and the scheduling of storage resources along all levels of the storage hierarchy. To achieve this, we will develop a software-defined framework based on the principles of scalable monitoring and control, separated control and data paths, and the orchestration of key system components and applications through embedded control points.
Funding
The ADMIRE project has received €7.9M funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 956748. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Spain, Germany, France, Italy, Poland, and Sweden.
The funding period starts in April 2021 and lasts until end of March 2024.
Project Partners
- University Carlos III of Madrid (UC3M), Spain, Coordinator
- Barcelona Supercomputing Center (BSC), Spain
- Technische Universität Darmstadt, Germany
- Max Planck Computing and Data Facility (MPCDF), Germany
- Forschungszentrum Jülich (FZJ), Germany
- DDN, France
- Paratools, France
- INRIA, France
- CINI, Italy
- CINECA, Italy
- E4, Italy
- Poznan Supercomputing and Networking Center (PSNC), Poland
- Royal Institute of Technology in Stockholm (KTH), Sweden
External Links
Web site of the Admire project
Official press release
Contact
Publications
2023
- Marc-André Vef, Alberto Miranda, Ramon Nou, and André Brinkmann. 2023. From Static to Malleable: Improving Flexibility and Compatibility in Burst Buffer File Systems. In 2nd International Workshop on Malleability Techniques Applications in High-Performance Computing (HPCMall).
2022
- Nafiseh Moti, Reza Salkhordeh, and André Brinkmann. 2022. Protected Functions: User Space Privileged Function Calls. In Proceedings of the 35th International Conference on the Architecture of Computing Systems (ARCS). Author/Publisher URL
- Yingjin Qian, Wen Cheng, Lingfang Zeng, Marc-André Vef, Oleg Drokin, Andreas Dilger, Shuichi Ihara, Wusheng Zhang, Yang Wang, and André Brinkmann. 2022. MetaWBC: POSIX-compliant metadata write-back caching for distributed file systems. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 795–814.
2021
- Frederic Schimmelpfennig, Marc-André Vef, Reza Salkhordeh, Alberto Miranda, Ramon Nou, and André Brinkmann. 2021. Streamlining distributed Deep Learning I/O with ad hoc file systems. In 2021 IEEE International Conference on Cluster Computing (CLUSTER), 169–180. DOI Author/Publisher URL