Inria is the French national research institute for digital sciences. World-class research and technological innovation are part of its DNA, together with the aim of developing and supporting scientific and entrepreneurial projects that create value for France, within a European context.
The institute is strongly involved in programmes aimed at fostering scientific excellence, such as the European Research Council: 59 Grants. Inria makes a firm commitment to Horizon 2020, with which the institute’s strategic plan is aligned. One of Inria’s objectives is to combine scientific excellence with a focus on major European and global societal challenges. Inria is currently involved in more than 150 H2020 funded projects.
In May 2019, Inria obtained the Human Resources Excellence in Research from the European Commission. It is also fully committed via its internal Operational Committee for the assessment of Legal and Ethical risks.
Inria focuses on several scientific themes including core digital technology, digital security, artificial intelligence, quantum computing and High Performance Computing.
The CAMUS team is focusing on developing, adapting and extending automatic parallelizing and optimizing techniques, as well as proof and certification methods, for the efficient use of current and future multi-core processors.
The purpose of the HiePACS project is to perform efficiently frontier simulations arising from challenging research and industrial multiscale applications. The solution of these challenging problems require a multidisciplinary approach involving applied mathematics, computational and computer sciences.
STORM team combines strengths on high level DSLs, heterogeneous runtimes and performance analysis tools to help programmers get the highest efficiency from modern computer architectures in a portable manner.
The goal of the TADaaM project is to design and build a stateful system-wide service layer for for data management in HPC systems.
INRIA Role in TEXTAROSSA
In TextaRossa, Inria will mainly contribute to WPs 1, 4 and 6. Inria will bring its expertise in task-based runtime systems, StarPU, in particular focusing on the integration of FPGAs and the use of dynamic approaches for inference and training, based on RoToR. We will also work on the optimization of communications between CPUs, GPUs and FPGAs. In addition, Inria will work on the adaptation of math kernels such as ScalFMM and Chameleon to the TextaRossa computational node.
• Olivier Beaumont
• Bérenger Bramas
• Lionel Eyraud-Dubois
• Brice Goglin
• Abdou Guermouche
• Raymond Namyst
• Samuel Thibault
E-mail addresses: firstname.lastname@example.org