Current projects

ANR JCJC Foutics, 2023 - 2026, 282 k€, leader

The aim of the FOUTICS project is to propose full-stack, open-source methods and tools to train and infer ultra-lightweight AIs, by extending, implementing, and optimizing Tangled Program Graphs (TPGs). Exploiting the TPG efficiency and integrating energy optimization at its core, FOUTICS will create methodologies to implement energy efficient AI, capable of nanoseconds reaction time on hardware platforms ranging from Ultra-Low Power embedded devices to reconfigurable devices. Extending TPGs to new learning environments, FOUTICS will enable real world Cyber-Physical System use cases and will optimize energy use from training to physical execution on the factory floor.

ANR PRC TrustGW, 2022 - 2025, 476 k€, participant

  • Partners: LabSTIC (leader), IRISA, INSA Rennes

The TrustGW project therefore aims to develop a dynamically reconfigurable heterogeneous software-hardware gateway architecture that can be trusted. The implementation of such an architecture guaranteeing confidentiality, integrity, availability and authentication properties is original. In the framework of the TrustGW project, three main scientific challenges are addressed:

  • To design a heterogeneous software-hardware gateway architecture that is trusted and dynamically reconfigurable;
  • To propose a trusted hypervisor that allows the deployment of virtual machines on a heterogeneous software-hardware architecture with resource virtualization;
  • Guarantee the security of applications within virtual machines.

ANR PRC DARK ERA, 2021 - 2025, 499 k€, participant

  • Partners: L2S (leader), INSA Rennes, IRISA, Observatoire de Nançay, Lagrange, ATOS

The Dark Era ANR project aims at tackling some of the High-Performance Computing (HPC) challenge behind the Square Kilometer Array (SKA) exascale radio telescope. Objectives of the project are:

Building SimSDP, a rapid prototyping tool providing exascale simulations from dataflow algorithm description. Exploring low power accelerators like FPGA or Kalray MPPA as alternatives to mainstream GPU architecture. Being source of proposals for SKA computing and promoting French contributions to the international SKA consortium.

Previous projects

FEDER RAISE, 2019 - 2022, 282 k€, participant

  • Partners: EDIXIA (leader), INSA Rennes, PSA Groupe

The project RAISE aims at defining, developing and commercializing technological components based on artificial intelligence to enable robotic assembly and inspections operations on moving pieces with no physical link with the environment or predefined trajectory. Automatic assembly on moving chain will answer the challenges of flexibility and compacity of industry 4.0. IETR will develop a flexible design method adapted to the industry 4.0. It aims to enable automatic and optimized porting of new algorithms on heterogeneous reconfigurable embedded systems.