Deep learning applied to solve inverse problems for interferometry

Portable GPU-based parallel algorithms for nuclear fuel simulation on exascale supercomputers

In a context where the standards of high performance computing (HPC) keep evolving, the design of supercomputers includes always more frequently a growing number of accelerators or graphics processing units (GPUs) that provide the bulk of the computing power in most supercomputers. Due to their architectural departures from CPUs and still-evolving software environments, GPUs pose profound programming challenges. GPUs use massive fine-grained parallelism, and thus programmers must rewrite their algorithms and code in order to effectively utilize the compute power.

CEA has developed PLEIADES, a computing platform devoted to simulating nuclear fuel behavior, from its manufacture all the way to its exploitation in reactors and its storage. PLEIADES can count on an MPI distributed memory parallelization allowing simulations to run on several hundred cores and it meets the needs of CEA's partners EDF and Framatome. Porting PLEIADES to use the most recent computing infrastructures is nevertheless essential. In particular providing a flexible, portable and high-performance solution for simulations on supercomputers equipped with GPUs is of major interest in order to capture ever more complex physics on simulations involving ever larger computational domains.

Within such a context the present thesis aims at developing and evaluating different strategies for porting computational kernels to GPUs and at using dynamic load balancing methods tailored to current and upcoming GPU-based supercomputers. The candidate will rely on the tools developed at CEA such as the thermo-mechanical solver MFEM-MGIS [1,2] or MANTA [3]. The software solutions and parallel algorithms proposed with this thesis will eventually enable large 3D multi-physics modeling calculations of the behavior of fuel rods on supercomputers comprising thousands of computing cores and GPUs.

The candidate will work at the PLEIADES Fuel Scientific Computing Tools Development Laboratory (LDOP) of the department for fuel studies (DEC - IRESNE, CEA Cadarache). They will be brought to evolve in a multidisciplinary team composed of mathematicians, physicists, mechanicians and computer scientists. Ultimately, the contributions of the thesis aim at enriching the computing platform for nuclear fuel simulations PLEIADES.

References :[1] MFEM-MGIS - https://thelfer.github.io/mfem-mgis/[2]; Th. Helfer, G. Latu. « MFEM-MGIS-MFRONT, a HPC mini-application targeting nonlinear thermo-mechanical simulations of nuclear fuels at mesoscale ». IAEA Technical Meeting on the Development and Application of Open-Source Modelling and Simulation Tools for Nuclear Reactors, June 2022, https://conferences.iaea.org/event/247/contributions/20551/attachments/10969/16119/Abstract_Latu.docx, https://conferences.iaea.org/event/247/contributions/20551/attachments/10969/19938/Latu_G_ONCORE.pdf; [3] O. Jamond et al. «MANTA : un code HPC généraliste pour la simulation de problèmes complexes en mécanique », https://hal.science/hal-03688160

Dynamic Assurance Cases for Autonomous Adaptive Systems

Providing assurances that autonomous systems will operate in a safe and secure manner is a prerequisite for their deployment in mission-critical and safety-critical application domains. Typically, assurances are provided in the form of assurance cases, which are auditable and reasoned arguments that a high-level claim (usually concerning safety or other critical properties) is satisfied given a set of evidence concerning the context, design, and implementation of a system. Assurance case development is traditionally an analytic activity, which is carried out off-line prior to system deployment and its validity relies on assumptions/predictions about system behavior (including its interactions with its environment). However, it has been argued that this is not a viable approach for autonomous systems that learn and adapt in operation. The proposed PhD will address the limitations of existing assurance approaches by proposing a new class of security-informed safety assurance techniques that are continually assessing and evolving the safety reasoning, concurrently with the system, to provide through-life safety assurance. That is, safety assurance will be provided not only during initial development and deployment, but also at runtime based on operational data.

Assisted generation of complex computational kernels in solid mechanics

The behavior laws used in numerical simulations describe the physical characteristics of simulated materials. As our understanding of these materials evolves, the complexity of these laws increases. Integrating these laws is a critical step for the performance and robustness of scientific computations. Therefore, this step can lead to intrusive and complex developments in the code.

Many digital platforms, such as FEniCS, FireDrake, FreeFEM, and Comsol, offer Just-In-Time (JIT) code generation techniques to handle various physics. This JIT approach significantly reduces the time required to implement new simulations, providing great versatility to the user. Additionally, it allows for optimization specific to the cases being treated and facilitates porting to various architectures (CPU or GPU). Finally, this approach hides implementation details; any changes in these details are invisible to the user and absorbed by the code generation layer.

However, these techniques are generally limited to the assembly steps of the linear systems to be solved and do not include the crucial step of integrating behavior laws.

Inspired by the successful experience of the open-source project mgis.fenics [1], this thesis aims to develop a Just-In-Time code generation solution dedicated to the next-generation structural mechanics code Manta [2], developed by CEA. The objective is to enable strong coupling with behavior laws generated by MFront [3], thereby improving the flexibility, performance, and robustness of numerical simulations.

The doctoral student will benefit from guidance from the developers of MFront and Manta (CEA), as well as the developers of the A-Set code (a collaboration between Mines-Paris Tech, Onera, and Safran). This collaboration within a multidisciplinary team will provide a stimulating and enriching environment for the candidate.

Furthermore, the thesis work will be enhanced by the opportunity to participate in conferences and publish articles in peer-reviewed scientific journals, offering national and international visibility to the thesis results.

The PhD will take place at CEA Cadarache, in south-eastern France, in the Nuclear Fuel Studies Department of the IRESNE Institute [4]. The host laboratory is the LMPC, whose role is to contribute to the development of the physical components of the PLEIADES digital platform [5], co-developed by CEA and EDF.

[1] https://thelfer.github.io/mgis/web/mgis_fenics.html
[2] MANTA : un code HPC généraliste pour la simulation de problèmes complexes en mécanique. https://hal.science/hal-03688160
[3] https://thelfer.github.io/tfel/web/index.html
[4] https://www.cea.fr/energies/iresne/Pages/Accueil.aspx
[5] PLEIADES: A numerical framework dedicated to the multiphysics and multiscale nuclear fuel behavior simulation https://www.sciencedirect.com/science/article/pii/S0306454924002408

CORTEX: Container Orchestration for Real-Time, Embedded/edge, miXed-critical applications

This PhD proposal will develop a container orchestration scheme for real-time applications, deployed on a continuum of heterogeneous computing resources in the embedded-edge-cloud space, with a specific focus on applications that require real-time guarantees.

Applications, from autonomous vehicles, environment monitoring, or industrial automation, applications traditionally require high predictability with real-time guarantees, but they increasingly ask for more runtime flexibility as well as a minimization of their overall environmental footprint.

For these applications, a novel adaptive runtime strategy is required that can optimize dynamically at runtime the deployment of software payloads on hardware nodes, with a mixed-critical objective that combines real-time guarantees with the minimization of the environmental footprint.

A revolution in intervention in complex environments: AI and Digital twins in synergy for innovative and effective solutions.

Scientific Context
The operation of complex equipment, particularly in the nuclear sector, relies on quick and secure access to heterogeneous data. Advances in generative AI, combined with Digital Twins (DT), offer innovative solutions to enhance human-system interactions. However, integrating these technologies into critical environments requires tailored approaches to ensure intuitiveness, security, and efficiency.

Proposed Work
This thesis aims to develop a generative AI architecture enriched with domain-specific data and accessible via mixed reality, enabling a glovebox operator to ask natural language questions. The proposed work includes:

A review of the state-of-the-art on Retrieval-Augmented Generation (RAG), ASR/TTS technologies, and Digital Twins.
The development and integration of a chatbot for nuclear operations.
The evaluation of human-AI interactions and the definition of efficiency and adoption metrics.
Expected Outcomes
The project aims to enhance safety and productivity through optimized interactions and to propose guidelines for the adoption of such systems in critical environments.

Design of asynchronous algorithms for solving the neutron transport equation on massively parallel and heterogeneous architectures

This PhD thesis work aims at designing an efficient solver for the solution to the neutron transport equation in Cartesian and hexagonal geometries for heterogeneous and massively parallel architectures. This goal can be achieved with the design of optimal algorithms with parallel and asynchronous programming models.
The industrial framework for this work is in solving the Boltzmann equation associated to the transportof neutrons in a nuclear reactor core. At present, more and more modern simulation codes employ an upwind discontinuous Galerkin finite element scheme for Cartesian and hexagonal meshes of the required domain.This work extends previous research which have been carried out recently to explore the solving step ondistributed computing architectures which we have not yet tackled in our context. It will require the cou-pling of algorithmic and numerical strategies along with programming model which allows an asynchronousparallelism framework to solve the transport equation efficiently.
This research work will be part of the numerical simulation of nuclear reactors. These multiphysics computations are very expensive as they require time-dependent neutron transport calculations for the severe power excursions for instance. The strategy proposed in this research endeavour will decrease thecomputational burden and time for a given accuracy, and coupled to a massively parallel and asynchronousmodel, may define an efficient neutronic solver for multiphysics applications.
Through this PhD research work, the candidate will be able to apply for research vacancies in highperformance numerical simulation for complex physical problems.

Top