PhD Position Modeling and Simulation of Exascale Storage Systems

PhD Position F/M Modeling and Simulation of Exascale Storage Systems

Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people and runs 200 agile project teams, generally in partnership with academia, bringing together more than 3,500 scientists and engineers to address digital‑technology challenges at the interface of multiple disciplines. The Institute also employs numerous talents across over forty professions and 900 research support staff that contribute worldwide.

Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people and 200 agile project teams, generally run jointly with academic partners, including more than 3,500 scientists and engineers working to meet the challenges of digital technology at the interface with other disciplines. The Institute also employs numerous talents in over forty different professions. 900 research support staff contribute to the preparation and development of scientific and entrepreneurial projects that have a worldwide impact.

Theme/Domain : Distributed and High Performance Computing
Scientific computing : BAP E
Town/city : Rennes
Inria Center : Centre Inria de l’Université de Rennes
Starting date : 2024‑09‑01
Duration of contract : 3 years
Final date to receive applications : 2024‑12‑31

• Contract type : Fixed‑term contract
• Level of qualifications required : Graduate degree or equivalent
• Other valued qualifications : Master’s degree
• Fonction : PhD Position

The Inria Rennes – Bretagne Atlantique Centre is one of Inria’s eight centres and has more than thirty research teams. It is a major player in digital sciences and at the heart of a rich R&D and innovation ecosystem involving large industrial groups, competitiveness clusters, research and higher education players, and laboratories of excellence.

–

• François Tessier (Inria)
• Gabriel Antoniu (Inria)
• Philippe Deniel (CEA)
• Thomas Leibovici (CEA)

The thesis, co‑supervised by Inria and CEA, will be hosted by the Ker Data team at the Inria research centre of Rennes and will include regular visits to the CEA Center of Bruyères‑le‑Châtel. Rennes is a dynamic, lively city and a major centre for higher education and research. The thesis will also include collaborations with international partners, especially from the US.

• Ker Data is a human‑sized team currently comprising 5 permanent researchers, 2 contract researchers, 1 engineer and 5 PhD students. You will work in a caring environment, offering a good work‑life balance.
• Ker Data is leading multiple projects in national and international collaborative environments such as the Joint‑Laboratory on Extreme‑Scale Computing.
• Our team strongly favours experimental research validated by implementation and experimentation of software prototypes on real‑world platforms.
• The Ker Data team is committed to personalized advising and coaching, to help PhD candidates train and grow.
• Check our website for more about the Ker Data team: (Use the "Apply for this Job" box below)./

–

Large‑scale scientific domains such as radio‑astronomy or weather forecast require computing power and data‑processing capacity beyond current machines. Supercomputers capable of reaching the exascale are becoming necessary, but efficient use of these systems raises new challenges, especially regarding data management.

This PhD thesis proposes to model and simulate heterogeneous storage systems to study their behavior, predict their performance and propose innovative algorithmic approaches for better resource utilization.

Initially, storage systems such as Lustre and DAOS will be studied, modeled and simulated using the existing WRENCH‑based simulator Stor Alloc. Next, advanced resource allocation algorithms will be proposed, implemented and evaluated in the simulator. International collaborations, especially with the University of Manoa (HI, USA), and national partnership with the French

SKA team will provide relevant use‑cases. The…