A5057790459- Distributed and Parallel Computing Systems
- Cloud Computing and Resource Management
- Advanced Data Storage Technologies
- Scientific Computing and Data Management
- Parallel Computing and Optimization Techniques
- Data Visualization and Analytics
- Distributed systems and fault tolerance
- Catalytic Processes in Materials Science
- Modular Robots and Swarm Intelligence
- Peer-to-Peer Network Technologies
- Multimedia Communication and Technology
- scientometrics and bibliometrics research
- Conservation Techniques and Studies
- Simulation Techniques and Applications
- Image Processing and 3D Reconstruction
- Meta-analysis and systematic reviews
- Robotics and Automated Systems
Centre National de la Recherche Scientifique
2015-2024
Institut de Recherche en Informatique de Toulouse
2022-2024
Université Toulouse - Jean Jaurès
2023-2024
Université Toulouse III - Paul Sabatier
2023-2024
Université Toulouse-I-Capitole
2023-2024
Institut Polytechnique de Bordeaux
2023-2024
Université de Toulouse
2024
Laboratoire d'Informatique de Grenoble
2015-2022
Centre Inria de l'Université Grenoble Alpes
2015-2022
Université Grenoble Alpes
2015-2022
Energy consumption has become one of the mostcritical issues in evolution High Performance Computingsystems (HPC). Controlling energy HPCplatforms is not only a way to control cost but also stepforward on road towards exaflops. Powercapping widelystudied technique that guarantees platform will notexceed certain power threshold instantaneously it givesno flexibility adapt job scheduling longer term energybudget control. We propose mechanism extends thebackfilling algorithm energy-aware....
The interactive scientific visualization applications are based on heterogeneous codes to implement simulation or data processing, and interaction parts. These different parts need be precisely assembled construct an efficient application running in time. Component-based approach is a good paradigm express this kind of applications. domain now classically extended with visual analysis In case, some the added removed dynamically during its execution. paper, we describe component-based...
Development of environments for distributed systems is a tedious and time-consuming iterative process. The reproducibility such crucial factor rigorous scientific contributions. We think that being able to smoothly test both locally on target dis-tributed platform makes development cycles faster reduces the friction adopt better experimental practices. To address this issue, paper introduces notion environment transposition implements it in NixOS Compose, tool generates reproducible...