DIANA-HEP: Analysis Functions:: Implementation and optimization of common particle physics analysis algorithms in a functional paradigm
- Mentors
- David Lange, Jim Pivarski
- Organization
- CERN-HSF
High Energy Particle physics experiments typically generate a large amount of data. To analyze them requires significant computing resources. This is however, limited and expensive to get. Thus, it is necessary to make optimum utilization of the resources to keep research fast and active. This requires an alternative approach to procedural programming, utilizing a vectorized, concurrent programming in a functional style, while maintaining a easy to use user interface for programming.
This Project aims to mitigate some of the issues, by building vectorized, fast primitives as well as several higher level functions, for fast prototyping, while maintaining speed. Furthermore, an experimental GPU offloading for concurrent processing of selected algorithms will also be implemented, and can be extended in he future. The library will be documented, and interfaces can be provided, to allow integration with other projects.