28 July 2020 to 6 August 2020
virtual conference
Europe/Prague timezone

What the new RooFit can do for your analysis

28 Jul 2020, 16:50
virtual conference

virtual conference

Talk 14. Computing and Data Handling Computing and Data Handling


Stephan Hageboeck (CERN)


RooFit is a toolkit for statistical modelling and fitting, and together with RooStats it is used for measurements and statistical tests by most experiments in particle physics.
Since one year, RooFit is being modernised. In this talk, improvements already released with ROOT will be discussed, such as faster data loading, vectorised computations and more standard-like interfaces. These allow for speeding up unbinned fits by several factors, and make RooFit easier to use from both C++ and python.
Furthermore, an overview of features in development is given, such as a fast implementation of "HistFactory" computations, easier data loading, and the prospects for RooFit computations on GPUs.

Primary author

Presentation Materials