We will discuss some performance measures obtained in an HPC cluster when running RDataFrame with Dask. In particular, we will compare multi-processing versus implicit multi-threading in RDF tasks and we will give an update on processing throughput measures.
Speakers:
Enric Tejedor Saavedra(CERN), Ivan Kabadzhov(Albert Ludwig University of Freiburg), Vincenzo Eduardo Padulano(Valencia Polytechnic University (ES))