Parallelise SPARKX #306
Description
Currently, all data is read in sequentially. Processing of particle quantities happens sequentially too. This is seen as in general acceptable, as often observables are calculated event-per-event, with single event execution times rather small. Therefore, we have embarassingly parellelizable problems.
However, currently, this parallelisation is left to the user. Future SPARKX should offer to split calculation on multiple cores and distribute events. This has to happen potentially at read-in and in some of the most important classes. Especially Lattice calculations are slow.
Future maintainers will probably want to look into an option to shift calculation to GPU as far as possible.
Note: this is probably connected to #304