Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Parallelise SPARKX #306

Open
NGoetz opened this issue Nov 7, 2024 · 0 comments
Open

Parallelise SPARKX #306

NGoetz opened this issue Nov 7, 2024 · 0 comments
Labels
enhancement New feature or request low priority Not important to do
Milestone
SPARKX 3.0

Comments

@NGoetz
Copy link
Member

NGoetz commented Nov 7, 2024 •
edited
Loading

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
@NGoetz NGoetz added enhancement New feature or request low priority Not important to do labels Nov 7, 2024
@NGoetz NGoetz added this to the SPARKX 3.0 milestone Nov 7, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request low priority Not important to do
Projects
None yet
Milestone
SPARKX 3.0
Development

No branches or pull requests
1 participant
@NGoetz