Choose timezone
Your profile timezone:
Help us make Indico better by taking this survey! Aidez-nous à améliorer Indico en répondant à ce sondage !
The current approach used for stepping limits the opportunity for having more instruction-level locality that is a prerequisite for CPU/GPU acceleration. Is it possible to have a smooth transition scenario to having track level parallelism in general and step level parallelism for certain computation phases in Geant4?