Abstract
The GeantV project is focused on the R&D of new particle transport techniques to maximize parallelism on multiple levels, profiting from the use of both SIMD instructions and co-processors for the CPU-intensive calculations specific to this type of applications. In our approach, vectors of tracks belonging to multiple events and matching different locality criteria must be gathered and dispatched to algorithms having vector signatures. While the transport propagates tracks and changes their individual states, data locality becomes harder to maintain. The scheduling policy has to be changed to maintain efficient vectors while keeping an optimal level of concurrency. The model has complex dynamics requiring tuning the thresholds to switch between the normal regime and special modes, i.e. prioritizing events to allow flushing memory, adding new events in the transport pipeline to boost locality, dynamically adjusting the particle vector size or switching between vector to single track mode when vectorization causes only overhead. This work requires a comprehensive study for optimizing these parameters to make the behaviour of the scheduler self-adapting, presenting here its initial results.
Highlights
The “why” part of the observation above is very important for understanding what can be done in the future besides just scaling up the resources, and using them more efficiently
Published under licence by IOP Publishing Ltd triggered the investigation and prototyping work that started in 2011 and which is the base for the current R&D behind the GeantV project [1]
Looking at the main reasons for the low number of instructions per cycle of about 0.8 in particle transport simulations and HEP code in general, we can identify a large range of sources, starting with abusing object-oriented design in data access patterns and ending with poor data and code locality caused by the sequential nature of the classical particle transport approach
Summary
The “why” part of the observation above is very important for understanding what can be done in the future besides just scaling up the resources, and using them more efficiently. The main idea behind the first version of the GeantV prototype was changing the basic work unit for transport simulation from a single particle to a vector of particles fulfilling geometry locality criteria.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
