GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, UK
Journal of Physics: Conference Series, Volume 396, Part 1, 012018, 2012
@article{emeliyanov2012gpu,
title={GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger},
author={Emeliyanov, D. and Howard, J.},
journal={Computing},
year={2012}
}
Results on the performance and viability of data-parallel algorithms on Graphics Processing Units (GPUs) in the ATLAS Level 2 trigger system are presented. We describe the existing trigger data preparation and track reconstruction algorithms, motivation for their optimization, GPU-parallelized versions of these algorithms, and a "client-server" solution for hybrid CPU/GPU event processing used for integration of the GPU-oriented algorithms into existing ATLAS trigger software. The resulting speed-up of event processing times obtained with high-luminosity simulated data is presented and discussed.
December 29, 2012 by hgpu
