28 July 2020 to 6 August 2020
virtual conference
Europe/Prague timezone

Muon Trigger using Deep Neural Networks accelerated by FPGAs

29 Jul 2020, 13:39
3m
virtual conference

virtual conference

Poster 11. Accelerator: Physics, Performance, and R&D for Future Facilities Accelerator: Physics, Performance, and R&D for Future Facilities - Posters

Speakers

Jason Lee (University of Seoul (KR)) Youngwan Son (University of Seoul) Ian James Watson (University of Seoul)

Description

Accuracy and latency are crucial to the trigger system in high luminosity particle physics experiments. We investigate the usage of deep neural networks (DNN) to improve the accuracy of the muon track segment reconstruction process at the trigger level. Track segments, made by hits within a detector module, are the initial partial reconstructed objects which are the typical building blocks for muon triggers. Currently, these segments are coarsely reconstructed on FPGAs to keep the latency manageable. DNNs are ideal for these types of pattern recognition problems, and so we examine the potential for DNN based track segment reconstruction to be accelerated by dedicated FPGAs to improve both processing speed and latency for the trigger system.

Secondary track (number) 12

Primary authors

Jason Lee (University of Seoul (KR)) Youngwan Son (University of Seoul) Ian James Watson (University of Seoul) Seungjin Yang (University of Seoul, Department of Physics (KR)) Seulgi Kim (University of Seoul, Department of Physics (KR)) Inkyu Park (University of Seoul, Department of Physics (KR))

Presentation Materials