Fast Neural Network Inference on FPGAs for Triggering on Long-Lived Particles at Colliders

Abstract

Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation. Heterogeneous computing with the employment of FPGA cards may emerge as a trending technology for the triggering strategy of the upcoming high-luminosity program of the Large Hadron Collider at CERN. In this context, we present two machine-learning algorithms for selecting events where neutral long-lived particles decay within the detector volume studying their accuracy and inference time when accelerated on commercially available Xilinx FPGA accelerator cards. The inference time is also confronted with a CPU- and GPU-based hardware setup. The proposed new algorithms are proven efficient for the considered benchmark physics scenario and their accuracy is found to not degrade when accelerated on the FPGA cards. The results indicate that all tested architectures fit within the latency requirements of a second-level trigger farm and that exploiting accelerator technologies for real-time processing of particle-physics collisions is a promising research field that deserves additional investigations, in particular with machine-learning models with a large number of trainable parameters.

arXiv comment12 pages, 10 figures, 2 tables

References in corpus (16)

• Echoes of a Hidden Valley at Hadron Colliders
• The CMS trigger system
• Discovering the Higgs Through Highly-Displaced Vertices
• Jet-Images -- Deep Learning Edition
• Searching for long-lived particles beyond the Standard Model at the Large Hadron Collider
• Anomaly Detection for Resonant New Physics with Machine Learning
• Operation of the ATLAS trigger system in Run 2
• Fast convolutional neural networks on FPGAs with hls4ml
• Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML
• Hidden Higgs Decaying to Lepton Jets
• Triggers for displaced decays of long-lived neutral particles in the ATLAS detector
• Discovering Higgs Decays to Lepton Jets at Hadron Colliders
• FPGA-accelerated machine learning inference as a service for particle physics computing
• Studies of the muon momentum calibration and performance of the ATLAS detector with $pp$ collisions at $\sqrt{s}$=13 TeV
• Data-driven Model-independent Searches for Long-lived Particles at the LHC
• Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network

Cited by in corpus (3)

• Ultrafast jet classification on FPGAs for the HL-LHC
• BitHEP -- The Limits of Low-Precision ML in HEP
• On the Utility Function of Experiments in Fundamental Science