Fast Neural Network Inference on FPGAs for Triggering on Long-Lived Particles at Colliders
This work addresses the need for efficient triggering in particle physics experiments, though it is incremental as it applies existing FPGA acceleration to a specific domain scenario.
The authors tackled the problem of real-time event selection for long-lived particle decays at the Large Hadron Collider by developing two machine-learning algorithms accelerated on FPGAs, achieving inference times that meet latency requirements without accuracy degradation compared to CPU and GPU setups.
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.