Rambelli(, L. and Coccaro, A. and Di Bello, F. and Giagu, S. and Stocchetti, N. (2024) FPGA inference of Deep Neural Network-based trigger algorithms at Colliders. Il nuovo cimento C, 47 (3). pp. 1-4. ISSN 1826-9885
|
Text
ncc12970.pdf - Published Version Download (113kB) | Preview |
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, this work presents 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 compared with a CPU- and GPU-based hardware setup. The results indicate that all tested architectures fit within the accuracy and 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 machinelearning models with a large number of trainable parameters.
| Item Type: | Article |
|---|---|
| Subjects: | 500 Scienze naturali e Matematica > 530 Fisica |
| Depositing User: | Marina Spanti |
| Date Deposited: | 29 Jul 2024 14:07 |
| Last Modified: | 29 Jul 2024 14:07 |
| URI: | http://eprints.bice.rm.cnr.it/id/eprint/23055 |
Actions (login required)
 |
View Item |
