Ultrafast jet classification on FPGAs for the HL-LHC

Abstract

Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN LHC during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that $O(100)$ ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.

13 pages, 3 figures, 3 tables. Mach. Learn.: Sci. Technol (2024)

References in corpus (19)

• The anti-k_t jet clustering algorithm
• FastJet user manual
• Particle-flow reconstruction and global event description with the CMS detector
• Fast inference of deep neural networks in FPGAs for particle physics
• ParticleNet: Jet Tagging via Particle Clouds
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Graph Neural Networks in Particle Physics
• JEDI-net: a jet identification algorithm based on interaction networks
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Fast inference of Boosted Decision Trees in FPGAs for particle physics
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics
• LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics
• The importance of calorimetry for highly-boosted jet substructure
• Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics
• Fast Neural Network Inference on FPGAs for Triggering on Long-Lived Particles at Colliders

Cited by in corpus (4)

• Jet Discrimination with Quantum Complete Graph Neural Network
• da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
• Fast Jet Tagging with MLP-Mixers on FPGAs
• JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs