Real-time Inference with 2D Convolutional Neural Networks on Field Programmable Gate Arrays for High-rate Particle Imaging Detectors

Abstract

We present a custom implementation of a 2D Convolutional Neural Network (CNN) as a viable application for real-time data selection in high-resolution and high-rate particle imaging detectors, making use of hardware acceleration in high-end Field Programmable Gate Arrays (FPGAs). To meet FPGA resource constraints, a two-layer CNN is optimized for accuracy and latency with KerasTuner, and network quantization is further used to minimize the computing resource utilization of the network. We use "High Level Synthesis for Machine Learning" (hls4ml) tools to test CNN deployment on a Xilinx UltraScale+ FPGA, which is a proposed FPGA technology for the front-end readout system of the future Deep Underground Neutrino Experiment (DUNE) far detector. We evaluate network accuracy and estimate latency and hardware resource usage, and comment on the feasibility of applying CNNs for real-time data selection within the proposed DUNE data acquisition system.

Machine learning in nuclear physics at low and intermediate energies

“…Firmware base ML applications are promising in improving the performance of data acquisitions. In the DUNE experiment, a hardware-accelerated Deep Neural Networks method is proposed for real-time data processing and data selection [155]. An general Python package for machine learning inference in Field Programmable Gate Arrays FPGAs is developed.…”