Fast inference on FPGA for the ATLAS Muon Trigger

Track finding in high-density environments is a key challenge for experiments at modern accelerators. In this presentation we describe the performance obtained running machine learning models studied for the ATLAS Muon High Level Trigger. These mod- els are designed for hit position reconstruction and track pattern recognition with a tracking detector, on a commercially available Xilinx Alveo U50 and Alveo U250. We compare the inference times obtained on a CPU, on a GPU and on the Alveo cards. These tests are done using TensorFlow libraries as well as the TensorRT framework, and software frameworks for AI-based applications acceleration. The inference times obtained are compared to the needs of present and future experiments at LHC.