Fast and resource-efficient Deep Neural Network on FPGA for the Phase-II Level-0 muon barrel trigger of the ATLAS experiment

Proceedings of parallel talk at CHEP 2019. The Level-0 muon trigger system of the ATLAS experiment will undergo a full upgrade for HL-LHC to stand the challenging requirements imposed by the increase in instantaneous luminosity. The upgraded trigger system will send raw hit data to off-detector processors, where trigger algorithms run on new generation of FPGA. To exploit the flexibility provided by the FPGA systems, ATLAS is developing novel precision deep neural network architectures based on trained ternary quantization, optimised to run on FPGA for efficient reconstruction and identification of muons in the ATLAS level-0 trigger. Physics performances in terms of efficiency and fake rates, and FPGA logic resource occupancy and timing obtained with the developed algorithms are discussed.