The upgrades of the four large experiments of the LHC in the coming years will result in a huge increase of data bandwidth for each which needs to be processed very efficiently. It is a challenging task for which several technologies are being considered, notably FPGA compute accelerators.

LHCb's Christian Faerber has been undertaking a series of performance studies for the LHCb upgrade with HEP algorithms on FPGA compute accelerators, in the context of the High-Throughput-Compute Collaboration with Intel.