An evaluation of GPUs for use in an upgraded ATLAS High Level Trigger

ATLAS is a general purpose particle physics experiment located on the LHC collider at CERN. The ATLAS Trigger system consists of two levels, the first level (L1) implemented in hardware and the High Level Trigger (HLT) implemented in software running on a farm of commodity CPU. The HLT reduces the trigger rate from the 100 kHz L1 accept rate to 1 kHz for recording requiring an average per-event processing time of ~250 ms for this task. The HLT selection is based on reconstructing tracks in the Inner Detector and Muon Spectrometer and clusters of energy deposited in the Calorimeter. Performing this reconstruction within the available HLT farm resources presents a significant challenge that will increase significantly after future LHC upgrades resulting in higher detector occupancies. General purpose Graphics Processor Units (GPGPU) are being evaluated for possible future inclusion in an upgraded HLT farm. We report on a demonstrator that has been developed consisting of GPGPU implementations of the Calorimeter clustering and Inner Detector and Muon tracking integrated within the HLT software framework. We give a brief overview of the algorithms implementation and present preliminary measurements comparing the performance of the algorithms implemented on GPU with the CPU versions.