GPUs for fast triggering and pattern matching at the CERN experiment NA62

In high energy physics experiment the trigger system is crucial to reduce the quantity of data recorded on tape and the acquisition bandwidth requirements. This is particularly true in rare decays experiments. The NA62 experiment aims at measuring the Branching Ratio of K+ -> π+νν, predicted in the Standard Model (SM) at level of ~ 10 -10. In this paper we describe the idea to use the commercial video card processor (GPU) to construct a fast and effective trigger system, both in hardware and software level. Due to the use of off the shelf technology, in continuous development for other purposes, the architecture described would be easily exported to other experiments, to build a versatile and fully customizable trigger system.