Fast online triggering in high-energy physics experiments using GPUs

We discuss an approach for using commercial graphic processors (GPUs) at the earliest trigger stages in high-energy physics experiments, and study its implementation on a real trigger system in preparation. Latency and processing rate measurements on several state-of-the-art devices are presented, and potential issues related to processing time jitter and data transfer throughput are discussed. GPUs might act as the missing link to allow present implementations of large DAQ systems to be entirely based on commodity devices.