Real-time highly-parallel tracking processing with FPGA at LHCb
Abstract
For the future high luminosity LHC runs, it is expected to reconstruct events more complex than the actual ones. in view of this need, the LHCb Collaboration has established a testbed for heterogeneous computing equipment to develop solutions for real-time event reconstruction integrated with the LHCb DAQ infrastructure. The most advanced one is a highly-parallelized tracking processor, based on the "Artificial Retina", which uses a set of FPGA, to which the data are distributed using a custom optical mesh with high speed links. The aim at the testbed is to implement a demonstrator for the tracking of pixel detectors, able to manage the data of a sector of a detector. The scalability to a full size processor will be discussed, as well as the DAQ integration issues for a system running on real data.
Related Papers
- → A hovercraft testbed for decentralized and cooperative control(2004)29 cited
- → A networked and cooperative control testbed(2004)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
- → Ditto Subsystem : A Case Study for Building Experiment Environment in StarBED Using TopDL(2017)
- → Deterlab testbed for cybersecurity research and education(2013)