Tracking, Vertexing and data handling strategy for the LHCb upgrade

For Run III (2021 onwards) of the LHC, LHCb will take data at an instantaneous luminosity of $2 \times 10^{33} \mathrm{cm}^{-2} \mathrm{s}^{-1}$, five times higher than in Run II (2015-2018). To cope with the harsher data taking conditions, the LHCb collaboration will upgrade the DAQ system and install a purely software based trigger, in addition to various detector upgrades. The high readout rate contributes to the challenge of reconstructing and selecting events in real time. Special emphasis in this contribution will be put on the need for fast track reconstruction in the software trigger. The modified detector infrastructure will be able to face this challenge and the necessary changes to the reconstruction sequence are discussed. A novel strategy is presented which distributes and maximises the bandwidth among the different physics channels using a genetic algorithm. The data processing chain includes a redesign of the event scheduling, introduction of concurrent processing, optimisations in processor cache accesses and code vectorisation. Furthermore changes in the areas of event model, conditions data and detector description are foreseen.